Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- config.json +51 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +253 -0
- quantize_config.json +21 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 36,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 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": 0.0025,
|
| 28 |
+
"damp_percent": 0.01,
|
| 29 |
+
"mse": 0.0,
|
| 30 |
+
"quantizer": [
|
| 31 |
+
"gptqmodel:2.2.0"
|
| 32 |
+
],
|
| 33 |
+
"static_groups": false,
|
| 34 |
+
"true_sequential": true,
|
| 35 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 36 |
+
},
|
| 37 |
+
"pack_dtype": "int32",
|
| 38 |
+
"quant_method": "gptq",
|
| 39 |
+
"sym": true
|
| 40 |
+
},
|
| 41 |
+
"rms_norm_eps": 1e-06,
|
| 42 |
+
"rope_scaling": null,
|
| 43 |
+
"rope_theta": 1000000,
|
| 44 |
+
"sliding_window": null,
|
| 45 |
+
"tie_word_embeddings": true,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"transformers_version": "4.51.3",
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"use_sliding_window": false,
|
| 50 |
+
"vocab_size": 151936
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.3"
|
| 13 |
+
}
|
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 sha256:9e11b6d23c0abc36f55b935661dda53fea501838e74dbd3f512262e70625925a
|
| 3 |
+
size 2669888648
|
quant_log.csv
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.00260956,0.01000,0.829
|
| 3 |
+
0,self_attn.v_proj,0.00233771,0.01000,0.591
|
| 4 |
+
0,self_attn.q_proj,0.00945148,0.01000,0.609
|
| 5 |
+
0,self_attn.o_proj,0.00626256,0.01000,0.988
|
| 6 |
+
0,mlp.up_proj,0.49306521,0.01000,0.624
|
| 7 |
+
0,mlp.gate_proj,0.56335938,0.01000,0.567
|
| 8 |
+
0,mlp.down_proj,0.05435039,0.01000,2.701
|
| 9 |
+
1,self_attn.k_proj,0.00402028,0.01000,0.648
|
| 10 |
+
1,self_attn.v_proj,0.00413055,0.01000,0.553
|
| 11 |
+
1,self_attn.q_proj,0.01495032,0.01000,0.557
|
| 12 |
+
1,self_attn.o_proj,0.00761302,0.01000,0.994
|
| 13 |
+
1,mlp.up_proj,6.14568138,0.01000,0.673
|
| 14 |
+
1,mlp.gate_proj,13.63503647,0.01000,0.573
|
| 15 |
+
1,mlp.down_proj,0.06105804,0.01000,2.646
|
| 16 |
+
2,self_attn.k_proj,0.01301107,0.01000,0.640
|
| 17 |
+
2,self_attn.v_proj,0.01256006,0.01000,0.552
|
| 18 |
+
2,self_attn.q_proj,0.04551908,0.01000,0.557
|
| 19 |
+
2,self_attn.o_proj,0.00959794,0.01000,1.076
|
| 20 |
+
2,mlp.up_proj,15.95272827,0.01000,0.671
|
| 21 |
+
2,mlp.gate_proj,20.05839157,0.01000,0.615
|
| 22 |
+
2,mlp.down_proj,0.05727252,0.01000,2.898
|
| 23 |
+
3,self_attn.k_proj,0.02194048,0.01000,0.648
|
| 24 |
+
3,self_attn.v_proj,0.02231835,0.01000,0.556
|
| 25 |
+
3,self_attn.q_proj,0.08355284,0.01000,0.557
|
| 26 |
+
3,self_attn.o_proj,0.01671291,0.01000,1.074
