Upload folder using huggingface_hub
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 +197 -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": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 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 sha256:8e17e40784c059f3ddc2d4d427c3577f32e2f68e6a5e7714baa7162a83872f40
|
| 3 |
+
size 541343840
|
quant_log.csv
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.09850946,0.01000,0.851
|
| 3 |
+
0,self_attn.v_proj,0.07586420,0.01000,0.408
|
| 4 |
+
0,self_attn.q_proj,0.22626629,0.01000,0.427
|
| 5 |
+
0,self_attn.o_proj,0.06250948,0.01000,0.889
|
| 6 |
+
0,mlp.up_proj,1.20686150,0.01000,0.456
|
| 7 |
+
0,mlp.gate_proj,2.40769720,0.01000,0.444
|
| 8 |
+
0,mlp.down_proj,0.06865632,0.01000,1.604
|
| 9 |
+
1,self_attn.k_proj,0.04139863,0.01000,0.474
|
| 10 |
+
1,self_attn.v_proj,0.03884006,0.01000,0.423
|
| 11 |
+
1,self_attn.q_proj,0.09340510,0.01000,0.514
|
| 12 |
+
1,self_attn.o_proj,0.01172515,0.01000,0.988
|
| 13 |
+
1,mlp.up_proj,4.21653891,0.01000,0.711
|
| 14 |
+
1,mlp.gate_proj,14.37671852,0.01000,0.726
|
| 15 |
+
1,mlp.down_proj,0.08684395,0.01000,2.226
|
| 16 |
+
2,self_attn.k_proj,0.07648005,0.01000,0.703
|
| 17 |
+
2,self_attn.v_proj,0.07283711,0.01000,0.739
|
| 18 |
+
2,self_attn.q_proj,0.17951047,0.01000,0.719
|
| 19 |
+
2,self_attn.o_proj,0.02008994,0.01000,1.110
|
| 20 |
+
2,mlp.up_proj,3.53466392,0.01000,0.649
|
| 21 |
+
2,mlp.gate_proj,9.86164284,0.01000,0.658
|
| 22 |
+
2,mlp.down_proj,3.31883287,0.01000,1.182
|
| 23 |
+
3,self_attn.k_proj,0.67591071,0.01000,0.422
|
| 24 |
+
3,self_attn.v_proj,0.68356144,0.01000,0.390
|
| 25 |
+
3,self_attn.q_proj,1.38537908,0.01000,0.403
|
| 26 |
+
3,self_attn.o_proj,0.03747530,0.01000,0.813
|
| 27 |
+
3,mlp.up_proj,4.85747910,0.01000,0.429
|
| 28 |
+
3,mlp.gate_proj,12.60369778,0.01000,0.410
|
| 29 |
+
3,mlp.down_proj,0.26924509,0.01000,-0.695
|
| 30 |
+
4,self_attn.k_proj,0.60738301,0.01000,0.589
|
| 31 |
+
4,self_attn.v_proj,0.62895143,0.01000,0.580
|
| 32 |
+
4,self_attn.q_proj,1.22826421,0.01000,0.395
|
| 33 |
+
4,self_attn.o_proj,0.08694792,0.01000,0.895
|
| 34 |
+
4,mlp.up_proj,5.18607664,0.01000,0.424
|
| 35 |
+
4,mlp.gate_proj,11.80922222,0.01000,0.417
|
| 36 |
+
4,mlp.down_proj,0.33178610,0.01000,1.255
|
| 37 |
+
5,self_attn.k_proj,0.91473466,0.01000,0.414
|
| 38 |
+
5,self_attn.v_proj,0.97595525,0.01000,0.399
|
| 39 |
+
5,self_attn.q_proj,2.19729996,0.01000,0.390
|
| 40 |
+
5,self_attn.o_proj,0.10701506,0.01000,0.853
|
| 41 |
+
5,mlp.up_proj,4.87147427,0.01000,0.447
|
| 42 |
+
5,mlp.gate_proj,8.15231133,0.01000,0.414
|
| 43 |
+
5,mlp.down_proj,0.37409323,0.01000,1.543
|
| 44 |
+
6,self_attn.k_proj,0.72675020,0.01000,0.387
|
| 45 |
+
6,self_attn.v_proj,0.66761994,0.01000,0.416
|
| 46 |
+
6,self_attn.q_proj,1.59998417,0.01000,0.580
|
| 47 |
+
