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 +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:db3efb62638df3912b67ff05698a093f01373f5940d05729b42cb1636bd41a37
|
3 |
+
size 1356909944
|
quant_log.csv
ADDED
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.07114227,0.01000,0.600
|
3 |
+
0,self_attn.v_proj,0.06271021,0.01000,0.443
|
4 |
+
0,self_attn.q_proj,0.14684428,0.01000,0.459
|
5 |
+
0,self_attn.o_proj,0.20455796,0.01000,0.496
|
6 |
+
0,mlp.up_proj,0.95415354,0.01000,0.496
|
7 |
+
0,mlp.gate_proj,1.45871198,0.01000,0.466
|
8 |
+
0,mlp.down_proj,0.31586921,0.01000,1.442
|
9 |
+
1,self_attn.k_proj,0.05271447,0.01000,0.473
|
10 |
+
1,self_attn.v_proj,0.05217995,0.01000,0.463
|
11 |
+
1,self_attn.q_proj,0.10997316,0.01000,0.471
|
12 |
+
1,self_attn.o_proj,0.06207019,0.01000,0.484
|
13 |
+
1,mlp.up_proj,9.83285427,0.01000,0.482
|
14 |
+
1,mlp.gate_proj,24.77632904,0.01000,0.469
|
15 |
+
1,mlp.down_proj,0.41462597,0.01000,1.427
|
16 |
+
2,self_attn.k_proj,0.10310683,0.01000,0.493
|
17 |
+
2,self_attn.v_proj,0.10245017,0.01000,0.460
|
18 |
+
2,self_attn.q_proj,0.22838725,0.01000,0.466
|
19 |
+
2,self_attn.o_proj,0.10580672,0.01000,0.489
|
20 |
+
2,mlp.up_proj,8.80762863,0.01000,0.472
|
21 |
+
2,mlp.gate_proj,22.06496811,0.01000,0.445
|
22 |
+
2,mlp.down_proj,535.41107178,0.01000,1.429
|
23 |
+
3,self_attn.k_proj,0.78096557,0.01000,0.505
|
24 |
+
3,self_attn.v_proj,0.78984427,0.01000,0.471
|
25 |
+
3,self_attn.q_proj,1.54680932,0.01000,0.471
|
26 |
+
3,self_attn.o_proj,0.22266930,0.01000,0.498
|
27 |
+
3,mlp.up_proj,11.51662636,0.01000,0.504
|
28 |
+
3,mlp.gate_proj,26.70483780,0.01000,0.477
|
29 |
+
3,mlp.down_proj,1.33799505,0.01000,1.462
|
30 |
+
4,self_attn.k_proj,0.72830570,0.01000,0.473
|
31 |
+
4,self_attn.v_proj,0.78775412,0.01000,0.439
|
32 |
+
4,self_attn.q_proj,1.50708663,0.01000,0.441
|
33 |
+
4,self_attn.o_proj,0.41974008,0.01000,0.467
|
34 |
+
4,mlp.up_proj,13.04739189,0.01000,0.474
|
35 |
+
4,mlp.gate_proj,27.74795341,0.01000,0.446
|
36 |
+
4,mlp.down_proj,1.72413623,0.01000,1.501
|
37 |
+
5,self_attn.k_proj,1.03371572,0.01000,0.503
|
38 |
+
5,self_attn.v_proj,1.13659787,0.01000,0.470
|
39 |
+
5,self_attn.q_proj,2.30706596,0.01000,0.470
|
40 |
+
5,self_attn.o_proj,0.53175581,0.01000,0.467
|
41 |
+
5,mlp.up_proj,9.60116577,0.01000,0.491
|
42 |
+
5,mlp.gate_proj,14.03951931,0.01000,0.464
|
43 |
+
5,mlp.down_proj,2.32746410,0.01000,1.430
|
44 |
+
6,self_attn.k_proj,1.00857258,0.01000,0.474
|
45 |
+
6,self_attn.v_proj,0.94336653,0.01000,0.442
|
46 |
+
6,self_attn.q_proj,2.09217811,0.01000,0.446
|
47 |
+
6,self_attn.o_proj,0.64230913,0.01000,0.467
|
48 |
+
6,mlp.up_proj,13.59673882,0.01000,0.474
|
49 |
+
6,mlp.gate_proj,19.45661545,0.01000,0.459
