End of training
Browse files- README.md +5 -2
- config.json +75 -0
README.md
CHANGED
|
@@ -1,17 +1,20 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-1.7B-Base
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: Qwen3-1.7B-Base-SFT
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
- trl
|
|
|
|
|
|
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for Qwen3-1.7B-Base-SFT
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-1.7B-Base
|
| 3 |
+
datasets: atomwalk12/linalg-debug
|
| 4 |
library_name: transformers
|
| 5 |
model_name: Qwen3-1.7B-Base-SFT
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
- trl
|
| 9 |
+
- linalg-zero
|
| 10 |
+
- sft
|
| 11 |
+
- tool-use
|
| 12 |
licence: license
|
| 13 |
---
|
| 14 |
|
| 15 |
# Model Card for Qwen3-1.7B-Base-SFT
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on the [atomwalk12/linalg-debug](https://huggingface.co/datasets/atomwalk12/linalg-debug) dataset.
|
| 18 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 19 |
|
| 20 |
## Quick start
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6144,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 32768,
|
| 45 |
+
"max_window_layers": 28,
|
| 46 |
+
"model_type": "qwen3",
|
| 47 |
+
"num_attention_heads": 16,
|
| 48 |
+
"num_hidden_layers": 28,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"quantization_config": {
|
| 51 |
+
"_load_in_4bit": true,
|
| 52 |
+
"_load_in_8bit": false,
|
| 53 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 54 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
| 55 |
+
"bnb_4bit_quant_type": "nf4",
|
| 56 |
+
"bnb_4bit_use_double_quant": false,
|
| 57 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 58 |
+
"llm_int8_has_fp16_weight": false,
|
| 59 |
+
"llm_int8_skip_modules": null,
|
| 60 |
+
"llm_int8_threshold": 6.0,
|
| 61 |
+
"load_in_4bit": true,
|
| 62 |
+
"load_in_8bit": false,
|
| 63 |
+
"quant_method": "bitsandbytes"
|
| 64 |
+
},
|
| 65 |
+
"rms_norm_eps": 1e-06,
|
| 66 |
+
"rope_scaling": null,
|
| 67 |
+
"rope_theta": 1000000,
|
| 68 |
+
"sliding_window": null,
|
| 69 |
+
"tie_word_embeddings": true,
|
| 70 |
+
"torch_dtype": "bfloat16",
|
| 71 |
+
"transformers_version": "4.53.2",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"use_sliding_window": false,
|
| 74 |
+
"vocab_size": 151936
|
| 75 |
+
}
|