Upload folder using huggingface_hub
Browse files- README.md +5 -5
- comparison_graph.png +0 -0
- config.json +6 -3
- generation_config.json +2 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +8 -8
- tokenizer.json +2 -2
- tokenizer_config.json +7 -185
README.md
CHANGED
|
@@ -27,18 +27,18 @@ This model is a **aggressively pruned** version of [Qwen/Qwen2.5-3B-Instruct](ht
|
|
| 27 |
|
| 28 |
| Category | Original | Pruned | Change |
|
| 29 |
|----------|----------|--------|--------|
|
| 30 |
-
| **Python** | 100.0% |
|
| 31 |
| Html | 6.7% | 0.0% | β 6.7% |
|
| 32 |
| Trivia | 66.7% | 60.0% | β 6.7% |
|
| 33 |
| Math | 60.0% | 66.7% | β 6.7% |
|
| 34 |
-
| Reasoning | 100.0% |
|
| 35 |
-
| Medical | 86.7% |
|
| 36 |
| Linux | 100.0% | 100.0% | β |
|
| 37 |
| Writing | 73.3% | 73.3% | β |
|
| 38 |
|
| 39 |
-
**Average**: 74.2% β
|
| 40 |
|
| 41 |
-
**Python Retention**:
|
| 42 |
|
| 43 |

|
| 44 |
|
|
|
|
| 27 |
|
| 28 |
| Category | Original | Pruned | Change |
|
| 29 |
|----------|----------|--------|--------|
|
| 30 |
+
| **Python** | 100.0% | 40.0% β | β 60.0% |
|
| 31 |
| Html | 6.7% | 0.0% | β 6.7% |
|
| 32 |
| Trivia | 66.7% | 60.0% | β 6.7% |
|
| 33 |
| Math | 60.0% | 66.7% | β 6.7% |
|
| 34 |
+
| Reasoning | 100.0% | 86.7% | β 13.3% |
|
| 35 |
+
| Medical | 86.7% | 80.0% | β 6.7% |
|
| 36 |
| Linux | 100.0% | 100.0% | β |
|
| 37 |
| Writing | 73.3% | 73.3% | β |
|
| 38 |
|
| 39 |
+
**Average**: 74.2% β 63.3% (-10.8%)
|
| 40 |
|
| 41 |
+
**Python Retention**: 40.0% of original performance
|
| 42 |
|
| 43 |

|
| 44 |
|
comparison_graph.png
CHANGED
|
|
config.json
CHANGED
|
@@ -54,12 +54,15 @@
|
|
| 54 |
"num_attention_heads": 16,
|
| 55 |
"num_hidden_layers": 36,
|
| 56 |
"num_key_value_heads": 2,
|
|
|
|
| 57 |
"rms_norm_eps": 1e-06,
|
| 58 |
-
"
|
| 59 |
-
|
|
|
|
|
|
|
| 60 |
"sliding_window": null,
|
| 61 |
"tie_word_embeddings": true,
|
| 62 |
-
"transformers_version": "
|
| 63 |
"use_cache": true,
|
| 64 |
"use_sliding_window": false,
|
| 65 |
"vocab_size": 151936
|
|
|
|
| 54 |
"num_attention_heads": 16,
|
| 55 |
"num_hidden_layers": 36,
|
| 56 |
"num_key_value_heads": 2,
|
| 57 |
+
"pad_token_id": null,
|
| 58 |
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_parameters": {
|
| 60 |
+
"rope_theta": 1000000.0,
|
| 61 |
+
"rope_type": "default"
|
| 62 |
+
},
|
| 63 |
"sliding_window": null,
|
| 64 |
"tie_word_embeddings": true,
|
| 65 |
+
"transformers_version": "5.0.0",
|
| 66 |
"use_cache": true,
|
| 67 |
"use_sliding_window": false,
|
| 68 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
|
|
|
| 3 |
"eos_token_id": [
|
| 4 |
151645,
|
| 5 |
151643
|
| 6 |
],
|
| 7 |
"pad_token_id": 151643,
|
| 8 |
"repetition_penalty": 1.05,
|
| 9 |
-
"transformers_version": "
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": false,
|
| 4 |
"eos_token_id": [
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"repetition_penalty": 1.05,
|
| 10 |
+
"transformers_version": "5.0.0"
|
| 11 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c32815103a55a91a5a9aaab5031ab4617fe45d38948ee2ba0e0e64a5ffe6336d
|
| 3 |
+
size 3995916600
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:726f87d51e70d642a1ef788b0659139104b53042a29d4968ae703ed35499b284
|
| 3 |
+
size 2176009944
|
model.safetensors.index.json
CHANGED
|
@@ -173,18 +173,18 @@
|
|
| 173 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
-
"model.layers.21.input_layernorm.weight": "model-
|
| 177 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
| 178 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
| 181 |
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
| 184 |
-
"model.layers.21.self_attn.q_proj.bias": "model-
|
| 185 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
| 186 |
-
"model.layers.21.self_attn.v_proj.bias": "model-
|
| 187 |
-
"model.layers.21.self_attn.v_proj.weight": "model-
|
| 188 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 173 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51354673edf4300eb841665e1fb684cc1badea87c49d5de6ef09981151683508
|
| 3 |
+
size 11422159
|
tokenizer_config.json
CHANGED
|
@@ -1,185 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
}
|
| 181 |
-
},
|
| 182 |
-
"additional_special_tokens": [
|
| 183 |
"<|im_start|>",
|
| 184 |
"<|im_end|>",
|
| 185 |
"<|object_ref_start|>",
|
|
@@ -194,11 +20,7 @@
|
|
| 194 |
"<|image_pad|>",
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
-
"
|
| 198 |
-
"clean_up_tokenization_spaces": false,
|
| 199 |
-
"eos_token": "<|im_end|>",
|
| 200 |
-
"errors": "replace",
|
| 201 |
-
"extra_special_tokens": {},
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
| 204 |
"split_special_tokens": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"<|im_start|>",
|
| 10 |
"<|im_end|>",
|
| 11 |
"<|object_ref_start|>",
|
|
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
| 23 |
+
"is_local": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"model_max_length": 131072,
|
| 25 |
"pad_token": "<|endoftext|>",
|
| 26 |
"split_special_tokens": false,
|