|
| 27 |
+
3,mlp.up_proj,12.27301884,0.01000,0.705
|
| 28 |
+
3,mlp.gate_proj,23.91833115,0.01000,0.619
|
| 29 |
+
3,mlp.down_proj,0.16981319,0.01000,2.797
|
| 30 |
+
4,self_attn.k_proj,0.04863824,0.01000,0.635
|
| 31 |
+
4,self_attn.v_proj,0.04902033,0.01000,0.553
|
| 32 |
+
4,self_attn.q_proj,0.17482278,0.01000,0.557
|
| 33 |
+
4,self_attn.o_proj,0.02858547,0.01000,0.979
|
| 34 |
+
4,mlp.up_proj,10.48973846,0.01000,0.676
|
| 35 |
+
4,mlp.gate_proj,26.65770721,0.01000,0.563
|
| 36 |
+
4,mlp.down_proj,0.28997350,0.01000,2.733
|
| 37 |
+
5,self_attn.k_proj,0.04801822,0.01000,0.634
|
| 38 |
+
5,self_attn.v_proj,0.05179255,0.01000,0.554
|
| 39 |
+
5,self_attn.q_proj,0.18255764,0.01000,0.556
|
| 40 |
+
5,self_attn.o_proj,0.04555316,0.01000,0.979
|
| 41 |
+
5,mlp.up_proj,5.48301125,0.01000,0.633
|
| 42 |
+
5,mlp.gate_proj,10.99185562,0.01000,0.565
|
| 43 |
+
5,mlp.down_proj,0.45506358,0.01000,2.682
|
| 44 |
+
6,self_attn.k_proj,0.09959402,0.01000,0.627
|
| 45 |
+
6,self_attn.v_proj,0.11477924,0.01000,0.555
|
| 46 |
+
6,self_attn.q_proj,0.41121966,0.01000,0.557
|
| 47 |
+
6,self_attn.o_proj,0.13184954,0.01000,0.966
|
| 48 |
+
6,mlp.up_proj,7.32487488,0.01000,0.630
|
| 49 |
+
6,mlp.gate_proj,12.34899235,0.01000,0.565
|
| 50 |
+
6,mlp.down_proj,137.00463867,0.01000,2.872
|
| 51 |
+
7,self_attn.k_proj,0.21236567,0.01000,0.624
|
| 52 |
+
7,self_attn.v_proj,0.21460515,0.01000,0.555
|
| 53 |
+
7,self_attn.q_proj,0.78465915,0.01000,0.556
|
| 54 |
+
7,self_attn.o_proj,0.13444883,0.01000,0.989
|
| 55 |
+
7,mlp.up_proj,8.85077858,0.01000,0.629
|
| 56 |
+
7,mlp.gate_proj,14.10528946,0.01000,0.567
|
| 57 |
+
7,mlp.down_proj,0.73926550,0.01000,2.479
|
| 58 |
+
8,self_attn.k_proj,0.34496000,0.01000,0.620
|
| 59 |
+
8,self_attn.v_proj,0.37624916,0.01000,0.552
|
| 60 |
+
8,self_attn.q_proj,1.29985523,0.01000,0.556
|
| 61 |
+
8,self_attn.o_proj,0.22197893,0.01000,0.986
|
| 62 |
+
8,mlp.up_proj,9.42709351,0.01000,0.624
|
| 63 |
+
8,mlp.gate_proj,11.46964645,0.01000,0.565
|
| 64 |
+
8,mlp.down_proj,1.18484640,0.01000,2.471
|
| 65 |
+
9,self_attn.k_proj,0.47145227,0.01000,0.641
|
| 66 |
+
9,self_attn.v_proj,0.46269092,0.01000,0.552
|
| 67 |
+
9,self_attn.q_proj,1.65912795,0.01000,0.554
|
| 68 |
+
9,self_attn.o_proj,0.26991138,0.01000,0.960
|
| 69 |
+
9,mlp.up_proj,12.27880478,0.01000,0.625
|
| 70 |
+
9,mlp.gate_proj,18.87297821,0.01000,0.565
|
| 71 |
+
9,mlp.down_proj,1.32681251,0.01000,2.463
|
| 72 |
+
10,self_attn.k_proj,0.72835219,0.01000,0.620
|
| 73 |
+
10,self_attn.v_proj,0.85435569,0.01000,0.552
|
| 74 |
+
10,self_attn.q_proj,2.74349403,0.01000,0.554
|
| 75 |
+
10,self_attn.o_proj,0.36292076,0.01000,0.956
|
| 76 |
+