|
50 |
+
6,mlp.down_proj,3.66275406,0.01000,1.523
|
51 |
+
7,self_attn.k_proj,2.09201455,0.01000,0.506
|
52 |
+
7,self_attn.v_proj,2.32086754,0.01000,0.478
|
53 |
+
7,self_attn.q_proj,4.81967449,0.01000,0.477
|
54 |
+
7,self_attn.o_proj,0.86715150,0.01000,0.499
|
55 |
+
7,mlp.up_proj,18.15211487,0.01000,0.505
|
56 |
+
7,mlp.gate_proj,27.41961288,0.01000,0.475
|
57 |
+
7,mlp.down_proj,4.25278187,0.01000,1.518
|
58 |
+
8,self_attn.k_proj,2.86768913,0.01000,0.499
|
59 |
+
8,self_attn.v_proj,2.76806831,0.01000,0.466
|
60 |
+
8,self_attn.q_proj,5.98885918,0.01000,0.470
|
61 |
+
8,self_attn.o_proj,0.71131384,0.01000,0.497
|
62 |
+
8,mlp.up_proj,18.29696274,0.01000,0.501
|
63 |
+
8,mlp.gate_proj,24.85815048,0.01000,0.474
|
64 |
+
8,mlp.down_proj,4.86363125,0.01000,1.510
|
65 |
+
9,self_attn.k_proj,5.18654585,0.01000,0.471
|
66 |
+
9,self_attn.v_proj,5.13819170,0.01000,0.449
|
67 |
+
9,self_attn.q_proj,11.77273560,0.01000,0.441
|
68 |
+
9,self_attn.o_proj,2.00078821,0.01000,0.470
|
69 |
+
9,mlp.up_proj,20.29730988,0.01000,0.474
|
70 |
+
9,mlp.gate_proj,25.16665459,0.01000,0.446
|
71 |
+
9,mlp.down_proj,8.43008709,0.01000,1.465
|
72 |
+
10,self_attn.k_proj,4.39699650,0.01000,0.477
|
73 |
+
10,self_attn.v_proj,4.59224987,0.01000,0.456
|
74 |
+
10,self_attn.q_proj,9.83474731,0.01000,0.451
|
75 |
+
10,self_attn.o_proj,1.89988995,0.01000,0.483
|
76 |
+
10,mlp.up_proj,21.38986588,0.01000,0.504
|
77 |
+
10,mlp.gate_proj,25.49797440,0.01000,0.473
|
78 |
+
10,mlp.down_proj,11.03967762,0.01000,1.510
|
79 |
+
11,self_attn.k_proj,8.21639729,0.01000,0.479
|
80 |
+
11,self_attn.v_proj,7.35907364,0.01000,0.445
|
81 |
+
11,self_attn.q_proj,18.91122818,0.01000,0.445
|
82 |
+
11,self_attn.o_proj,4.71220970,0.01000,0.469
|
83 |
+
11,mlp.up_proj,23.39077759,0.01000,0.491
|
84 |
+
11,mlp.gate_proj,24.30593872,0.01000,0.464
|
85 |
+
11,mlp.down_proj,14.53606415,0.01000,1.464
|
86 |
+
12,self_attn.k_proj,9.01887226,0.01000,0.511
|
87 |
+
12,self_attn.v_proj,8.93775558,0.01000,0.475
|
88 |
+
12,self_attn.q_proj,20.22336006,0.01000,0.475
|
89 |
+
12,self_attn.o_proj,3.15767241,0.01000,0.490
|
90 |
+
12,mlp.up_proj,23.69978333,0.01000,0.492
|
91 |
+
12,mlp.gate_proj,23.40773010,0.01000,0.457
|
92 |
+
12,mlp.down_proj,13.95071316,0.01000,1.450
|
93 |
+
13,self_attn.k_proj,10.80947304,0.01000,0.473
|
94 |
+
13,self_attn.v_proj,11.58708477,0.01000,0.440
|
95 |
+
13,self_attn.q_proj,28.41043472,0.01000,0.445
|
96 |
+
13,self_attn.o_proj,4.35299778,0.01000,0.480
|
97 |
+
13,mlp.up_proj,25.00242615,0.01000,0.476
|
98 |
+
13,mlp.gate_proj,24.57505035,0.01000,0.455
|
99 |
+
13,mlp.down_proj,18.15122223,0.01000,1.444
|
100 |
+
14,self_attn.k_proj,17.51714706,0.01000,0.497
|
101 |
+
