qianguo sun
commited on
Commit
·
102bb9f
0
Parent(s):
update
Browse files- .gitattributes +37 -0
- README.md +243 -0
- codec_config.json +209 -0
- config.json +30 -0
- g_00204000 +3 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +346 -0
- pytorch_model.bin.index.json +346 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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 |
+
g_00204000 filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
{}
|
| 3 |
+
---
|
| 4 |
+
## UniTTS
|
| 5 |
+
|
| 6 |
+
### Overview
|
| 7 |
+
we introduce UniTTS and [DistilCodec](https://github.com/IDEA-Emdoor-Lab/DistilCodec) . DistilCodec is a single-codebook audio codec, which has 32768 codes, and the utilization of the codebook achieves nearly 100\%. UniTTS leverages DistilCodec for audio discretization, while its backbone network adopts Qwen2.5-7B to model relationships between audio tokens.
|
| 8 |
+
|
| 9 |
+
Our main contributions are summarized as follows:
|
| 10 |
+
|
| 11 |
+
- DistilCodec: We propose a training methodology that enables the distillation of multi-codebook Neural Audio Codecs(NAC) into single-codebook NAC. Through this approach, we have developed DistilCodec - a single-codebook NAC containing 32,768 codes that achieves 100\% utilization with balanced code distribution. Notably, DistilCodec employs universal audio data for training rather than being restricted to speech-specific datasets.
|
| 12 |
+
- UniTTS: We present UniTTS, a novel TTS system trained on QWen2.5-7B and DistilCodec. Leveraging DistilCodec's comprehensive audio modeling capabilities, UniTTS achieves end-to-end speech synthesis with full-spectrum audio input/output. The system demonstrates enhanced naturalness in emotional expressiveness compared to conventional TTS systems, particularly in capturing subtle prosodic variations and affective nuances during audio generation.
|
| 13 |
+
- Novel Audio Language Model Paradigm: We establish a dual-phase Audio Language Model (ALM) training framework, which comprises (i) Audio Perceptual Modeling (DistilCodec) focusing purely on acoustic discretization, and (ii) Audio Cognitive Modeling (UniTTS) implemented via pretraining (incorporating universal audio autoregressive tasks), supervised fine-tuning (evaluating text-audio interleaved prompts' impact), and alignment (employing direct preference optimization for speech refinement) - enabled by UniTTS's complete end-to-end integration within the LLM.
|
| 14 |
+
|
| 15 |
+
## Training data distribution and application scope
|
| 16 |
+
The model architecture was augmented with cross-lingual text-speech paired datasets (English and Chinese) alongside text-associated instruction corpora during pretraining. Subsequent SFT and alignment phases systematically incorporated three datasets: text instructions dataset, long-CoT dataset, and Chinese TTS dataset. Consequently, the model demonstrates robust capabilities in text-based conversational, long-CoT conversational, and Chinese TTS.