10,mlp.up_proj,11.62601280,0.01000,0.622
|
| 77 |
+
10,mlp.gate_proj,16.43843842,0.01000,0.566
|
| 78 |
+
10,mlp.down_proj,1.36114752,0.01000,2.477
|
| 79 |
+
11,self_attn.k_proj,0.39711615,0.01000,0.660
|
| 80 |
+
11,self_attn.v_proj,0.42185795,0.01000,0.594
|
| 81 |
+
11,self_attn.q_proj,1.41280699,0.01000,0.598
|
| 82 |
+
11,self_attn.o_proj,0.27962011,0.01000,0.957
|
| 83 |
+
11,mlp.up_proj,11.56846046,0.01000,0.629
|
| 84 |
+
11,mlp.gate_proj,14.54604149,0.01000,0.571
|
| 85 |
+
11,mlp.down_proj,1.35389423,0.01000,2.474
|
| 86 |
+
12,self_attn.k_proj,0.46813077,0.01000,0.613
|
| 87 |
+
12,self_attn.v_proj,0.50627100,0.01000,0.551
|
| 88 |
+
12,self_attn.q_proj,1.68932188,0.01000,0.554
|
| 89 |
+
12,self_attn.o_proj,0.32685736,0.01000,0.954
|
| 90 |
+
12,mlp.up_proj,11.97426701,0.01000,0.666
|
| 91 |
+
12,mlp.gate_proj,13.71073341,0.01000,0.606
|
| 92 |
+
12,mlp.down_proj,1.34886861,0.01000,2.631
|
| 93 |
+
13,self_attn.k_proj,0.34903091,0.01000,0.648
|
| 94 |
+
13,self_attn.v_proj,0.35327876,0.01000,0.588
|
| 95 |
+
13,self_attn.q_proj,1.34817195,0.01000,0.581
|
| 96 |
+
13,self_attn.o_proj,0.22018546,0.01000,0.977
|
| 97 |
+
13,mlp.up_proj,12.59172344,0.01000,0.665
|
| 98 |
+
13,mlp.gate_proj,13.15475464,0.01000,0.583
|
| 99 |
+
13,mlp.down_proj,1.50714171,0.01000,2.509
|
| 100 |
+
14,self_attn.k_proj,0.61326528,0.01000,0.655
|
| 101 |
+
14,self_attn.v_proj,0.64901257,0.01000,0.588
|
| 102 |
+
14,self_attn.q_proj,2.28437233,0.01000,0.598
|
| 103 |
+
14,self_attn.o_proj,0.45074007,0.01000,1.035
|
| 104 |
+
14,mlp.up_proj,12.52815437,0.01000,0.663
|
| 105 |
+
14,mlp.gate_proj,13.09080696,0.01000,0.601
|
| 106 |
+
14,mlp.down_proj,1.38611388,0.01000,2.572
|
| 107 |
+
15,self_attn.k_proj,0.60994160,0.01000,0.638
|
| 108 |
+
15,self_attn.v_proj,0.59522879,0.01000,0.553
|
| 109 |
+
15,self_attn.q_proj,2.29438472,0.01000,0.556
|
| 110 |
+
15,self_attn.o_proj,0.35033396,0.01000,0.986
|
| 111 |
+
15,mlp.up_proj,11.78823280,0.01000,0.640
|
| 112 |
+
15,mlp.gate_proj,11.89937019,0.01000,0.567
|
| 113 |
+
15,mlp.down_proj,1.51105714,0.01000,2.595
|
| 114 |
+
16,self_attn.k_proj,1.04074728,0.01000,0.646
|
| 115 |
+
16,self_attn.v_proj,1.19501519,0.01000,0.560
|
| 116 |
+
16,self_attn.q_proj,4.24412441,0.01000,0.563
|
| 117 |
+
16,self_attn.o_proj,0.47474825,0.01000,1.000
|
| 118 |
+
16,mlp.up_proj,13.40410614,0.01000,0.654
|
| 119 |
+
16,mlp.gate_proj,14.28797817,0.01000,0.578
|
| 120 |
+
16,mlp.down_proj,5.78086710,0.01000,2.659
|
| 121 |
+
17,self_attn.k_proj,0.93727171,0.01000,0.632
|
| 122 |
+
17,self_attn.v_proj,1.08398855,0.01000,0.552
|
| 123 |
+
17,self_attn.q_proj,4.18204689,0.01000,0.556
|
| 124 |
+
17,self_attn.o_proj,0.54972744,0.01000,0.985
