James
commited on
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +71 -0
- config.json +41 -0
- generation_config.json +9 -0
- hf_quant_config.json +14 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +990 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +195 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
metrics:
|
| 4 |
+
- accuracy
|
| 5 |
+
base_model:
|
| 6 |
+
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<div align="center">
|
| 10 |
+
<h1> POLARIS </h1>
|
| 11 |
+
<div>
|
| 12 |
+
🌠 A <strong>PO</strong>st-training recipe for scaling R<strong>L</strong> on <strong>A</strong>dvanced <strong>R</strong>eason<strong>I</strong>ng model<strong>S</strong> 🚀
|
| 13 |
+
</div>
|
| 14 |
+
</div>
|
| 15 |
+
<br>
|
| 16 |
+
|
| 17 |
+
<div align="center" style="line-height: 1;">
|
| 18 |
+
<a href="https://github.com/ChenxinAn-fdu/POLARIS" style="margin: 2px;">
|
| 19 |
+
<img alt="Code" src="https://img.shields.io/badge/POLARIS-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 20 |
+
</a>
|
| 21 |
+
<a href="https://honorable-payment-890.notion.site/POLARIS-A-POst-training-recipe-for-scaling-reinforcement-Learning-on-Advanced-ReasonIng-modelS-1dfa954ff7c38094923ec7772bf447a1" target="_blank" style="margin: 2px;">
|
| 22 |
+
<img alt="Blog" src="https://img.shields.io/badge/Notion-%23000000.svg?style=for-the-badge&logo=notion&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 23 |
+
</a>
|
| 24 |
+
<a href="https://x.com/AnChancy46881/status/1936099024769368506" style="margin: 2px;">
|
| 25 |
+
<img alt="Twitter" src="https://img.shields.io/badge/Twitter-white?style=for-the-badge&logo=twitter&logoColor=000&color=000&labelColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 26 |
+
</a>
|
| 27 |
+
<a href="commingsoon" style="margin: 2px;">
|
| 28 |
+
<img alt="Paper" src="https://img.shields.io/badge/Paper-%23000000.svg?style=for-the-badge&logo=arxiv&logoColor=000&color=000&labelColor=white" style="display: inline-block; vertical-align: middle;"/>
|
| 29 |
+
</a>
|
| 30 |
+
</div>
|
| 31 |
+
|
| 32 |
+
## Overview
|
| 33 |
+
Polaris is an open-source post-training method that uses reinforcement learning (RL) scaling to refine and enhance models with advanced reasoning abilities. Our research shows that even top-tier models like Qwen3-4B can achieve significant improvements on challenging reasoning tasks when optimized with Polaris.
|
| 34 |
+
By leveraging open-source data and academic-level resources, Polaris pushes the capabilities of open-recipe reasoning models to unprecedented heights. In benchmark tests, our method even surpasses top commercial systems, including Claude-4-Opus, Grok-3-Beta, and o3-mini-high (2025/01/03).
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
## Polaris's Recipe
|
| 38 |
+
- **Data Difficulty:** Before training, Polaris analyzes and maps the distribution of data difficulty. The dataset should not be overwhelmed by either overly difficult or trivially easy problems. We recommend using a data distribution with a slight bias toward challenging problems, which typically exhibits a mirrored J-shaped distribution.
|
| 39 |
+
- **Diversity-Based Rollout:** We leverage the *diversity among rollouts* to initialize the sampling temperature, which is then progressively increased throughout the RL training stages.
|
| 40 |
+
- **Inference-Time Length:** Polaris incorporates length extrapolation techniques for generating longer CoT at inference stage. This enables a *"train-short, generate-long"* paradigm for CoT reasoning, mitigating the computational burden of training with excessively long rollouts .
|
| 41 |
+
- **Exploration Efficiency:** Exploration efficiency in Polaris is enhanced through multi-stage training. However, reducing the model's response length in the first stage poses potential risks. A more conservative approach would be to directly allow the model to "think longer" from the beginning.
|
| 42 |
+
|
| 43 |
+
The details of our training recipe and analysis can be found in our [blog post](https://hkunlp.github.io/blog/2025/Polaris).
|
| 44 |
+
The code and data for reproducing our results can be found in our [github repo](https://github.com/ChenxinAn-fdu/POLARIS).