|
| 17 |
+
|
| 18 |
+
The distribution of the pretraining training data is as follows:
|
| 19 |
+
| Data Type | Data Size (B) |
|
| 20 |
+
|----------------------------|---------------|
|
| 21 |
+
| Text Data | 140 |
|
| 22 |
+
| Text-Audio Alignment Data | 82 |
|
| 23 |
+
| Audio Data | 100 |
|
| 24 |
+
| **Total** | **322** |
|
| 25 |
+
|
| 26 |
+
The distribution of the sft training data is as follows:
|
| 27 |
+
|
| 28 |
+
| Data Type | Number of Samples |
|
| 29 |
+
|----------------------------|-------------------|
|
| 30 |
+
| Text Data | 181K |
|
| 31 |
+
| Long-cot Dataset | 55K |
|
| 32 |
+
| Chinese Text-Audio Alignment Data | 401K |
|
| 33 |
+
| Total | 637K |
|
| 34 |
+
|
| 35 |
+
The distribution of the lpo training data is as follows:
|
| 36 |
+
|
| 37 |
+
| Data Type | Number of Samples |
|
| 38 |
+
|----------------------------|-------------------|
|
| 39 |
+
| General SFT Data | 100K |
|
| 40 |
+
| Long-cot Dataset | 45K |
|
| 41 |
+
| Chinese Text-Audio Alignment Data | 300K |
|
| 42 |
+
| Total | 445K |
|
| 43 |
+
|
| 44 |
+
The proposed model supports the following capabilities
|
| 45 |
+
|
| 46 |
+
| Application Type | Support Status |
|
| 47 |
+
|----------------------------|-------------------|
|
| 48 |
+
| Text conversation | Supported |
|
| 49 |
+
| Long-cot conversation | Supported |
|
| 50 |
+
| Chinese TTS | Supported |
|
| 51 |
+
|
| 52 |
+
## Install
|
| 53 |
+
**Clone and Install**
|
| 54 |
+
|
| 55 |
+
- Clone the repo
|
| 56 |
+
``` sh
|
| 57 |
+
git clone [email protected]:IDEA-Emdoor-Lab/UniTTS.git
|
| 58 |
+
|
| 59 |
+
git clone [email protected]:IDEA-Emdoor-Lab/DistilCodec.git
|
| 60 |
+
|
| 61 |
+
cd UniTTS
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
- Installation environment
|
| 65 |
+
``` sh
|
| 66 |
+
conda create -n unitts -y python=3.10
|
| 67 |
+
conda activate unitts
|
| 68 |
+
pip install -r requirements.txt
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
**Model Download**
|
| 74 |
+
|
| 75 |
+
Download via git clone:
|
| 76 |
+
```sh
|
| 77 |
+
mkdir -p pretrained_models
|
| 78 |
+
|
| 79 |
+
# Make sure you have git-lfs installed (https://git-lfs.com)
|
| 80 |
+
git lfs install
|
| 81 |
+
|
| 82 |
+
# clone UniTTS model
|
| 83 |
+
git clone [email protected]:IDEA-Emdoor/UniTTS-mixed-v0.1
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
## Inference Usage
|
| 88 |
+
### TTS Inference Usage
|
| 89 |
+
|
| 90 |
+
```
|
| 91 |
+
#### Step 1: Init model
|
| 92 |
+
|
| 93 |
+
from cli.tokenizer import QWenTokenizer
|
| 94 |
+
from cli.tts_tool import enocde_audio, tts_prompt_ref_text
|
| 95 |
+
import soundfile as sf
|
| 96 |
+
import librosa
|
| 97 |
+
from vllm import LLM, SamplingParams
|
| 98 |
+
|
| 99 |
+
import sys
|
| 100 |
+
sys.path.append('../DistilCodec/') # set DistilCodec code path
|
| 101 |
+
from distil_codec import DistilCodec # type: ignore
|
| 102 |
+