14,self_attn.v_proj,18.04700089,0.01000,0.468
|
102 |
+
14,self_attn.q_proj,42.27303314,0.01000,0.463
|
103 |
+
14,self_attn.o_proj,5.30609083,0.01000,0.472
|
104 |
+
14,mlp.up_proj,27.03120041,0.01000,0.480
|
105 |
+
14,mlp.gate_proj,25.95209885,0.01000,0.451
|
106 |
+
14,mlp.down_proj,22.86153030,0.01000,1.432
|
107 |
+
15,self_attn.k_proj,34.18364716,0.01000,0.497
|
108 |
+
15,self_attn.v_proj,40.16418839,0.01000,0.466
|
109 |
+
15,self_attn.q_proj,99.72208405,0.01000,0.473
|
110 |
+
15,self_attn.o_proj,11.91862297,0.01000,0.469
|
111 |
+
15,mlp.up_proj,31.59889603,0.01000,0.490
|
112 |
+
15,mlp.gate_proj,29.65262604,0.01000,0.469
|
113 |
+
15,mlp.down_proj,32.96525574,0.01000,1.506
|
114 |
+
16,self_attn.k_proj,50.75338745,0.01000,0.498
|
115 |
+
16,self_attn.v_proj,46.66554642,0.01000,0.465
|
116 |
+
16,self_attn.q_proj,128.15777588,0.01000,0.466
|
117 |
+
16,self_attn.o_proj,14.49590492,0.01000,0.470
|
118 |
+
16,mlp.up_proj,41.83290863,0.01000,0.476
|
119 |
+
16,mlp.gate_proj,36.63706970,0.01000,0.447
|
120 |
+
16,mlp.down_proj,78.94730377,0.01000,1.501
|
121 |
+
17,self_attn.k_proj,138.37619019,0.01000,0.481
|
122 |
+
17,self_attn.v_proj,155.36178589,0.01000,0.463
|
123 |
+
17,self_attn.q_proj,372.06481934,0.01000,0.448
|
124 |
+
17,self_attn.o_proj,38.35939789,0.01000,0.486
|
125 |
+
17,mlp.up_proj,62.04616165,0.01000,0.476
|
126 |
+
17,mlp.gate_proj,54.14920044,0.01000,0.448
|
127 |
+
17,mlp.down_proj,111.43744659,0.01000,1.435
|
128 |
+
18,self_attn.k_proj,151.19328308,0.01000,0.477
|
129 |
+
18,self_attn.v_proj,150.51007080,0.01000,0.459
|
130 |
+
18,self_attn.q_proj,403.53033447,0.01000,0.456
|
131 |
+
18,self_attn.o_proj,33.56160736,0.01000,0.471
|
132 |
+
18,mlp.up_proj,81.22657013,0.01000,0.555
|
133 |
+
18,mlp.gate_proj,70.57396698,0.01000,0.529
|
134 |
+
18,mlp.down_proj,178.23185730,0.01000,1.519
|
135 |
+
19,self_attn.k_proj,261.90435791,0.01000,0.503
|
136 |
+
19,self_attn.v_proj,282.16760254,0.01000,0.482
|
137 |
+
19,self_attn.q_proj,712.55236816,0.01000,0.474
|
138 |
+
19,self_attn.o_proj,62.32764816,0.01000,0.500
|
139 |
+
19,mlp.up_proj,108.45788574,0.01000,0.488
|
140 |
+
19,mlp.gate_proj,91.89966583,0.01000,0.476
|
141 |
+
19,mlp.down_proj,372.02542114,0.01000,1.533
|
142 |
+
20,self_attn.k_proj,424.24545288,0.01000,0.478
|
143 |
+
20,self_attn.v_proj,454.50985718,0.01000,0.444
|
144 |
+
20,self_attn.q_proj,1082.80407715,0.01000,0.449
|
145 |
+
20,self_attn.o_proj,101.83114624,0.01000,0.479
|
146 |
+
20,mlp.up_proj,135.17749023,0.01000,0.492
|
147 |
+
20,mlp.gate_proj,117.30091858,0.01000,0.473
|
148 |
+
20,mlp.down_proj,529.21905518,0.01000,1.511
|
149 |
+
21,self_attn.k_proj,665.27276611,0.01000,0.499
|
150 |
+
21,self_attn.v_proj,741.05126953,0.01000,0.468