|
| 45 |
+
|
| 46 |
+
### Evaluation Results
|
| 47 |
+
|
| 48 |
+
| **Models** | **AIME24 avg@32** | **AIME25 avg@32** | **Minerva Math avg@4** | **Olympiad Bench avg@4** | **AMC23 avg@8** |
|
| 49 |
+
| --- | --- | --- | --- | --- | --- |
|
| 50 |
+
| Deepseek-R1-Distill-Qwen-7B | 55.0 | 39.7 | 36.7 | 56.8 | 81.9 |
|
| 51 |
+
| AReal-boba-RL-7B | 61.9 | 48.3 | 39.5 | 61.9 | 86.4 |
|
| 52 |
+
| Skywork-OR1-7B-Math | 69.8 | 52.3 | **40.8** | 63.2 | 85.3 |
|
| 53 |
+
| **`POLARIS-7B-Preview`** | **72.6** | **52.6** | 40.2 | **65.4** | **89.0** |
|
| 54 |
+
| Deepseek-R1-Distill-Qwen-32B | 72.6 | 54.9 | 42.1 | 59.4 | 84.3 |
|
| 55 |
+
| qwen3-32B | 81.4 | 72.9 | 44.2 | 66.7 | 92.4 |
|
| 56 |
+
| qwen3-4B | 73.8 | 65.6 | 43.6 | 62.2 | 87.2 |
|
| 57 |
+
| **`POLARIS-4B-Preview`** | **81.2** | **79.4** | **44.0** | **69.1** | **94.8** |
|
| 58 |
+
|
| 59 |
+
## Acknowledgements
|
| 60 |
+
The training and evaluation codebase is heavily built on [Verl](https://github.com/volcengine/verl). The reward function in polaris in from [DeepScaleR](https://github.com/agentica-project/rllm). Our model is trained on top of [`Qwen3-4B`](https://huggingface.co/Qwen/Qwen3-4B) and [`DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B). Thanks for their wonderful work.
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
## Citation
|
| 64 |
+
```bibtex
|
| 65 |
+
@misc{Polaris2025,
|
| 66 |
+
title = {POLARIS: A Post-Training Recipe for Scaling Reinforcement Learning on Advanced Reasoning Models},
|
| 67 |
+
url = {https://hkunlp.github.io/blog/2025/Polaris},
|
| 68 |
+
author = {An, Chenxin and Xie, Zhihui and Li, Xiaonan and Li, Lei and Zhang, Jun and Gong, Shansan and Zhong, Ming and Xu, Jingjing and Qiu, Xipeng and Wang, Mingxuan and Kong, Lingpeng}
|
| 69 |
+
year = {2025}
|
| 70 |
+
}
|
| 71 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151646,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 3584,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 18944,
|
| 12 |
+
"max_position_embeddings": 131072,
|
| 13 |
+
"max_window_layers": 28,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 28,
|
| 16 |
+
"num_hidden_layers": 28,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.51.3",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"use_mrope": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 152064,
|
| 30 |
+
"quantization_config": {
|
| 31 |
+
"ignore": [
|
| 32 |
+
"lm_head"
|
| 33 |
+
],
|
| 34 |
+
"quant_algo": "NVFP4",
|
| 35 |
+
"kv_cache_scheme": "FP8",
|
| 36 |
+
"producer": {
|
| 37 |
+
"name": "modelopt",
|
| 38 |
+
"version": "0.31.0"
|
| 39 |
+
}
|
| 40 |
+
}
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.51.3"
|
| 9 |
+
}
|
hf_quant_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"producer": {
|
| 3 |
+
"name": "modelopt",
|
| 4 |
+
"version": "0.31.0"
|
| 5 |
+
},
|
| 6 |
+
"quantization": {
|
| 7 |
+
"quant_algo": "NVFP4",
|
| 8 |
+
"kv_cache_quant_algo": "FP8",
|
| 9 |
+
"group_size": 16,
|
| 10 |
+
"exclude_modules": [
|
| 11 |
+
"lm_head"
|
| 12 |
+
]
|
| 13 |
+
}
|
| 14 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a6609cc37a71333879028d3c01b9049f81bfe8021690332055db56b80209cd4
|
| 3 |
+
size 4761244880
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27e9696613a97b608b74b5e8f744b9e953c82cb972d1134d6d88235cd477915d
|
| 3 |
+
size 1089994880
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,990 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5851132672
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.0.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.0.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.1.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.1.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.1.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.1.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.1.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.1.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.1.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.1.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.1.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.1.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.1.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.10.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.10.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.10.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.10.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.10.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.10.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.10.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.10.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.10.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.10.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.10.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.10.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.10.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.10.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.11.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.11.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.11.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.11.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.11.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.11.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.11.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.11.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.11.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.11.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.11.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.11.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.12.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.12.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.12.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.12.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.12.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.12.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.12.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.12.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.12.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.12.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.12.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.12.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.12.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.12.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.13.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.13.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.13.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.13.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.13.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.13.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.13.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.13.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.13.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.13.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.13.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.13.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.13.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.13.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.13.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.14.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.14.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.14.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.14.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.14.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.14.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.14.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.14.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.14.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.14.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.14.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.14.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.14.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.14.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.14.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.14.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.15.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.15.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.15.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.15.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.15.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.15.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.15.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.15.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.15.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.15.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.15.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.15.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.15.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.15.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.16.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.16.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.16.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.16.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.16.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.16.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.16.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.16.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.16.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.16.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.16.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.16.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.16.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.16.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.16.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.16.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.17.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.17.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.17.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.17.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.17.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.17.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.17.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.17.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.17.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.17.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.17.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.17.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.17.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.17.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.17.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.17.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.18.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.18.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.18.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.18.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.18.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.18.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.18.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.18.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.18.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.18.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.18.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.18.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.18.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.18.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.18.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.18.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.19.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.19.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.19.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.19.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.19.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.19.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.19.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.19.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.19.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.19.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.19.