|
| 103 |
+
#init model
|
| 104 |
+
model_name="IDEA-Emdoor/UniTTS-mixed-v0.1"
|
| 105 |
+
model_config="IDEA-Emdoor/UniTTS-mixed-v0.1/codec_config.json"
|
| 106 |
+
ckpt_config="IDEA-Emdoor/UniTTS-mixed-v0.1"
|
| 107 |
+
|
| 108 |
+
ref_audio_path='cli/ref.mp3'
|
| 109 |
+
ref_text='求求你，再给我一次机会，我保证不会让你失望……'
|
| 110 |
+
infer_text='天啊！这竟然是真的？我简直不敢相信！'
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
llm = LLM(model=model_name, dtype='auto', gpu_memory_utilization=0.8, seed=0)
|
| 114 |
+
codec = DistilCodec.from_pretrained(
|
| 115 |
+
config_path=model_config,
|
| 116 |
+
model_path=ckpt_config,
|
| 117 |
+
use_generator=True,
|
| 118 |
+
is_debug=False,
|
| 119 |
+
local_rank=0).eval()
|
| 120 |
+
|
| 121 |
+
tokenizer: QWenTokenizer = QWenTokenizer(model_name)
|
| 122 |
+
stop_tokens = ["<|endoftext|>", "<|endofaudio|>", "<|im_end|>"]
|
| 123 |
+
stop_ids = tokenizer.tokenizer.convert_tokens_to_ids(stop_tokens)
|
| 124 |
+
|
| 125 |
+
#### Step 2: format prompt
|
| 126 |
+
|
| 127 |
+
ref_audio_text = enocde_audio(codec, tokenizer, ref_audio_path)
|
| 128 |
+
ref_audio_text = f'<|inter_audio_begin|>{ref_audio_text}<|inter_audio_end|>'
|
| 129 |
+
prompt = tts_prompt_ref_text.format(content=infer_text, example_voice=ref_audio_text, example_text=ref_text)
|
| 130 |
+
|
| 131 |
+
#### Step 3: inference speech token
|
| 132 |
+
sampling_params = SamplingParams(temperature=0.9, top_p=0.9, stop_token_ids=stop_ids, max_tokens=6000)
|
| 133 |
+
output = llm.generate([prompt], sampling_params)
|
| 134 |
+
|
| 135 |
+
#### step 4: decode speech token
|
| 136 |
+
|
| 137 |
+
output_dir='./' # save path
|
| 138 |
+
tokens = tokenizer.tokenizer.encode(output[0].outputs[0].text)[1: -2]
|
| 139 |
+
utt = 'infer'
|
| 140 |
+
y_gen = codec.decode_from_codes(
|
| 141 |
+
tokens,
|
| 142 |
+
minus_token_offset=True # if the 'plus_llm_offset' of method demo_for_generate_audio_codes is set to True, then minus_token_offset must be True.
|
| 143 |
+
)
|
| 144 |
+
codec.save_wav(
|
| 145 |
+
audio_gen_batch=y_gen,
|
| 146 |
+
nhop_lengths=[y_gen.shape[-1]],
|
| 147 |
+
save_path=output_dir,
|
| 148 |
+
name_tag=utt
|
| 149 |
+
)
|
| 150 |
+
|
| 151 |
+
```
|
| 152 |
+
|
| 153 |
+
### Long-cot Inference Usage
|
| 154 |
+
```
|
| 155 |
+
#### Step 1: Init model
|
| 156 |
+
|
| 157 |
+
from cli.tokenizer import QWenTokenizer
|
| 158 |
+
from cli.tts_tool import enocde_audio, long_cot_prompt_template
|
| 159 |
+
from vllm import LLM, SamplingParams
|
| 160 |
+
|
| 161 |
+
|
| 162 |
+
#init model
|
| 163 |
+
model_name="IDEA-Emdoor/UniTTS-mixed-v0.1"
|
| 164 |
+
infer_text="给我写一首春天的作文"
|
| 165 |
+
llm = LLM(model=model_name, dtype='auto', gpu_memory_utilization=0.8, seed=0)
|
| 166 |
+
|
| 167 |
+
tokenizer: QWenTokenizer = QWenTokenizer(model_name)
|
| 168 |
+
stop_tokens = ["<|endoftext|>", "<|endofaudio|>", "<|im_end|>"]
|
| 169 |
+
