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": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6144,
|
| 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 sha256:1ae2e7ec9dbbde8423592351c53b06777df97e564f3b60a393f3fe575a9771ab
|
| 3 |
+
size 1356909944
|
quant_log.csv
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.06161176,0.01000,0.932
|
| 3 |
+
0,self_attn.v_proj,0.05438014,0.01000,0.723
|
| 4 |
+
0,self_attn.q_proj,0.12705065,0.01000,0.915
|
| 5 |
+
0,self_attn.o_proj,0.17126846,0.01000,0.846
|
| 6 |
+
0,mlp.up_proj,0.80178344,0.01000,1.060
|
| 7 |
+
0,mlp.gate_proj,1.22950339,0.01000,1.030
|
| 8 |
+
0,mlp.down_proj,0.29198846,0.01000,0.589
|
| 9 |
+
1,self_attn.k_proj,0.04196536,0.01000,0.766
|
| 10 |
+
1,self_attn.v_proj,0.04195968,0.01000,0.801
|
| 11 |
+
1,self_attn.q_proj,0.08776645,0.01000,0.850
|
| 12 |
+
1,self_attn.o_proj,0.05204657,0.01000,0.786
|
| 13 |
+
1,mlp.up_proj,7.74701595,0.01000,0.884
|
| 14 |
+
1,mlp.gate_proj,19.37592506,0.01000,-1.316
|
| 15 |
+
1,mlp.down_proj,0.42635429,0.01000,2.649
|
| 16 |
+
2,self_attn.k_proj,0.08282123,0.01000,0.777
|
| 17 |
+
2,self_attn.v_proj,0.08251686,0.01000,0.780
|
| 18 |
+
2,self_attn.q_proj,0.18313025,0.01000,0.831
|
| 19 |
+
2,self_attn.o_proj,0.09041101,0.01000,0.758
|
| 20 |
+
2,mlp.up_proj,6.97388744,0.01000,0.819
|
| 21 |
+
2,mlp.gate_proj,17.37420845,0.01000,0.842
|
| 22 |
+
2,mlp.down_proj,555.31311035,0.01000,2.470
|
| 23 |
+
3,self_attn.k_proj,0.66062665,0.01000,0.745
|
| 24 |
+
3,self_attn.v_proj,0.66629398,0.01000,0.738
|
| 25 |
+
3,self_attn.q_proj,1.30134702,0.01000,0.779
|
| 26 |
+
3,self_attn.o_proj,0.19163772,0.01000,0.752
|
| 27 |
+
3,mlp.up_proj,9.49505615,0.01000,0.824
|
| 28 |
+
3,mlp.gate_proj,22.15675545,0.01000,0.830
|
| 29 |
+
3,mlp.down_proj,1.11858487,0.01000,2.587
|
| 30 |
+
4,self_attn.k_proj,0.60883915,0.01000,0.758
|
| 31 |
+
4,self_attn.v_proj,0.65701765,0.01000,0.766
|
| 32 |
+
4,self_attn.q_proj,1.25714827,0.01000,0.778
|
| 33 |
+
4,self_attn.o_proj,0.33684582,0.01000,0.767
|
| 34 |
+
4,mlp.up_proj,10.67844296,0.01000,0.800
|
| 35 |
+
4,mlp.gate_proj,22.64768982,0.01000,0.814
|
| 36 |
+
4,mlp.down_proj,1.57849216,0.01000,2.662
|
| 37 |
+
5,self_attn.k_proj,0.86607969,0.01000,0.761
|
| 38 |
+
5,self_attn.v_proj,0.95299339,0.01000,0.767
|
| 39 |
+
5,self_attn.q_proj,1.92915726,0.01000,0.806
|
| 40 |
+
5,self_attn.o_proj,0.51527029,0.01000,0.788
|
| 41 |
+
5,mlp.up_proj,8.11690903,0.01000,0.815
|
| 42 |
+
5,mlp.gate_proj,11.88039017,0.01000,0.810
|
| 43 |
+
5,mlp.down_proj,2.06314588,0.01000,2.476
|
| 44 |
+
6,self_attn.k_proj,0.84522438,0.01000,0.771
|
| 45 |
+
6,self_attn.v_proj,0.79271960,0.01000,0.758
|
| 46 |
+
6,self_attn.q_proj,1.74664021,0.01000,0.806
|
| 47 |
+
6,self_attn.o_proj,0.51649594,0.01000,0.770
|
| 48 |
+
6,mlp.up_proj,11.36476040,0.01000,0.821