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.19.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.19.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.19.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.19.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.19.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.2.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.2.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.2.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.2.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.2.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.2.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.2.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.2.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.2.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.2.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.2.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.2.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.20.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.20.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.20.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.20.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.20.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.20.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.20.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.20.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.20.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.20.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.20.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.20.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.20.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.20.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.20.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.20.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.21.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.21.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.21.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.21.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.21.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.21.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.21.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.21.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.21.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.21.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.21.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.21.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.21.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.layers.21.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.21.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.layers.21.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.22.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.22.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.22.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.22.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.22.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.22.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.22.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.22.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.22.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.22.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.22.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.22.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.22.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.22.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.22.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.22.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.23.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.23.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.23.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.23.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.23.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.23.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.23.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.23.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.23.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.23.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.23.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.23.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.23.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.23.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.23.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.23.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.24.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.24.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.24.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.layers.24.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.layers.24.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.layers.24.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.layers.24.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.layers.24.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.24.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.layers.24.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.layers.24.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.layers.24.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.layers.24.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.24.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.layers.24.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.layers.24.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.layers.25.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.layers.25.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.layers.25.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.layers.25.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.layers.25.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.layers.25.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.layers.25.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.layers.25.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.layers.25.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.layers.25.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.layers.25.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.layers.25.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.layers.25.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.layers.25.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.layers.25.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.layers.25.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.layers.26.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.layers.26.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.layers.26.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.layers.26.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.layers.26.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.layers.26.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.layers.26.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.layers.26.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.layers.26.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.layers.26.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.layers.26.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.layers.26.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.layers.26.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.layers.26.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.layers.26.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.layers.26.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.layers.27.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.layers.27.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.layers.27.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.layers.27.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.layers.27.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.layers.27.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.layers.27.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 724 |
+
"model.layers.27.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 725 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.layers.27.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 728 |
+
"model.layers.27.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 729 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 731 |
+
"model.layers.27.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 732 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"model.layers.27.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 734 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 736 |
+
"model.layers.27.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 737 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 738 |
+
"model.layers.27.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 739 |
+
"model.layers.27.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 740 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 741 |
+
"model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 742 |
+
"model.layers.27.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 743 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 745 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 747 |
+
"model.layers.3.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 748 |
+
"model.layers.3.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.layers.3.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.layers.3.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.layers.3.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.layers.3.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.layers.3.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 762 |
+
"model.layers.3.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 763 |
+
"model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 764 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 766 |
+
"model.layers.3.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 767 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 768 |
+
"model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 769 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 771 |
+
"model.layers.3.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 772 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 774 |
+
"model.layers.3.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 775 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 777 |
+
"model.layers.3.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 778 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 779 |
+
"model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 780 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 781 |
+
"model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 782 |
+
"model.layers.4.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 783 |
+
"model.layers.4.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 784 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 786 |
+
"model.layers.4.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 787 |
+
"model.layers.4.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 788 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 789 |
+
"model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 790 |
+
"model.layers.4.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 791 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"model.layers.4.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 794 |
+
"model.layers.4.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 795 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 797 |
+
"model.layers.4.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 798 |
+
"model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 799 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 801 |
+
"model.layers.4.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 802 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"model.layers.4.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 804 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 805 |
+
"model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 806 |
+
"model.layers.4.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 807 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 808 |