stop_ids = tokenizer.tokenizer.convert_tokens_to_ids(stop_tokens)
|
| 170 |
+
|
| 171 |
+
#### Step 2: format prompt
|
| 172 |
+
|
| 173 |
+
prompt = long_cot_prompt_template.format(question=infer_text)
|
| 174 |
+
|
| 175 |
+
#### Step 3: inference speech token
|
| 176 |
+
sampling_params = SamplingParams(temperature=0.8, top_p=0.8, stop_token_ids=stop_ids, max_tokens=6000)
|
| 177 |
+
output = llm.generate([prompt], sampling_params)
|
| 178 |
+
|
| 179 |
+
print(output[0].outputs[0].text)
|
| 180 |
+
|
| 181 |
+
```
|
| 182 |
+
|
| 183 |
+
### Text conversation Inference Usage
|
| 184 |
+
|
| 185 |
+
```
|
| 186 |
+
#### Step 1: Init model
|
| 187 |
+
|
| 188 |
+
from cli.tokenizer import QWenTokenizer
|
| 189 |
+
from cli.tts_tool import enocde_audio, text_conversation_prompt_template
|
| 190 |
+
from vllm import LLM, SamplingParams
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
#init model
|
| 194 |
+
model_name="IDEA-Emdoor/UniTTS-mixed-v0.1"
|
| 195 |
+
|
| 196 |
+
infer_text="天空为什么是蓝色的？"
|
| 197 |
+
llm = LLM(model=model_name, dtype='auto', gpu_memory_utilization=0.8, seed=0)
|
| 198 |
+
|
| 199 |
+
tokenizer: QWenTokenizer = QWenTokenizer(model_name)
|
| 200 |
+
stop_tokens = ["<|endoftext|>", "<|endofaudio|>", "<|im_end|>"]
|
| 201 |
+
stop_ids = tokenizer.tokenizer.convert_tokens_to_ids(stop_tokens)
|
| 202 |
+
|
| 203 |
+
#### Step 2: format prompt
|
| 204 |
+
|
| 205 |
+
prompt = text_conversation_prompt_template.format(question=infer_text)
|
| 206 |
+
|
| 207 |
+
#### Step 3: inference speech token
|
| 208 |
+
sampling_params = SamplingParams(temperature=0.75, top_p=0.75, stop_token_ids=stop_ids, max_tokens=6000)
|
| 209 |
+
output = llm.generate([prompt], sampling_params)
|
| 210 |
+
|
| 211 |
+
print(output[0].outputs[0].text)
|
| 212 |
+
|
| 213 |
+
```
|
| 214 |
+
|
| 215 |
+
## Citation
|
| 216 |
+
```
|
| 217 |
+
@misc{wang2025unittsendtoendttsdecoupling,
|
| 218 |
+
title={UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information},
|
| 219 |
+
author={Rui Wang and Qianguo Sun and Tianrong Chen and Zhiyun Zeng and Junlong Wu and Jiaxing Zhang},
|
| 220 |
+
year={2025},
|
| 221 |
+
eprint={2505.17426},
|
| 222 |
+
archivePrefix={arXiv},
|
| 223 |
+
primaryClass={cs.SD},
|
| 224 |
+
url={https://arxiv.org/abs/2505.17426},
|
| 225 |
+
}
|
| 226 |
+
```
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
## Disclaimer
|
| 230 |
+
|
| 231 |
+
Our model provides zero-shot voice cloning only for academic research purposes. We encourage the community to uphold safety and ethical principles in AI research and applications.
|
| 232 |
+
|
| 233 |
+
Important Notes:
|
| 234 |
+
|
| 235 |
+
- Compliance with the model's open-source license is mandatory.
|
| 236 |
+
|
| 237 |
+
- Unauthorized voice replication applications are strictly prohibited.
|
| 238 |
+
|
| 239 |
+
- Developers bear no responsibility for any misuse of this model.