|
| 125 |
+
17,mlp.up_proj,13.20138741,0.01000,0.647
|
| 126 |
+
17,mlp.gate_proj,13.71052074,0.01000,0.566
|
| 127 |
+
17,mlp.down_proj,2.41512918,0.01000,2.736
|
| 128 |
+
18,self_attn.k_proj,1.14480364,0.01000,0.650
|
| 129 |
+
18,self_attn.v_proj,1.27249444,0.01000,0.555
|
| 130 |
+
18,self_attn.q_proj,4.76111126,0.01000,0.558
|
| 131 |
+
18,self_attn.o_proj,0.54431963,0.01000,0.999
|
| 132 |
+
18,mlp.up_proj,15.39452362,0.01000,0.646
|
| 133 |
+
18,mlp.gate_proj,15.82460308,0.01000,0.567
|
| 134 |
+
18,mlp.down_proj,2.41237640,0.01000,2.696
|
| 135 |
+
19,self_attn.k_proj,2.23619556,0.01000,0.651
|
| 136 |
+
19,self_attn.v_proj,2.33040428,0.01000,0.555
|
| 137 |
+
19,self_attn.q_proj,9.37097549,0.01000,0.556
|
| 138 |
+
19,self_attn.o_proj,0.89986920,0.01000,0.987
|
| 139 |
+
19,mlp.up_proj,17.55361557,0.01000,0.651
|
| 140 |
+
19,mlp.gate_proj,17.96214294,0.01000,0.563
|
| 141 |
+
19,mlp.down_proj,2.75978541,0.01000,2.821
|
| 142 |
+
20,self_attn.k_proj,1.84364629,0.01000,0.692
|
| 143 |
+
20,self_attn.v_proj,2.03417015,0.01000,0.602
|
| 144 |
+
20,self_attn.q_proj,8.70787430,0.01000,0.605
|
| 145 |
+
20,self_attn.o_proj,0.82709742,0.01000,0.994
|
| 146 |
+
20,mlp.up_proj,19.15014076,0.01000,0.695
|
| 147 |
+
20,mlp.gate_proj,19.27664566,0.01000,0.609
|
| 148 |
+
20,mlp.down_proj,2.91169357,0.01000,2.637
|
| 149 |
+
21,self_attn.k_proj,2.38239908,0.01000,0.698
|
| 150 |
+
21,self_attn.v_proj,2.78411126,0.01000,0.601
|
| 151 |
+
21,self_attn.q_proj,10.69113255,0.01000,0.606
|
| 152 |
+
21,self_attn.o_proj,0.86217725,0.01000,1.063
|
| 153 |
+
21,mlp.up_proj,22.03649902,0.01000,0.657
|
| 154 |
+
21,mlp.gate_proj,22.27753639,0.01000,0.568
|
| 155 |
+
21,mlp.down_proj,3.55271626,0.01000,2.668
|
| 156 |
+
22,self_attn.k_proj,5.02607822,0.01000,0.646
|
| 157 |
+
22,self_attn.v_proj,5.24235153,0.01000,0.553
|
| 158 |
+
22,self_attn.q_proj,20.75082779,0.01000,0.559
|
| 159 |
+
22,self_attn.o_proj,1.57138991,0.01000,0.989
|
| 160 |
+
22,mlp.up_proj,24.25587654,0.01000,0.652
|
| 161 |
+
22,mlp.gate_proj,25.06272507,0.01000,0.567
|
| 162 |
+
22,mlp.down_proj,5.23081446,0.01000,2.644
|
| 163 |
+
23,self_attn.k_proj,4.54250908,0.01000,0.654
|
| 164 |
+
23,self_attn.v_proj,5.57414436,0.01000,0.558
|
| 165 |
+
23,self_attn.q_proj,20.68773270,0.01000,0.561
|
| 166 |
+
23,self_attn.o_proj,2.26957107,0.01000,0.998
|
| 167 |
+
23,mlp.up_proj,27.23978996,0.01000,0.660
|
| 168 |
+
23,mlp.gate_proj,29.70862198,0.01000,0.570
|
| 169 |
+
23,mlp.down_proj,6.30178261,0.01000,2.689
|
| 170 |
+
24,self_attn.k_proj,7.05984497,0.01000,0.643
|
| 171 |
+
24,self_attn.v_proj,8.92666817,0.01000,0.584
|
| 172 |
+