+
"model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 809 |
+
"model.layers.4.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 810 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 812 |
+
"model.layers.4.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 813 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 815 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 816 |
+
"model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 817 |
+
"model.layers.5.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 818 |
+
"model.layers.5.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 819 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 820 |
+
"model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 821 |
+
"model.layers.5.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 822 |
+
"model.layers.5.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 823 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 825 |
+
"model.layers.5.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 826 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 827 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 828 |
+
"model.layers.5.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 829 |
+
"model.layers.5.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 830 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 831 |
+
"model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 832 |
+
"model.layers.5.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 833 |
+
"model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 834 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 835 |
+
"model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 836 |
+
"model.layers.5.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 837 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 838 |
+
"model.layers.5.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 839 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 840 |
+
"model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 841 |
+
"model.layers.5.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 842 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 843 |
+
"model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 844 |
+
"model.layers.5.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 845 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 846 |
+
"model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 847 |
+
"model.layers.5.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 848 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 849 |
+
"model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 850 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 851 |
+
"model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 852 |
+
"model.layers.6.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 853 |
+
"model.layers.6.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 854 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 855 |
+
"model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 856 |
+
"model.layers.6.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 857 |
+
"model.layers.6.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 858 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 859 |
+
"model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 860 |
+
"model.layers.6.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 861 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 862 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 863 |
+
"model.layers.6.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 864 |
+
"model.layers.6.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 865 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 866 |
+
"model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 867 |
+
"model.layers.6.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 868 |
+
"model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 869 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 870 |
+
"model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 871 |
+
"model.layers.6.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 872 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 873 |
+
"model.layers.6.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 874 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 875 |
+
"model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 876 |
+
"model.layers.6.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 877 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 878 |
+
"model.layers.6.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 879 |
+
"model.layers.6.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 880 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 881 |
+
"model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 882 |
+
"model.layers.6.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 883 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 884 |
+
"model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 885 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 886 |
+
"model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 887 |
+
"model.layers.7.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 888 |
+
"model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 889 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 890 |
+
"model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 891 |
+
"model.layers.7.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 892 |
+
"model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 893 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 894 |
+
"model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 895 |
+
"model.layers.7.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 896 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 897 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 898 |
+
"model.layers.7.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 899 |
+
"model.layers.7.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 900 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 901 |
+
"model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 902 |
+
"model.layers.7.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 903 |
+
"model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 904 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 905 |
+
"model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 906 |
+
"model.layers.7.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 907 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 908 |
+
"model.layers.7.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 909 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 910 |
+
"model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 911 |
+
"model.layers.7.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 912 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 913 |
+
"model.layers.7.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 914 |
+
"model.layers.7.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 915 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 916 |
+
"model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 917 |
+
"model.layers.7.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 918 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 919 |
+
"model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 920 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 921 |
+
"model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 922 |
+
"model.layers.8.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 923 |
+
"model.layers.8.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 924 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 925 |
+
"model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 926 |
+
"model.layers.8.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 927 |
+
"model.layers.8.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 928 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 929 |
+
"model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 930 |
+
"model.layers.8.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 931 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 932 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 933 |
+
"model.layers.8.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 934 |
+
"model.layers.8.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 935 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 936 |
+
"model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 937 |
+
"model.layers.8.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 938 |
+
"model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 939 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 940 |
+
"model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 941 |
+
"model.layers.8.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 942 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 943 |
+
"model.layers.8.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 944 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 945 |
+
"model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 946 |
+
"model.layers.8.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 947 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 948 |
+
"model.layers.8.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 949 |
+
"model.layers.8.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 950 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 951 |
+
"model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 952 |
+
"model.layers.8.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 953 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 954 |
+
"model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 955 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 956 |
+
"model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 957 |
+
"model.layers.9.mlp.down_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 958 |
+
"model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 959 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 960 |
+
"model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 961 |
+
"model.layers.9.mlp.gate_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 962 |
+
"model.layers.9.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 963 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 964 |
+
"model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 965 |
+
"model.layers.9.mlp.up_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 966 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 967 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 968 |
+
"model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 969 |
+
"model.layers.9.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
|
| 970 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 971 |
+
"model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 972 |
+
"model.layers.9.self_attn.k_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 973 |
+
"model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 974 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 975 |
+
"model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 976 |
+
"model.layers.9.self_attn.o_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 977 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 978 |
+
"model.layers.9.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 979 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 980 |
+
"model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 981 |
+
"model.layers.9.self_attn.q_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 982 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 983 |
+
"model.layers.9.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
| 984 |
+
"model.layers.9.self_attn.v_proj.v_scale": "model-00001-of-00002.safetensors",
|
| 985 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 986 |
+
"model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 987 |
+
"model.layers.9.self_attn.v_proj.weight_scale_2": "model-00001-of-00002.safetensors",
|
| 988 |
+
"model.norm.weight": "model-00001-of-00002.safetensors"
|
| 989 |
+
}
|
| 990 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<｜end▁of▁sentence｜>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|