|
| 49 |
+
6,mlp.gate_proj,16.26104736,0.01000,0.898
|
| 50 |
+
6,mlp.down_proj,3.12330055,0.01000,2.463
|
| 51 |
+
7,self_attn.k_proj,1.74236369,0.01000,0.763
|
| 52 |
+
7,self_attn.v_proj,1.94380081,0.01000,0.762
|
| 53 |
+
7,self_attn.q_proj,4.01041460,0.01000,0.794
|
| 54 |
+
7,self_attn.o_proj,0.80392551,0.01000,0.767
|
| 55 |
+
7,mlp.up_proj,15.10862732,0.01000,0.819
|
| 56 |
+
7,mlp.gate_proj,22.81257248,0.01000,0.837
|
| 57 |
+
7,mlp.down_proj,3.62108111,0.01000,2.464
|
| 58 |
+
8,self_attn.k_proj,2.43949366,0.01000,0.745
|
| 59 |
+
8,self_attn.v_proj,2.31129289,0.01000,0.943
|
| 60 |
+
8,self_attn.q_proj,5.06256580,0.01000,1.057
|
| 61 |
+
8,self_attn.o_proj,0.60827088,0.01000,0.802
|
| 62 |
+
8,mlp.up_proj,15.40246868,0.01000,0.809
|
| 63 |
+
8,mlp.gate_proj,20.87147713,0.01000,0.801
|
| 64 |
+
8,mlp.down_proj,4.27449131,0.01000,2.384
|
| 65 |
+
9,self_attn.k_proj,4.37583876,0.01000,-0.010
|
| 66 |
+
9,self_attn.v_proj,4.23343515,0.01000,0.706
|
| 67 |
+
9,self_attn.q_proj,9.79721832,0.01000,0.719
|
| 68 |
+
9,self_attn.o_proj,1.85169268,0.01000,0.739
|
| 69 |
+
9,mlp.up_proj,16.51148033,0.01000,0.745
|
| 70 |
+
9,mlp.gate_proj,20.53764725,0.01000,0.745
|
| 71 |
+
9,mlp.down_proj,6.68374157,0.01000,2.179
|
| 72 |
+
10,self_attn.k_proj,3.51351452,0.01000,0.692
|
| 73 |
+
10,self_attn.v_proj,3.65583849,0.01000,0.691
|
| 74 |
+
10,self_attn.q_proj,7.80333757,0.01000,0.702
|
| 75 |
+
10,self_attn.o_proj,1.93884957,0.01000,0.745
|
| 76 |
+
10,mlp.up_proj,17.16555405,0.01000,0.722
|
| 77 |
+
10,mlp.gate_proj,20.50786018,0.01000,0.751
|
| 78 |
+
10,mlp.down_proj,9.01197052,0.01000,2.197
|
| 79 |
+
11,self_attn.k_proj,6.72875261,0.01000,0.697
|
| 80 |
+
11,self_attn.v_proj,5.92448235,0.01000,0.648
|
| 81 |
+
11,self_attn.q_proj,15.31981468,0.01000,0.650
|
| 82 |
+
11,self_attn.o_proj,4.41754627,0.01000,0.755
|
| 83 |
+
11,mlp.up_proj,18.27470398,0.01000,0.786
|
| 84 |
+
11,mlp.gate_proj,18.97273636,0.01000,0.760
|
| 85 |
+
11,mlp.down_proj,10.93863583,0.01000,2.211
|
| 86 |
+
12,self_attn.k_proj,6.80087852,0.01000,0.664
|
| 87 |
+
12,self_attn.v_proj,6.75032997,0.01000,0.680
|
| 88 |
+
12,self_attn.q_proj,15.24656105,0.01000,0.685
|
| 89 |
+
12,self_attn.o_proj,2.62905002,0.01000,0.684
|
| 90 |
+
12,mlp.up_proj,18.10563850,0.01000,0.837
|
| 91 |
+
12,mlp.gate_proj,17.88245010,0.01000,0.808
|
| 92 |
+
12,mlp.down_proj,10.52472878,0.01000,1.750
|
| 93 |
+
13,self_attn.k_proj,8.15466690,0.01000,0.707
|
| 94 |
+
13,self_attn.v_proj,8.60487556,0.01000,0.702
|
| 95 |
+
13,self_attn.q_proj,21.30573654,0.01000,0.736
|
| 96 |
+
13,self_attn.o_proj,3.62042069,0.01000,0.731
|
| 97 |
+
13,mlp.up_proj,18.99537659,0.01000,0.764
|
| 98 |
+
13,mlp.gate_proj,18.67168045,0.01000,0.876
|
| 99 |
+
13,mlp.down_proj,13.00555801,0.01000,2.089
|
| 100 |
+
14,self_attn.k_proj,13.40824318,0.01000,0.727