6,self_attn.o_proj,0.09201059,0.01000,0.896
|
| 48 |
+
6,mlp.up_proj,6.21852303,0.01000,0.444
|
| 49 |
+
6,mlp.gate_proj,9.88837433,0.01000,0.398
|
| 50 |
+
6,mlp.down_proj,0.49651879,0.01000,1.820
|
| 51 |
+
7,self_attn.k_proj,1.26669955,0.01000,0.630
|
| 52 |
+
7,self_attn.v_proj,1.42955840,0.01000,0.521
|
| 53 |
+
7,self_attn.q_proj,3.06221533,0.01000,0.607
|
| 54 |
+
7,self_attn.o_proj,0.13521528,0.01000,1.171
|
| 55 |
+
7,mlp.up_proj,6.99258566,0.01000,0.594
|
| 56 |
+
7,mlp.gate_proj,11.28202152,0.01000,0.617
|
| 57 |
+
7,mlp.down_proj,0.60300756,0.01000,1.500
|
| 58 |
+
8,self_attn.k_proj,1.67595625,0.01000,0.619
|
| 59 |
+
8,self_attn.v_proj,1.60502338,0.01000,0.603
|
| 60 |
+
8,self_attn.q_proj,3.77824259,0.01000,0.620
|
| 61 |
+
8,self_attn.o_proj,0.14908858,0.01000,1.397
|
| 62 |
+
8,mlp.up_proj,7.38887978,0.01000,0.699
|
| 63 |
+
8,mlp.gate_proj,11.49653625,0.01000,0.727
|
| 64 |
+
8,mlp.down_proj,0.69127196,0.01000,2.227
|
| 65 |
+
9,self_attn.k_proj,2.98744106,0.01000,0.424
|
| 66 |
+
9,self_attn.v_proj,3.08891487,0.01000,0.411
|
| 67 |
+
9,self_attn.q_proj,7.24598789,0.01000,0.376
|
| 68 |
+
9,self_attn.o_proj,0.24744949,0.01000,-1.119
|
| 69 |
+
9,mlp.up_proj,8.45534515,0.01000,0.373
|
| 70 |
+
9,mlp.gate_proj,13.44919872,0.01000,0.372
|
| 71 |
+
9,mlp.down_proj,0.99226213,0.01000,1.276
|
| 72 |
+
10,self_attn.k_proj,2.64885235,0.01000,0.509
|
| 73 |
+
10,self_attn.v_proj,2.75350857,0.01000,0.495
|
| 74 |
+
10,self_attn.q_proj,6.37406826,0.01000,0.553
|
| 75 |
+
10,self_attn.o_proj,0.24520609,0.01000,0.987
|
| 76 |
+
10,mlp.up_proj,8.50265503,0.01000,0.465
|
| 77 |
+
10,mlp.gate_proj,13.53136253,0.01000,0.459
|
| 78 |
+
10,mlp.down_proj,1.33377266,0.01000,1.378
|
| 79 |
+
11,self_attn.k_proj,4.98540545,0.01000,0.455
|
| 80 |
+
11,self_attn.v_proj,4.54301262,0.01000,0.453
|
| 81 |
+
11,self_attn.q_proj,12.94447422,0.01000,0.445
|
| 82 |
+
11,self_attn.o_proj,0.57048726,0.01000,0.945
|
| 83 |
+
11,mlp.up_proj,8.60743999,0.01000,0.486
|
| 84 |
+
11,mlp.gate_proj,11.23224926,0.01000,0.478
|
| 85 |
+
11,mlp.down_proj,1.66301322,0.01000,1.320
|
| 86 |
+
12,self_attn.k_proj,4.47545052,0.01000,0.556
|
| 87 |
+
12,self_attn.v_proj,4.59355307,0.01000,0.547
|
| 88 |
+
12,self_attn.q_proj,11.99758339,0.01000,0.570
|
| 89 |
+
12,self_attn.o_proj,0.24353495,0.01000,0.980
|
| 90 |
+
12,mlp.up_proj,8.05024338,0.01000,0.470
|
| 91 |
+
12,mlp.gate_proj,9.81564045,0.01000,0.467
|
| 92 |
+
12,mlp.down_proj,1.52156746,0.01000,1.359
|
| 93 |
+
13,self_attn.k_proj,4.28024578,0.01000,0.455
|
| 94 |
+
13,self_attn.v_proj,5.05019331,0.01000,0.459
|
| 95 |
+
13,self_attn.q_proj,12.57633018,0.01000,0.460
|
| 96 |
+
13,self_attn.o_proj,0.35622856,0.01000,0.909
|
| 97 |
+
13,mlp.up_proj,8.56893921,0.01000,0.460
|
| 98 |
+
13,mlp.gate_proj,10.62047768,0.01000,0.542
|
| 99 |
+