|
| 240 |
+
|
| 241 |
+
|
| 242 |
+
## License
|
| 243 |
+
<a href="https://arxiv.org/abs/2505.17426">UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information</a> © 2025 by <a href="https://creativecommons.org">Rui Wang, Qianguo Sun, Tianrong Chen, Zhiyun Zeng, Junlong Wu, Jiaxing Zhang</a> is licensed under <a href="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0</a><img src="https://mirrors.creativecommons.org/presskit/icons/cc.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/by.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/nc.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/nd.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;">
|
codec_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"summary": {
|
| 3 |
+
"quantizer_dim": 3584,
|
| 4 |
+
"codebook_per_group_per_residual": 3584,
|
| 5 |
+
"group": 1,
|
| 6 |
+
"residual": 1,
|
| 7 |
+
"original_residual_dim": 1024,
|
| 8 |
+
"codebook_upsample": 3.5,
|
| 9 |
+
"codebook_dim": 3584
|
| 10 |
+
},
|
| 11 |
+
"base_model": "QWen2.5-7B-Pretrain",
|
| 12 |
+
"token_id_offset": 152064,
|
| 13 |
+
"spec_transform": {
|
| 14 |
+
"sampling_rate": 24000,
|
| 15 |
+
"segment_size": 72000,
|
| 16 |
+
"num_mels": 128,
|
| 17 |
+
"n_fft": 1024,
|
| 18 |
+
"hop_size": 256,
|
| 19 |
+
"win_size": 1024,
|
| 20 |
+
"fmin": 0,
|
| 21 |
+
"fmax": 12000,
|
| 22 |
+
"fmax_loss": null
|
| 23 |
+
},
|
| 24 |
+
"encoder": {
|
| 25 |
+
"input_channels": 128,
|
| 26 |
+
"depths": [
|
| 27 |
+
3,
|
| 28 |
+
3,
|
| 29 |
+
9,
|
| 30 |
+
3
|
| 31 |
+
],
|
| 32 |
+
"dims": [
|
| 33 |
+
256,
|
| 34 |
+
512,
|
| 35 |
+
768,
|
| 36 |
+
1024
|
| 37 |
+
],
|
| 38 |
+
"drop_path_rate": 0.2,
|
| 39 |
+
"kernel_size": 7
|
| 40 |
+
},
|
| 41 |
+
"decoder": {
|
| 42 |
+
"hop_length": 256,
|
| 43 |
+
"upsample_rates": [
|
| 44 |
+
8,
|
| 45 |
+
4,
|
| 46 |
+
2,
|
| 47 |
+
2,
|
| 48 |
+
2
|
| 49 |
+
],
|
| 50 |
+
"upsample_kernel_sizes": [
|
| 51 |
+
16,
|
| 52 |
+
12,
|
| 53 |
+
4,
|
| 54 |
+
4,
|
| 55 |
+
4
|
| 56 |
+
],
|
| 57 |
+
"resblock_kernel_sizes": [
|
| 58 |
+
3,
|
| 59 |
+
7,
|
| 60 |
+
11
|
| 61 |
+
],
|
| 62 |
+
"resblock_dilation_sizes": [
|
| 63 |
+
[
|
| 64 |
+
1,
|
| 65 |
+
3,
|
| 66 |
+
5
|
| 67 |
+
],
|
| 68 |
+
[
|
| 69 |
+
1,
|
| 70 |
+
3,
|
| 71 |
+
5
|
| 72 |
+
],
|
| 73 |
+
[
|
| 74 |
+
1,
|
| 75 |
+
3,
|
| 76 |
+
5
|
| 77 |
+
]
|
| 78 |
+
],
|
| 79 |
+
"num_mels": 1024,
|
| 80 |
+
"upsample_initial_channel": 1024,
|
| 81 |
+
"use_template": false,
|
| 82 |
+
"pre_conv_kernel_size": 13,
|
| 83 |
+
"post_conv_kernel_size": 13
|
| 84 |
+
},
|
| 85 |
+
"quantizer": {
|
| 86 |
+
"quantizer_type": "grvq",
|
| 87 |
+
"input_dim": 1024,
|
| 88 |
+
"n_groups": 1,
|
| 89 |
+
"n_codebooks": 1,
|
| 90 |
+
"codebook_size": 32768,
|
| 91 |
+
"codebook_dim": 3584,
|
| 92 |
+
"levels": [
|
| 93 |
+
8,
|
| 94 |
+
5,
|
| 95 |
+
5,
|
| 96 |
+
5
|
| 97 |
+
],
|
| 98 |
+
"downsample_factor": [
|
| 99 |
+
1
|
| 100 |
+
],
|
| 101 |
+
"ema_decay": 0.8,
|
| 102 |
+
"codebook_diversity_loss_weight": 1.0,
|
| 103 |
+
"codebook_diversity_temperature": 100.0
|
| 104 |
+
},
|
| 105 |
+
"teacher_quantizer": {
|
| 106 |
+