|
151 |
+
21,self_attn.q_proj,1601.47827148,0.01000,0.447
|
152 |
+
21,self_attn.o_proj,167.93096924,0.01000,0.470
|
153 |
+
21,mlp.up_proj,169.13842773,0.01000,0.476
|
154 |
+
21,mlp.gate_proj,146.42749023,0.01000,0.448
|
155 |
+
21,mlp.down_proj,745.69061279,0.01000,1.428
|
156 |
+
22,self_attn.k_proj,804.48864746,0.01000,0.472
|
157 |
+
22,self_attn.v_proj,1004.24609375,0.01000,0.448
|
158 |
+
22,self_attn.q_proj,1916.98144531,0.01000,0.461
|
159 |
+
22,self_attn.o_proj,141.04286194,0.01000,0.463
|
160 |
+
22,mlp.up_proj,188.47378540,0.01000,0.476
|
161 |
+
22,mlp.gate_proj,165.64068604,0.01000,0.457
|
162 |
+
22,mlp.down_proj,843.61877441,0.01000,1.492
|
163 |
+
23,self_attn.k_proj,1125.70556641,0.01000,0.478
|
164 |
+
23,self_attn.v_proj,1245.50048828,0.01000,0.456
|
165 |
+
23,self_attn.q_proj,2323.92480469,0.01000,0.444
|
166 |
+
23,self_attn.o_proj,176.02182007,0.01000,0.474
|
167 |
+
23,mlp.up_proj,223.18539429,0.01000,0.480
|
168 |
+
23,mlp.gate_proj,198.56817627,0.01000,0.453
|
169 |
+
23,mlp.down_proj,925.89892578,0.01000,1.450
|
170 |
+
24,self_attn.k_proj,1905.89501953,0.01000,0.476
|
171 |
+
24,self_attn.v_proj,2126.29785156,0.01000,0.442
|
172 |
+
24,self_attn.q_proj,4544.92333984,0.01000,0.442
|
173 |
+
24,self_attn.o_proj,220.99414062,0.01000,0.469
|
174 |
+
24,mlp.up_proj,218.09120178,0.01000,0.480
|
175 |
+
24,mlp.gate_proj,188.41921997,0.01000,0.468
|
176 |
+
24,mlp.down_proj,1127.04858398,0.01000,1.444
|
177 |
+
25,self_attn.k_proj,2240.13427734,0.01000,0.475
|
178 |
+
25,self_attn.v_proj,3264.89599609,0.01000,0.441
|
179 |
+
25,self_attn.q_proj,5202.63769531,0.01000,0.442
|
180 |
+
25,self_attn.o_proj,273.60961914,0.01000,0.470
|
181 |
+
25,mlp.up_proj,206.46627808,0.01000,0.479
|
182 |
+
25,mlp.gate_proj,174.69842529,0.01000,0.454
|
183 |
+
25,mlp.down_proj,1342.83105469,0.01000,1.442
|
184 |
+
26,self_attn.k_proj,2047.58374023,0.01000,0.475
|
185 |
+
26,self_attn.v_proj,2847.05908203,0.01000,0.441
|
186 |
+
26,self_attn.q_proj,5104.44238281,0.01000,0.445
|
187 |
+
26,self_attn.o_proj,532.84490967,0.01000,0.473
|
188 |
+
26,mlp.up_proj,201.04057312,0.01000,0.476
|
189 |
+
26,mlp.gate_proj,173.91522217,0.01000,0.449
|
190 |
+
26,mlp.down_proj,1581.80273438,0.01000,1.447
|
191 |
+
27,self_attn.k_proj,1067.43774414,0.01000,0.476
|
192 |
+
27,self_attn.v_proj,1201.65100098,0.01000,0.443
|
193 |
+
27,self_attn.q_proj,2251.94140625,0.01000,0.444
|
194 |
+
27,self_attn.o_proj,320.76138306,0.01000,0.472
|
195 |
+
27,mlp.up_proj,264.07699585,0.01000,0.481
|
196 |
+
27,mlp.gate_proj,271.31008911,0.01000,0.451
|
197 |
+
27,mlp.down_proj,2308.78808594,0.01000,1.447
|
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
|
|