Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- config.json +55 -0
- generation_config.json +8 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +197 -0
- quantization_info.json +21 -0
- quantize_config.json +23 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +244 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen3",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 151654,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bits": 4,
|
| 22 |
+
"checkpoint_format": "gptq",
|
| 23 |
+
"desc_act": true,
|
| 24 |
+
"group_size": 128,
|
| 25 |
+
"lm_head": false,
|
| 26 |
+
"meta": {
|
| 27 |
+
"damp_auto_increment": 0.01,
|
| 28 |
+
"damp_percent": 0.05,
|
| 29 |
+
"mse": 0.0,
|
| 30 |
+
"quantizer": [
|
| 31 |
+
"gptqmodel:4.0.0-dev"
|
| 32 |
+
],
|
| 33 |
+
"static_groups": false,
|
| 34 |
+
"true_sequential": true,
|
| 35 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 36 |
+
"v2": true,
|
| 37 |
+
"v2_alpha": 0.25
|
| 38 |
+
},
|
| 39 |
+
"pack_dtype": "int32",
|
| 40 |
+
"quant_method": "gptq",
|
| 41 |
+
"sym": true
|
| 42 |
+
},
|
| 43 |
+
"rms_norm_eps": 1e-06,
|
| 44 |
+
"rope_scaling": null,
|
| 45 |
+
"rope_theta": 1000000,
|
| 46 |
+
"sliding_window": null,
|
| 47 |
+
"tie_word_embeddings": true,
|
| 48 |
+
"torch_dtype": "bfloat16",
|
| 49 |
+
"transformers_version": "4.51.3",
|
| 50 |
+
"unsloth_fixed": true,
|
| 51 |
+
"unsloth_version": "2025.5.7",
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"use_sliding_window": false,
|
| 54 |
+
"vocab_size": 151936
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_length": 32768,
|
| 5 |
+
"max_new_tokens": 2048,
|
| 6 |
+
"pad_token_id": 151654,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1886b4e0ba480781184499fddff7d79bfdcb1ab99bffa433c13330eec189b4d0
|
| 3 |
+
size 541343840
|
quant_log.csv
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.0102534108,0.05000,0.499
|
| 3 |
+
0,self_attn.v_proj,0.0079884017,0.05000,0.270
|
| 4 |
+
0,self_attn.q_proj,0.0232020114,0.05000,0.277
|
| 5 |
+
0,self_attn.o_proj,0.0059849275,0.05000,0.541
|
| 6 |
+
0,mlp.gate_proj,0.2101839185,0.05000,0.273
|
| 7 |
+
0,mlp.up_proj,0.1052171737,0.05000,0.271
|
| 8 |
+
0,mlp.down_proj,0.0060404502,0.05000,1.081
|
| 9 |
+
1,self_attn.k_proj,0.0035987182,0.05000,0.270
|
| 10 |
+
1,self_attn.v_proj,0.0033963406,0.05000,0.271
|
| 11 |
+
1,self_attn.q_proj,0.0081585497,0.05000,0.268
|
| 12 |
+
1,self_attn.o_proj,0.0016202630,0.05000,0.530
|
| 13 |
+
1,mlp.gate_proj,1.3692135811,0.05000,0.272
|
| 14 |
+
1,mlp.up_proj,0.4010225534,0.05000,0.270
|
| 15 |
+
1,mlp.down_proj,0.0095159207,0.05000,0.812
|
| 16 |
+
2,self_attn.k_proj,0.0069046794,0.05000,0.268
|
| 17 |
+
2,self_attn.v_proj,0.0065494906,0.05000,0.274
|
| 18 |
+
2,self_attn.q_proj,0.0161531456,0.05000,0.267
|
| 19 |
+
2,self_attn.o_proj,0.0026321127,0.05000,0.539
|
| 20 |
+
2,mlp.gate_proj,0.9242770672,0.05000,0.269
|
| 21 |
+
2,mlp.up_proj,0.3328490257,0.05000,0.271
|
| 22 |