"quantizer_type": "grvq",
|
| 107 |
+
"input_dim": 1024,
|
| 108 |
+
"n_groups": 2,
|
| 109 |
+
"n_codebooks": 1,
|
| 110 |
+
"codebook_size": 32768,
|
| 111 |
+
"codebook_dim": 3584,
|
| 112 |
+
"levels": [
|
| 113 |
+
8,
|
| 114 |
+
5,
|
| 115 |
+
5,
|
| 116 |
+
5
|
| 117 |
+
],
|
| 118 |
+
"downsample_factor": [
|
| 119 |
+
2
|
| 120 |
+
],
|
| 121 |
+
"ema_decay": 0.8,
|
| 122 |
+
"codebook_diversity_loss_weight": 1.0,
|
| 123 |
+
"codebook_diversity_temperature": 100.0
|
| 124 |
+
},
|
| 125 |
+
"descriminators": {
|
| 126 |
+
"MultiPeriodDiscriminator": {
|
| 127 |
+
"periods": [
|
| 128 |
+
5,
|
| 129 |
+
8,
|
| 130 |
+
13,
|
| 131 |
+
19,
|
| 132 |
+
30
|
| 133 |
+
],
|
| 134 |
+
"kernal_size": 5,
|
| 135 |
+
"stride": 3
|
| 136 |
+
},
|
| 137 |
+
"MultiScaleDiscriminator": {
|
| 138 |
+
"avg_poolings": {
|
| 139 |
+
"kernal_sizes": [
|
| 140 |
+
6,
|
| 141 |
+
6
|
| 142 |
+
],
|
| 143 |
+
"stridess": [
|
| 144 |
+
3,
|
| 145 |
+
3
|
| 146 |
+
],
|
| 147 |
+
"paddings": [
|
| 148 |
+
3,
|
| 149 |
+
3
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"DiscriminatorS": {
|
| 153 |
+
"kernal_sizes": [
|
| 154 |
+
21,
|
| 155 |
+
61,
|
| 156 |
+
61,
|
| 157 |
+
61,
|
| 158 |
+
61,
|
| 159 |
+
61,
|
| 160 |
+
7
|
| 161 |
+
],
|
| 162 |
+
"strides": [
|
| 163 |
+
1,
|
| 164 |
+
3,
|
| 165 |
+
3,
|
| 166 |
+
6,
|
| 167 |
+
6,
|
| 168 |
+
1,
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"paddings": [
|
| 172 |
+
10,
|
| 173 |
+
30,
|
| 174 |
+
30,
|
| 175 |
+
30,
|
| 176 |
+
30,
|
| 177 |
+
30,
|
| 178 |
+
3
|
| 179 |
+
]
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"MultiScaleSTFTDiscriminator": {
|
| 183 |
+
"n_ffts": [
|
| 184 |
+
1024,
|
| 185 |
+
2048,
|
| 186 |
+
512,
|
| 187 |
+
256,
|
| 188 |
+
128
|
| 189 |
+
],
|
| 190 |
+
"hop_lengths": [
|
| 191 |
+
256,
|
| 192 |
+
512,
|
| 193 |
+
128,
|
| 194 |
+
64,
|
| 195 |
+
32
|
| 196 |
+
],
|
| 197 |
+
"win_lengths": [
|
| 198 |
+
1024,
|
| 199 |
+
2048,
|
| 200 |
+
512,
|
| 201 |
+
256,
|
| 202 |
+
128
|
| 203 |
+
],
|
| 204 |
+
"filters": 32,
|
| 205 |
+
"in_channels": 1,
|
| 206 |
+
"out_channels": 1
|
| 207 |
+
}
|
| 208 |
+
}
|
| 209 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cognitive_comp/ccnl_common_data/wangrui/alm_sft_training/20250410/train/checkpoint/xpo-mcore-qwen2.5-7B-lr-8e-7-minlr-5e-7-bs-6-gbs-120-seqlen-4096-pr-bf16-tp-2-pp-4-cp-1-ac-false-do-true-sp-true-ti-18000-wi-66/iter_00020500_hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2Model"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 8192,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.48.3",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"use_mrope": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 184840
|
| 30 |
+
}
|
g_00204000
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097fcfee379183ce7d02a610bb1a8eba080d7ea4972c104f608e5c561940d44f
|
| 3 |
+
size 1625057395
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.46.3"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd6a3131b068db092f33df8a85ff132b074272e3b80a1eb70a72a8a66e2b3b5f
|
| 3 |
+
size 2649866376
|