13,mlp.down_proj,1.53902888,0.01000,1.246
|
| 100 |
+
14,self_attn.k_proj,5.75165176,0.01000,0.463
|
| 101 |
+
14,self_attn.v_proj,6.18406296,0.01000,0.434
|
| 102 |
+
14,self_attn.q_proj,15.81763935,0.01000,0.461
|
| 103 |
+
14,self_attn.o_proj,0.35870335,0.01000,0.932
|
| 104 |
+
14,mlp.up_proj,9.21350956,0.01000,0.457
|
| 105 |
+
14,mlp.gate_proj,11.32985497,0.01000,0.433
|
| 106 |
+
14,mlp.down_proj,2.05143332,0.01000,1.450
|
| 107 |
+
15,self_attn.k_proj,10.10069084,0.01000,0.471
|
| 108 |
+
15,self_attn.v_proj,12.60639000,0.01000,0.462
|
| 109 |
+
15,self_attn.q_proj,31.56911850,0.01000,0.458
|
| 110 |
+
15,self_attn.o_proj,0.54869986,0.01000,0.878
|
| 111 |
+
15,mlp.up_proj,10.21630764,0.01000,0.463
|
| 112 |
+
15,mlp.gate_proj,12.16793251,0.01000,0.475
|
| 113 |
+
15,mlp.down_proj,2.27123475,0.01000,-0.618
|
| 114 |
+
16,self_attn.k_proj,14.20170116,0.01000,0.449
|
| 115 |
+
16,self_attn.v_proj,13.06950951,0.01000,0.456
|
| 116 |
+
16,self_attn.q_proj,40.14150238,0.01000,0.458
|
| 117 |
+
16,self_attn.o_proj,0.68756855,0.01000,1.101
|
| 118 |
+
16,mlp.up_proj,11.80347443,0.01000,0.433
|
| 119 |
+
16,mlp.gate_proj,13.10005951,0.01000,0.460
|
| 120 |
+
16,mlp.down_proj,4.53475285,0.01000,1.299
|
| 121 |
+
17,self_attn.k_proj,29.83925247,0.01000,0.438
|
| 122 |
+
17,self_attn.v_proj,35.82016754,0.01000,0.441
|
| 123 |
+
17,self_attn.q_proj,90.73204041,0.01000,0.450
|
| 124 |
+
17,self_attn.o_proj,1.52864456,0.01000,0.871
|
| 125 |
+
17,mlp.up_proj,16.85394669,0.01000,0.503
|
| 126 |
+
17,mlp.gate_proj,19.09194946,0.01000,0.473
|
| 127 |
+
17,mlp.down_proj,5.12950706,0.01000,1.328
|
| 128 |
+
18,self_attn.k_proj,27.85187912,0.01000,0.491
|
| 129 |
+
18,self_attn.v_proj,29.46336555,0.01000,0.440
|
| 130 |
+
18,self_attn.q_proj,86.81141663,0.01000,0.500
|
| 131 |
+
18,self_attn.o_proj,1.21956921,0.01000,-1.325
|
| 132 |
+
18,mlp.up_proj,20.33577156,0.01000,0.450
|
| 133 |
+
18,mlp.gate_proj,23.08765602,0.01000,0.506
|
| 134 |
+
18,mlp.down_proj,8.18551445,0.01000,1.637
|
| 135 |
+
19,self_attn.k_proj,47.84007645,0.01000,0.482
|
| 136 |
+
19,self_attn.v_proj,59.33264923,0.01000,0.453
|
| 137 |
+
19,self_attn.q_proj,156.72351074,0.01000,0.468
|
| 138 |
+
19,self_attn.o_proj,2.17994380,0.01000,1.132
|
| 139 |
+
19,mlp.up_proj,25.84054565,0.01000,0.429
|
| 140 |
+
19,mlp.gate_proj,24.49751282,0.01000,0.434
|
| 141 |
+
19,mlp.down_proj,16.08885384,0.01000,1.426
|
| 142 |
+
20,self_attn.k_proj,66.53054047,0.01000,0.480
|
| 143 |
+
20,self_attn.v_proj,79.11817932,0.01000,0.449
|
| 144 |
+
20,self_attn.q_proj,194.38667297,0.01000,0.451
|
| 145 |
+
20,self_attn.o_proj,2.74797773,0.01000,0.900
|
| 146 |
+
20,mlp.up_proj,28.64339828,0.01000,0.483
|
| 147 |
+
20,mlp.gate_proj,25.69481659,0.01000,0.461
|
| 148 |
+
20,mlp.down_proj,19.23760605,0.01000,1.325
|
| 149 |
+