+
2,mlp.down_proj,12.6786127090,0.05000,0.812
|
| 23 |
+
3,self_attn.k_proj,0.0600524060,0.05000,0.267
|
| 24 |
+
3,self_attn.v_proj,0.0603904948,0.05000,0.270
|
| 25 |
+
3,self_attn.q_proj,0.1229075640,0.05000,0.266
|
| 26 |
+
3,self_attn.o_proj,0.0060743806,0.05000,0.533
|
| 27 |
+
3,mlp.gate_proj,1.1898157597,0.05000,0.269
|
| 28 |
+
3,mlp.up_proj,0.4574447274,0.05000,0.268
|
| 29 |
+
3,mlp.down_proj,0.0240235925,0.05000,0.809
|
| 30 |
+
4,self_attn.k_proj,0.0597024262,0.05000,0.269
|
| 31 |
+
4,self_attn.v_proj,0.0602943413,0.05000,0.266
|
| 32 |
+
4,self_attn.q_proj,0.1205628663,0.05000,0.268
|
| 33 |
+
4,self_attn.o_proj,0.0091588972,0.05000,0.532
|
| 34 |
+
4,mlp.gate_proj,1.0823590755,0.05000,0.274
|
| 35 |
+
4,mlp.up_proj,0.4695992768,0.05000,0.269
|
| 36 |
+
4,mlp.down_proj,0.0285880528,0.05000,0.810
|
| 37 |
+
5,self_attn.k_proj,0.0870025828,0.05000,0.268
|
| 38 |
+
5,self_attn.v_proj,0.0894146040,0.05000,0.270
|
| 39 |
+
5,self_attn.q_proj,0.2058143020,0.05000,0.267
|
| 40 |
+
5,self_attn.o_proj,0.0124091133,0.05000,0.540
|
| 41 |
+
5,mlp.gate_proj,0.7296952605,0.05000,0.269
|
| 42 |
+
5,mlp.up_proj,0.4307921827,0.05000,0.267
|
| 43 |
+
5,mlp.down_proj,0.0321102552,0.05000,0.815
|
| 44 |
+
6,self_attn.k_proj,0.0651639923,0.05000,0.270
|
| 45 |
+
6,self_attn.v_proj,0.0574318357,0.05000,0.271
|
| 46 |
+
6,self_attn.q_proj,0.1408478618,0.05000,0.284
|
| 47 |
+
6,self_attn.o_proj,0.0105036153,0.05000,0.559
|
| 48 |
+
6,mlp.gate_proj,0.8694056273,0.05000,0.277
|
| 49 |
+
6,mlp.up_proj,0.5381510854,0.05000,0.270
|
| 50 |
+
6,mlp.down_proj,0.0412271991,0.05000,0.817
|
| 51 |
+
7,self_attn.k_proj,0.1137319654,0.05000,0.272
|
| 52 |
+
7,self_attn.v_proj,0.1268429458,0.05000,0.269
|
| 53 |
+
7,self_attn.q_proj,0.2715810537,0.05000,0.270
|
| 54 |
+
7,self_attn.o_proj,0.0162299760,0.05000,0.572
|
| 55 |
+
7,mlp.gate_proj,0.9687359333,0.05000,0.274
|
| 56 |
+
7,mlp.up_proj,0.5892530084,0.05000,0.273
|
| 57 |
+
7,mlp.down_proj,0.0502672568,0.05000,0.836
|
| 58 |
+
8,self_attn.k_proj,0.1439509392,0.05000,0.272
|
| 59 |
+
8,self_attn.v_proj,0.1313253343,0.05000,0.268
|
| 60 |
+
8,self_attn.q_proj,0.3237347603,0.05000,0.270
|
| 61 |
+
8,self_attn.o_proj,0.0149488933,0.05000,0.542
|
| 62 |
+
8,mlp.gate_proj,0.9375967979,0.05000,0.271
|
| 63 |
+
8,mlp.up_proj,0.5916349888,0.05000,0.274
|
| 64 |
+
8,mlp.down_proj,0.0501379147,0.05000,0.821
|
| 65 |
+
9,self_attn.k_proj,0.2607176304,0.05000,0.270
|
| 66 |
+
9,self_attn.v_proj,0.2475461066,0.05000,0.272
|
| 67 |
+
9,self_attn.q_proj,0.6035818458,0.05000,0.269
|
| 68 |
+
9,self_attn.o_proj,0.0311477184,0.05000,0.538
|
| 69 |
+
9,mlp.gate_proj,1.0245599747,0.05000,0.271
|
| 70 |
+
9,mlp.up_proj,0.6295373440,0.05000,0.269
|
| 71 |
+
9,mlp.down_proj,0.0618912131,0.05000,0.818
|
| 72 |
+
10,self_attn.k_proj,0.2044563591,0.05000,0.271
|
| 73 |
+
10,self_attn.v_proj,0.2067638040,0.05000,0.275
|
| 74 |
+
10,self_attn.q_proj,0.4824802279,0.05000,0.270
|
| 75 |
+