model-00002-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ce3bb32bc2c6bdee06ed879df19537ae855a81f436fd87c00cfde6d5fd9a3c1
|
| 3 |
+
size 1981924776
|
model-00003-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcb0bafca04c2c2bcbecd6086fa9b6c0ec3319610e1f8e10da7de2032d0676ea
|
| 3 |
+
size 1864465064
|
model-00004-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:876397c2d0d7241776c25cdc747c233b041559b3a80202ddeb0d8c11c5969a20
|
| 3 |
+
size 1864465064
|
model-00005-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a88f7f74224d730593ac65ad35d2939ac8374f9c3c3ff7620de49f877b8352af
|
| 3 |
+
size 1864465064
|
model-00006-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea87aa68c358bfe729d02d56520cf52c71409294a772eb8ab6e7c67168dde60f
|
| 3 |
+
size 1864465048
|
model-00007-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eda6d74cb0830a1a5f2dff89fd5ea1fa625d05a62bb4962dde8b99bc985d1a24
|
| 3 |
+
size 1864465088
|
model-00008-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4b6f7ed16611d1db372087fc4df20500a9694db8d4768eb21fb20f4b4b61bf5
|
| 3 |
+
size 1864465088
|
model-00009-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192d5320e2cd7f490d57b73c67e49f58a266bd4e6f0bed325a236e1cde55a069
|
| 3 |
+
size 1864465088
|
model-00010-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8661439722241cd0dfa2c64c74c44f63a400edc55e6eb7fe4b66bdedfc66e48
|
| 3 |
+
size 1864465088
|
model-00011-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a389f6ccc791b5109e68506e58403c626a2286821a607902f4e5e2f512f359f4
|
| 3 |
+
size 1864465088
|
model-00012-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfac48d7d98a8cf3151155ea98df1342b36fecbbf7daf9117a92bfe55eef9e13
|
| 3 |
+
size 1864465088
|
model-00013-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd6d6dfa8697e7faa6ad9d61ae5af6da6be75dbb947aef015125bb2c77c7232a
|
| 3 |
+
size 1864465088
|
model-00014-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fde867d7cd6b080ed431854c96c2f0bf1fb52dbea7a7f26f509d256cbdbd52d
|
| 3 |
+
size 1864465088
|
model-00015-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9de00d1d0c4de487a9dee1ad5dcd4c5abec6fdc5079ee2a5633e450be42f427
|
| 3 |
+
size 2649866368
|
model-00016-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:730dc6f35bc065723b196e5bda034943db4fdb2d1bcee8fa55101277062ef0a5
|
| 3 |
+
size 1747019776
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 31402219520
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00015-of-00016.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00016.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00016-of-00016.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00016-of-00016.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00016-of-00016.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15701109760
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 344 |
+
"model.norm.weight": "pytorch_model-00003-of-00004.bin"
|
| 345 |
+
}
|
| 346 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acabcaa15a4db2a61dcd09647ef99bdf3f9c2e11410648cad5392bf4b2fbcebe
|
| 3 |
+
size 17790582
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|