24,self_attn.q_proj,31.14116287,0.01000,0.586
|
| 173 |
+
24,self_attn.o_proj,2.77548218,0.01000,1.071
|
| 174 |
+
24,mlp.up_proj,29.65335464,0.01000,0.649
|
| 175 |
+
24,mlp.gate_proj,33.00664520,0.01000,0.565
|
| 176 |
+
24,mlp.down_proj,7.27749395,0.01000,2.815
|
| 177 |
+
25,self_attn.k_proj,5.49420643,0.01000,0.700
|
| 178 |
+
25,self_attn.v_proj,6.28153324,0.01000,0.608
|
| 179 |
+
25,self_attn.q_proj,22.71930885,0.01000,0.612
|
| 180 |
+
25,self_attn.o_proj,1.31197178,0.01000,1.056
|
| 181 |
+
25,mlp.up_proj,32.39283371,0.01000,0.647
|
| 182 |
+
25,mlp.gate_proj,36.58316803,0.01000,0.561
|
| 183 |
+
25,mlp.down_proj,8.68100739,0.01000,2.829
|
| 184 |
+
26,self_attn.k_proj,8.18059158,0.01000,0.703
|
| 185 |
+
26,self_attn.v_proj,9.73805428,0.01000,0.606
|
| 186 |
+
26,self_attn.q_proj,35.29013062,0.01000,0.609
|
| 187 |
+
26,self_attn.o_proj,1.64416206,0.01000,1.029
|
| 188 |
+
26,mlp.up_proj,37.90194702,0.01000,0.655
|
| 189 |
+
26,mlp.gate_proj,41.78019714,0.01000,0.570
|
| 190 |
+
26,mlp.down_proj,9.65947247,0.01000,2.646
|
| 191 |
+
27,self_attn.k_proj,9.37205124,0.01000,0.644
|
| 192 |
+
27,self_attn.v_proj,12.03858185,0.01000,0.552
|
| 193 |
+
27,self_attn.q_proj,41.76227951,0.01000,0.554
|
| 194 |
+
27,self_attn.o_proj,1.72142029,0.01000,0.998
|
| 195 |
+
27,mlp.up_proj,42.76330566,0.01000,0.647
|
| 196 |
+
27,mlp.gate_proj,45.72332764,0.01000,0.566
|
| 197 |
+
27,mlp.down_proj,13.29294109,0.01000,2.657
|
| 198 |
+
28,self_attn.k_proj,11.01844501,0.01000,0.636
|
| 199 |
+
28,self_attn.v_proj,12.33791637,0.01000,0.550
|
| 200 |
+
28,self_attn.q_proj,44.51463318,0.01000,0.554
|
| 201 |
+
28,self_attn.o_proj,2.65718555,0.01000,1.000
|
| 202 |
+
28,mlp.up_proj,49.45624161,0.01000,0.653
|
| 203 |
+
28,mlp.gate_proj,50.92063141,0.01000,0.563
|
| 204 |
+
28,mlp.down_proj,18.92489243,0.01000,2.806
|
| 205 |
+
29,self_attn.k_proj,23.87117004,0.01000,0.650
|
| 206 |
+
29,self_attn.v_proj,33.11904907,0.01000,0.551
|
| 207 |
+
29,self_attn.q_proj,99.74765778,0.01000,0.552
|
| 208 |
+
29,self_attn.o_proj,3.10340786,0.01000,0.981
|
| 209 |
+
29,mlp.up_proj,59.07789612,0.01000,0.652
|
| 210 |
+
29,mlp.gate_proj,58.26216125,0.01000,0.562
|
| 211 |
+
29,mlp.down_proj,20.03937149,0.01000,2.770
|
| 212 |
+
30,self_attn.k_proj,30.15834808,0.01000,0.636
|
| 213 |
+
30,self_attn.v_proj,37.56179428,0.01000,0.550
|
| 214 |
+
30,self_attn.q_proj,120.38098145,0.01000,0.552
|
| 215 |
+
30,self_attn.o_proj,4.69311810,0.01000,0.974
|
| 216 |
+
30,mlp.up_proj,64.21419525,0.01000,0.655
|
| 217 |
+
30,mlp.gate_proj,61.41302109,0.01000,0.566
|
| 218 |
+
30,mlp.down_proj,26.27643013,0.01000,2.646
|
| 219 |
+
31,self_attn.k_proj,39.68087006,0.01000,0.644
|
| 220 |