10,self_attn.o_proj,0.0315365233,0.05000,0.539
|
| 76 |
+
10,mlp.gate_proj,1.0230076313,0.05000,0.276
|
| 77 |
+
10,mlp.up_proj,0.6350437403,0.05000,0.275
|
| 78 |
+
10,mlp.down_proj,0.0830124989,0.05000,0.831
|
| 79 |
+
11,self_attn.k_proj,0.3832934499,0.05000,0.272
|
| 80 |
+
11,self_attn.v_proj,0.3299685717,0.05000,0.273
|
| 81 |
+
11,self_attn.q_proj,0.9707468152,0.05000,0.276
|
| 82 |
+
11,self_attn.o_proj,0.0668854564,0.05000,0.537
|
| 83 |
+
11,mlp.gate_proj,0.7399315238,0.05000,0.274
|
| 84 |
+
11,mlp.up_proj,0.5590443611,0.05000,0.271
|
| 85 |
+
11,mlp.down_proj,0.0836513788,0.05000,0.824
|
| 86 |
+
12,self_attn.k_proj,0.3102838993,0.05000,0.268
|
| 87 |
+
12,self_attn.v_proj,0.3088186979,0.05000,0.272
|
| 88 |
+
12,self_attn.q_proj,0.8227573633,0.05000,0.515
|
| 89 |
+
12,self_attn.o_proj,0.0342148244,0.05000,0.536
|
| 90 |
+
12,mlp.gate_proj,0.6812306643,0.05000,0.273
|
| 91 |
+
12,mlp.up_proj,0.5542650223,0.05000,0.270
|
| 92 |
+
12,mlp.down_proj,0.0880227759,0.05000,0.816
|
| 93 |
+
13,self_attn.k_proj,0.3208425641,0.05000,0.271
|
| 94 |
+
13,self_attn.v_proj,0.3610678911,0.05000,0.271
|
| 95 |
+
13,self_attn.q_proj,0.9154192209,0.05000,0.271
|
| 96 |
+
13,self_attn.o_proj,0.0465078503,0.05000,0.541
|
| 97 |
+
13,mlp.gate_proj,0.7669239044,0.05000,0.274
|
| 98 |
+
13,mlp.up_proj,0.6116556525,0.05000,0.272
|
| 99 |
+
13,mlp.down_proj,0.0951566845,0.05000,0.815
|
| 100 |
+
14,self_attn.k_proj,0.4429032505,0.05000,0.270
|
| 101 |
+
14,self_attn.v_proj,0.4558904767,0.05000,0.269
|
| 102 |
+
14,self_attn.q_proj,1.1899302006,0.05000,0.271
|
| 103 |
+
14,self_attn.o_proj,0.0465852544,0.05000,0.539
|
| 104 |
+
14,mlp.gate_proj,0.7928631902,0.05000,0.273
|
| 105 |
+
14,mlp.up_proj,0.6356908083,0.05000,0.271
|
| 106 |
+
14,mlp.down_proj,0.1102237254,0.05000,0.813
|
| 107 |
+
15,self_attn.k_proj,0.7353894711,0.05000,0.269
|
| 108 |
+
15,self_attn.v_proj,0.8996654749,0.05000,0.275
|
| 109 |
+
15,self_attn.q_proj,2.2844204903,0.05000,0.277
|
| 110 |
+
15,self_attn.o_proj,0.0681514293,0.05000,0.546
|
| 111 |
+
15,mlp.gate_proj,0.9548274279,0.05000,0.271
|
| 112 |
+
15,mlp.up_proj,0.7745286226,0.05000,0.270
|
| 113 |
+
15,mlp.down_proj,0.1513546854,0.05000,0.809
|
| 114 |
+
16,self_attn.k_proj,1.0767021179,0.05000,0.271
|
| 115 |
+
16,self_attn.v_proj,0.9916024208,0.05000,0.275
|
| 116 |
+
16,self_attn.q_proj,3.0991945267,0.05000,0.275
|
| 117 |
+
16,self_attn.o_proj,0.0973514616,0.05000,0.542
|
| 118 |
+
16,mlp.gate_proj,1.0501160622,0.05000,0.270
|
| 119 |
+
16,mlp.up_proj,0.9404838085,0.05000,0.272
|
| 120 |
+
16,mlp.down_proj,0.3604103029,0.05000,0.813
|
| 121 |
+
17,self_attn.k_proj,2.4124805927,0.05000,0.273
|
| 122 |
+
17,self_attn.v_proj,2.8787002563,0.05000,0.270
|
| 123 |
+
17,self_attn.q_proj,7.4132294655,0.05000,0.271
|
| 124 |
+
17,self_attn.o_proj,0.2221524268,0.05000,0.544
|
| 125 |
+
17,mlp.gate_proj,1.6191822290,0.05000,0.272
|
| 126 |
+
17,mlp.up_proj,1.4351911545,0.05000,0.273
|
| 127 |
+