21,self_attn.k_proj,113.03172302,0.01000,0.433
|
| 150 |
+
21,self_attn.v_proj,146.76942444,0.01000,0.426
|
| 151 |
+
21,self_attn.q_proj,324.40625000,0.01000,0.427
|
| 152 |
+
21,self_attn.o_proj,5.76776075,0.01000,0.925
|
| 153 |
+
21,mlp.up_proj,34.46822739,0.01000,0.407
|
| 154 |
+
21,mlp.gate_proj,27.89905167,0.01000,0.447
|
| 155 |
+
21,mlp.down_proj,26.42908859,0.01000,1.104
|
| 156 |
+
22,self_attn.k_proj,125.87751770,0.01000,0.426
|
| 157 |
+
22,self_attn.v_proj,180.92504883,0.01000,0.424
|
| 158 |
+
22,self_attn.q_proj,331.65649414,0.01000,0.431
|
| 159 |
+
22,self_attn.o_proj,4.63394165,0.01000,0.739
|
| 160 |
+
22,mlp.up_proj,37.16413116,0.01000,0.366
|
| 161 |
+
22,mlp.gate_proj,29.45936966,0.01000,0.397
|
| 162 |
+
22,mlp.down_proj,28.59059715,0.01000,1.551
|
| 163 |
+
23,self_attn.k_proj,171.20681763,0.01000,0.501
|
| 164 |
+
23,self_attn.v_proj,195.14624023,0.01000,0.458
|
| 165 |
+
23,self_attn.q_proj,383.41241455,0.01000,0.468
|
| 166 |
+
23,self_attn.o_proj,7.37380075,0.01000,0.937
|
| 167 |
+
23,mlp.up_proj,42.09543228,0.01000,0.470
|
| 168 |
+
23,mlp.gate_proj,32.35834503,0.01000,0.468
|
| 169 |
+
23,mlp.down_proj,29.46091080,0.01000,1.385
|
| 170 |
+
24,self_attn.k_proj,291.67578125,0.01000,0.474
|
| 171 |
+
24,self_attn.v_proj,316.21063232,0.01000,0.479
|
| 172 |
+
24,self_attn.q_proj,754.08447266,0.01000,0.472
|
| 173 |
+
24,self_attn.o_proj,7.86809063,0.01000,1.055
|
| 174 |
+
24,mlp.up_proj,39.64069748,0.01000,0.484
|
| 175 |
+
24,mlp.gate_proj,29.28566170,0.01000,0.590
|
| 176 |
+
24,mlp.down_proj,30.14324951,0.01000,2.362
|
| 177 |
+
25,self_attn.k_proj,349.52825928,0.01000,0.477
|
| 178 |
+
25,self_attn.v_proj,526.72943115,0.01000,0.477
|
| 179 |
+
25,self_attn.q_proj,925.39587402,0.01000,0.482
|
| 180 |
+
25,self_attn.o_proj,10.81455994,0.01000,0.979
|
| 181 |
+
25,mlp.up_proj,39.06259918,0.01000,0.487
|
| 182 |
+
25,mlp.gate_proj,27.49106216,0.01000,0.495
|
| 183 |
+
25,mlp.down_proj,37.65495300,0.01000,1.569
|
| 184 |
+
26,self_attn.k_proj,347.12860107,0.01000,0.496
|
| 185 |
+
26,self_attn.v_proj,485.27230835,0.01000,0.483
|
| 186 |
+
26,self_attn.q_proj,980.94482422,0.01000,0.490
|
| 187 |
+
26,self_attn.o_proj,29.47231483,0.01000,1.047
|
| 188 |
+
26,mlp.up_proj,41.97579956,0.01000,0.491
|
| 189 |
+
26,mlp.gate_proj,30.15745354,0.01000,0.496
|
| 190 |
+
26,mlp.down_proj,57.37902069,0.01000,1.621
|
| 191 |
+
27,self_attn.k_proj,254.03285217,0.01000,0.483
|
| 192 |
+
27,self_attn.v_proj,308.76086426,0.01000,-1.707
|
| 193 |
+
27,self_attn.q_proj,559.01251221,0.01000,0.476
|
| 194 |
+
27,self_attn.o_proj,16.60070992,0.01000,1.032
|
| 195 |
+
27,mlp.up_proj,74.08196259,0.01000,0.523
|
| 196 |
+
27,mlp.gate_proj,68.86535645,0.01000,0.492
|
| 197 |
+
27,mlp.down_proj,66.11711884,0.01000,1.535
|
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
|
|
|