+
31,self_attn.v_proj,55.66039276,0.01000,0.550
|
| 221 |
+
31,self_attn.q_proj,148.81207275,0.01000,0.554
|
| 222 |
+
31,self_attn.o_proj,5.62770224,0.01000,0.992
|
| 223 |
+
31,mlp.up_proj,67.36556244,0.01000,0.656
|
| 224 |
+
31,mlp.gate_proj,61.42463684,0.01000,0.564
|
| 225 |
+
31,mlp.down_proj,33.80282211,0.01000,2.631
|
| 226 |
+
32,self_attn.k_proj,52.13278198,0.01000,0.647
|
| 227 |
+
32,self_attn.v_proj,80.29966736,0.01000,0.550
|
| 228 |
+
32,self_attn.q_proj,210.71531677,0.01000,0.547
|
| 229 |
+
32,self_attn.o_proj,7.62773275,0.01000,0.983
|
| 230 |
+
32,mlp.up_proj,70.70653534,0.01000,0.653
|
| 231 |
+
32,mlp.gate_proj,63.02287674,0.01000,0.565
|
| 232 |
+
32,mlp.down_proj,44.33407593,0.01000,2.744
|
| 233 |
+
33,self_attn.k_proj,91.17549133,0.01000,0.645
|
| 234 |
+
33,self_attn.v_proj,181.99508667,0.01000,0.548
|
| 235 |
+
33,self_attn.q_proj,422.93328857,0.01000,0.555
|
| 236 |
+
33,self_attn.o_proj,16.37356377,0.01000,0.993
|
| 237 |
+
33,mlp.up_proj,76.78594971,0.01000,0.654
|
| 238 |
+
33,mlp.gate_proj,67.32464600,0.01000,0.564
|
| 239 |
+
33,mlp.down_proj,56.63261795,0.01000,2.873
|
| 240 |
+
34,self_attn.k_proj,80.26489258,0.01000,0.644
|
| 241 |
+
34,self_attn.v_proj,133.13087463,0.01000,0.546
|
| 242 |
+
34,self_attn.q_proj,352.78515625,0.01000,0.548
|
| 243 |
+
34,self_attn.o_proj,23.87093353,0.01000,0.984
|
| 244 |
+
34,mlp.up_proj,84.84834290,0.01000,0.647
|
| 245 |
+
34,mlp.gate_proj,79.85603333,0.01000,0.565
|
| 246 |
+
34,mlp.down_proj,74.65843201,0.01000,2.654
|
| 247 |
+
35,self_attn.k_proj,48.68472672,0.01000,0.644
|
| 248 |
+
35,self_attn.v_proj,63.22115326,0.01000,0.549
|
| 249 |
+
35,self_attn.q_proj,187.34757996,0.01000,0.551
|
| 250 |
+
35,self_attn.o_proj,21.02386856,0.01000,0.983
|
| 251 |
+
35,mlp.up_proj,132.50225830,0.01000,0.646
|
| 252 |
+
35,mlp.gate_proj,127.69544983,0.01000,0.560
|
| 253 |
+
35,mlp.down_proj,131.40872192,0.01000,2.672
|
quantize_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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:2.2.0"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.01,
|
| 16 |
+
"damp_auto_increment": 0.0025,
|
| 17 |
+
"static_groups": false,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 0.0
|
| 20 |
+
}
|
| 21 |
+
}
|
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": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<unk>"
|
| 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 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<unk>",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 239 |
+
"unk_token": null,
|
| 240 |
+
"_commit_hash": null
|
| 241 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|