17,mlp.down_proj,0.4600560665,0.05000,0.816
|
| 128 |
+
18,self_attn.k_proj,2.4339659214,0.05000,0.270
|
| 129 |
+
18,self_attn.v_proj,2.6121122837,0.05000,0.272
|
| 130 |
+
18,self_attn.q_proj,7.7049455643,0.05000,0.267
|
| 131 |
+
18,self_attn.o_proj,0.1935115755,0.05000,0.535
|
| 132 |
+
18,mlp.gate_proj,2.0874688625,0.05000,0.271
|
| 133 |
+
18,mlp.up_proj,1.8297674656,0.05000,0.269
|
| 134 |
+
18,mlp.down_proj,0.8489264846,0.05000,0.810
|
| 135 |
+
19,self_attn.k_proj,4.2865271568,0.05000,0.267
|
| 136 |
+
19,self_attn.v_proj,5.3223285675,0.05000,0.266
|
| 137 |
+
19,self_attn.q_proj,14.3558692932,0.05000,0.268
|
| 138 |
+
19,self_attn.o_proj,0.3448703289,0.05000,0.536
|
| 139 |
+
19,mlp.gate_proj,2.2460441589,0.05000,0.267
|
| 140 |
+
19,mlp.up_proj,2.3563187122,0.05000,0.266
|
| 141 |
+
19,mlp.down_proj,1.4070756435,0.05000,0.814
|
| 142 |
+
20,self_attn.k_proj,6.4479541779,0.05000,0.268
|
| 143 |
+
20,self_attn.v_proj,7.3154568672,0.05000,0.267
|
| 144 |
+
20,self_attn.q_proj,19.4513092041,0.05000,0.269
|
| 145 |
+
20,self_attn.o_proj,0.4146451354,0.05000,0.535
|
| 146 |
+
20,mlp.gate_proj,2.5706572533,0.05000,0.270
|
| 147 |
+
20,mlp.up_proj,2.8989415169,0.05000,0.268
|
| 148 |
+
20,mlp.down_proj,1.9455537796,0.05000,0.809
|
| 149 |
+
21,self_attn.k_proj,11.4309139252,0.05000,0.270
|
| 150 |
+
21,self_attn.v_proj,13.4588928223,0.05000,0.269
|
| 151 |
+
21,self_attn.q_proj,33.1673202515,0.05000,0.271
|
| 152 |
+
21,self_attn.o_proj,0.6142717600,0.05000,0.536
|
| 153 |
+
21,mlp.gate_proj,3.0040376186,0.05000,0.269
|
| 154 |
+
21,mlp.up_proj,3.6499385834,0.05000,0.267
|
| 155 |
+
21,mlp.down_proj,2.9936137199,0.05000,0.810
|
| 156 |
+
22,self_attn.k_proj,13.1742839813,0.05000,0.267
|
| 157 |
+
22,self_attn.v_proj,17.1264152527,0.05000,0.267
|
| 158 |
+
22,self_attn.q_proj,37.4587974548,0.05000,0.268
|
| 159 |
+
22,self_attn.o_proj,0.8527563214,0.05000,0.533
|
| 160 |
+
22,mlp.gate_proj,3.4767191410,0.05000,0.271
|
| 161 |
+
22,mlp.up_proj,4.3843421936,0.05000,0.269
|
| 162 |
+
22,mlp.down_proj,3.9900336266,0.05000,0.848
|
| 163 |
+
23,self_attn.k_proj,17.5688858032,0.05000,0.267
|
| 164 |
+
23,self_attn.v_proj,20.2590312958,0.05000,0.267
|
| 165 |
+
23,self_attn.q_proj,42.3259162903,0.05000,0.270
|
| 166 |
+
23,self_attn.o_proj,0.9686302543,0.05000,0.533
|
| 167 |
+
23,mlp.gate_proj,3.8405270576,0.05000,0.273
|
| 168 |
+
23,mlp.up_proj,5.0237965584,0.05000,0.269
|
| 169 |
+
23,mlp.down_proj,4.2359795570,0.05000,1.067
|
| 170 |
+
24,self_attn.k_proj,28.6652069092,0.05000,0.271
|
| 171 |
+
24,self_attn.v_proj,31.3004150391,0.05000,0.266
|
| 172 |
+
24,self_attn.q_proj,80.2267913818,0.05000,0.268
|
| 173 |
+
24,self_attn.o_proj,1.1186426878,0.05000,0.541
|
| 174 |
+
24,mlp.gate_proj,3.6467981339,0.05000,0.271
|
| 175 |
+
24,mlp.up_proj,4.9967317581,0.05000,0.269
|
| 176 |
+
24,mlp.down_proj,5.0153646469,0.05000,0.818
|
| 177 |
+
25,self_attn.k_proj,34.1952438354,0.05000,0.268
|
| 178 |
+