|
| 101 |
+
14,self_attn.v_proj,13.49943829,0.01000,0.687
|
| 102 |
+
14,self_attn.q_proj,32.17544556,0.01000,0.673
|
| 103 |
+
14,self_attn.o_proj,4.37822676,0.01000,0.702
|
| 104 |
+
14,mlp.up_proj,20.30528450,0.01000,0.753
|
| 105 |
+
14,mlp.gate_proj,19.48166656,0.01000,0.776
|
| 106 |
+
14,mlp.down_proj,16.70061111,0.01000,2.228
|
| 107 |
+
15,self_attn.k_proj,25.33942032,0.01000,0.636
|
| 108 |
+
15,self_attn.v_proj,29.75099182,0.01000,0.648
|
| 109 |
+
15,self_attn.q_proj,74.12033844,0.01000,0.662
|
| 110 |
+
15,self_attn.o_proj,9.15364933,0.01000,0.649
|
| 111 |
+
15,mlp.up_proj,23.37993050,0.01000,0.699
|
| 112 |
+
15,mlp.gate_proj,21.96615601,0.01000,0.709
|
| 113 |
+
15,mlp.down_proj,24.15357208,0.01000,2.310
|
| 114 |
+
16,self_attn.k_proj,37.24622726,0.01000,0.711
|
| 115 |
+
16,self_attn.v_proj,33.53807831,0.01000,0.698
|
| 116 |
+
16,self_attn.q_proj,92.94651794,0.01000,0.715
|
| 117 |
+
16,self_attn.o_proj,10.30152321,0.01000,0.665
|
| 118 |
+
16,mlp.up_proj,29.35601807,0.01000,0.695
|
| 119 |
+
16,mlp.gate_proj,25.80093002,0.01000,0.200
|
| 120 |
+
16,mlp.down_proj,60.27460098,0.01000,2.165
|
| 121 |
+
17,self_attn.k_proj,95.47402954,0.01000,0.684
|
| 122 |
+
17,self_attn.v_proj,105.25405884,0.01000,0.674
|
| 123 |
+
17,self_attn.q_proj,253.24885559,0.01000,0.657
|
| 124 |
+
17,self_attn.o_proj,28.11261368,0.01000,0.670
|
| 125 |
+
17,mlp.up_proj,42.57036591,0.01000,0.704
|
| 126 |
+
17,mlp.gate_proj,36.58126831,0.01000,0.717
|
| 127 |
+
17,mlp.down_proj,81.79136658,0.01000,2.167
|
| 128 |
+
18,self_attn.k_proj,102.99479675,0.01000,0.644
|
| 129 |
+
18,self_attn.v_proj,101.50364685,0.01000,0.670
|
| 130 |
+
18,self_attn.q_proj,275.00637817,0.01000,0.704
|
| 131 |
+
18,self_attn.o_proj,21.60307312,0.01000,0.651
|
| 132 |
+
18,mlp.up_proj,54.27608109,0.01000,0.661
|
| 133 |
+
18,mlp.gate_proj,46.83805847,0.01000,0.716
|
| 134 |
+
18,mlp.down_proj,132.89431763,0.01000,2.199
|
| 135 |
+
19,self_attn.k_proj,178.74481201,0.01000,0.711
|
| 136 |
+
19,self_attn.v_proj,189.77200317,0.01000,0.786
|
| 137 |
+
19,self_attn.q_proj,486.16369629,0.01000,0.783
|
| 138 |
+
19,self_attn.o_proj,41.97334290,0.01000,0.726
|
| 139 |
+
19,mlp.up_proj,73.76881409,0.01000,0.756
|
| 140 |
+
19,mlp.gate_proj,62.54061508,0.01000,0.787
|
| 141 |
+
19,mlp.down_proj,308.76110840,0.01000,2.161
|
| 142 |
+
20,self_attn.k_proj,298.62933350,0.01000,0.629
|
| 143 |
+
20,self_attn.v_proj,316.93182373,0.01000,0.640
|
| 144 |
+
20,self_attn.q_proj,764.87170410,0.01000,0.705
|
| 145 |
+
20,self_attn.o_proj,67.96992493,0.01000,0.644
|
| 146 |
+
20,mlp.up_proj,94.94843292,0.01000,0.728
|
| 147 |
+
20,mlp.gate_proj,82.94094849,0.01000,0.693
|
| 148 |
+
20,mlp.down_proj,463.50665283,0.01000,2.142
|
| 149 |
+
21,self_attn.k_proj,478.08056641,0.01000,0.662
|
| 150 |
+