25,self_attn.v_proj,52.2172927856,0.05000,0.268
|
| 179 |
+
25,self_attn.q_proj,102.7100524902,0.05000,0.267
|
| 180 |
+
25,self_attn.o_proj,1.4557044506,0.05000,0.544
|
| 181 |
+
25,mlp.gate_proj,3.5655152798,0.05000,0.271
|
| 182 |
+
25,mlp.up_proj,5.1156783104,0.05000,0.266
|
| 183 |
+
25,mlp.down_proj,6.0685262680,0.05000,0.818
|
| 184 |
+
26,self_attn.k_proj,33.4326934814,0.05000,0.270
|
| 185 |
+
26,self_attn.v_proj,48.4014549255,0.05000,0.269
|
| 186 |
+
26,self_attn.q_proj,111.4053268433,0.05000,0.270
|
| 187 |
+
26,self_attn.o_proj,3.3541142941,0.05000,0.532
|
| 188 |
+
26,mlp.gate_proj,3.8577950001,0.05000,0.269
|
| 189 |
+
26,mlp.up_proj,5.3475961685,0.05000,0.267
|
| 190 |
+
26,mlp.down_proj,11.5380468369,0.05000,0.810
|
| 191 |
+
27,self_attn.k_proj,31.9528331757,0.05000,0.270
|
| 192 |
+
27,self_attn.v_proj,38.4808578491,0.05000,0.272
|
| 193 |
+
27,self_attn.q_proj,70.9194641113,0.05000,0.268
|
| 194 |
+
27,self_attn.o_proj,2.9374377728,0.05000,0.532
|
| 195 |
+
27,mlp.gate_proj,17.0734329224,0.05000,0.267
|
| 196 |
+
27,mlp.up_proj,17.2442932129,0.05000,0.266
|
| 197 |
+
27,mlp.down_proj,24.1500759125,0.05000,0.809
|
quantization_info.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "gptq_v2",
|
| 3 |
+
"version": "v2",
|
| 4 |
+
"bits": 4,
|
| 5 |
+
"group_size": 128,
|
| 6 |
+
"quantization_time": 319.0039792060852,
|
| 7 |
+
"model_size_gb": 0.5041657388210297,
|
| 8 |
+
"peak_memory_gb": 2.2490234375,
|
| 9 |
+
"calibration_size": 1024,
|
| 10 |
+
"config": {
|
| 11 |
+
"method": "gptq_v2",
|
| 12 |
+
"version": "v2",
|
| 13 |
+
"bits": 4,
|
| 14 |
+
"group_size": 128,
|
| 15 |
+
"desc_act": true,
|
| 16 |
+
"sym": true,
|
| 17 |
+
"true_sequential": true,
|
| 18 |
+
"batch_size": 1,
|
| 19 |
+
"auto_gc": false
|
| 20 |
+
}
|
| 21 |
+
}
|
quantize_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"sym": true,
|
| 6 |
+
"lm_head": false,
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"checkpoint_format": "gptq",
|
| 9 |
+
"pack_dtype": "int32",
|
| 10 |
+
"meta": {
|
| 11 |
+
"quantizer": [
|
| 12 |
+
"gptqmodel:4.0.0-dev"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.05,
|
| 16 |
+
"damp_auto_increment": 0.01,
|
| 17 |
+
"static_groups": false,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 0.0,
|
| 20 |
+
"v2": true,
|
| 21 |
+
"v2_alpha": 0.25
|
| 22 |
+
}
|
| 23 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|vision_pad|>"
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|endoftext|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"max_length": null,
|
| 235 |
+
"model_max_length": 32768,
|
| 236 |
+
"pad_to_multiple_of": null,
|
| 237 |
+
"pad_token": "<|vision_pad|>",
|
| 238 |
+
"pad_token_type_id": 0,
|
| 239 |
+
"padding_side": "left",
|
| 240 |
+
"split_special_tokens": false,
|
| 241 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 242 |
+
"unk_token": null,
|
| 243 |
+
"_commit_hash": null
|
| 244 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|