21,self_attn.v_proj,546.54919434,0.01000,0.660
|
| 151 |
+
21,self_attn.q_proj,1147.31347656,0.01000,0.683
|
| 152 |
+
21,self_attn.o_proj,118.71049500,0.01000,0.655
|
| 153 |
+
21,mlp.up_proj,120.02677917,0.01000,0.708
|
| 154 |
+
21,mlp.gate_proj,103.04946899,0.01000,0.708
|
| 155 |
+
21,mlp.down_proj,659.67437744,0.01000,2.128
|
| 156 |
+
22,self_attn.k_proj,593.22070312,0.01000,0.665
|
| 157 |
+
22,self_attn.v_proj,763.92529297,0.01000,0.669
|
| 158 |
+
22,self_attn.q_proj,1391.22949219,0.01000,0.679
|
| 159 |
+
22,self_attn.o_proj,101.20243835,0.01000,0.657
|
| 160 |
+
22,mlp.up_proj,135.26795959,0.01000,0.796
|
| 161 |
+
22,mlp.gate_proj,118.14506531,0.01000,0.779
|
| 162 |
+
22,mlp.down_proj,766.93237305,0.01000,2.130
|
| 163 |
+
23,self_attn.k_proj,817.42401123,0.01000,0.667
|
| 164 |
+
23,self_attn.v_proj,912.42480469,0.01000,0.663
|
| 165 |
+
23,self_attn.q_proj,1677.90209961,0.01000,0.679
|
| 166 |
+
23,self_attn.o_proj,115.38923645,0.01000,0.684
|
| 167 |
+
23,mlp.up_proj,160.92965698,0.01000,0.767
|
| 168 |
+
23,mlp.gate_proj,142.50930786,0.01000,0.720
|
| 169 |
+
23,mlp.down_proj,837.10455322,0.01000,2.173
|
| 170 |
+
24,self_attn.k_proj,1420.40991211,0.01000,0.793
|
| 171 |
+
24,self_attn.v_proj,1595.83715820,0.01000,0.683
|
| 172 |
+
24,self_attn.q_proj,3344.17285156,0.01000,0.736
|
| 173 |
+
24,self_attn.o_proj,152.69662476,0.01000,0.738
|
| 174 |
+
24,mlp.up_proj,158.49810791,0.01000,0.714
|
| 175 |
+
24,mlp.gate_proj,136.60337830,0.01000,0.771
|
| 176 |
+
24,mlp.down_proj,973.98236084,0.01000,2.152
|
| 177 |
+
25,self_attn.k_proj,1685.52282715,0.01000,0.890
|
| 178 |
+
25,self_attn.v_proj,2474.76318359,0.01000,0.920
|
| 179 |
+
25,self_attn.q_proj,3874.19628906,0.01000,0.971
|
| 180 |
+
25,self_attn.o_proj,197.16078186,0.01000,0.679
|
| 181 |
+
25,mlp.up_proj,151.62023926,0.01000,0.738
|
| 182 |
+
25,mlp.gate_proj,128.06694031,0.01000,0.745
|
| 183 |
+
25,mlp.down_proj,1148.98022461,0.01000,2.151
|
| 184 |
+
26,self_attn.k_proj,1625.11279297,0.01000,0.675
|
| 185 |
+
26,self_attn.v_proj,2256.05908203,0.01000,0.691
|
| 186 |
+
26,self_attn.q_proj,3975.20971680,0.01000,0.716
|
| 187 |
+
26,self_attn.o_proj,443.28439331,0.01000,0.676
|
| 188 |
+
26,mlp.up_proj,148.50442505,0.01000,0.720
|
| 189 |
+
26,mlp.gate_proj,127.99733734,0.01000,0.741
|
| 190 |
+
26,mlp.down_proj,1423.76660156,0.01000,2.141
|
| 191 |
+
27,self_attn.k_proj,793.07702637,0.01000,0.666
|
| 192 |
+
27,self_attn.v_proj,898.25610352,0.01000,0.678
|
| 193 |
+
27,self_attn.q_proj,1676.92187500,0.01000,0.674
|
| 194 |
+
27,self_attn.o_proj,251.81840515,0.01000,0.676
|
| 195 |
+
27,mlp.up_proj,196.21633911,0.01000,0.717
|
| 196 |
+
27,mlp.gate_proj,199.20074463,0.01000,0.710
|
| 197 |
+
27,mlp.down_proj,2001.17333984,0.01000,2.171
|
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
|
|
|