Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +49 -0
- generation_config.json +14 -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 +209 -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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 70,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 36,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"quantization_config": {
|
19 |
+
"bits": 8,
|
20 |
+
"checkpoint_format": "gptq",
|
21 |
+
"desc_act": true,
|
22 |
+
"group_size": 128,
|
23 |
+
"lm_head": false,
|
24 |
+
"meta": {
|
25 |
+
"damp_auto_increment": 0.0025,
|
26 |
+
"damp_percent": 0.01,
|
27 |
+
"mse": 0.0,
|
28 |
+
"quantizer": [
|
29 |
+
"gptqmodel:2.1.1-dev"
|
30 |
+
],
|
31 |
+
"static_groups": false,
|
32 |
+
"true_sequential": true,
|
33 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
34 |
+
},
|
35 |
+
"pack_dtype": "int32",
|
36 |
+
"quant_method": "gptq",
|
37 |
+
"sym": true
|
38 |
+
},
|
39 |
+
"rms_norm_eps": 1e-06,
|
40 |
+
"rope_scaling": null,
|
41 |
+
"rope_theta": 1000000.0,
|
42 |
+
"sliding_window": 32768,
|
43 |
+
"tie_word_embeddings": true,
|
44 |
+
"torch_dtype": "bfloat16",
|
45 |
+
"transformers_version": "4.50.1",
|
46 |
+
"use_cache": true,
|
47 |
+
"use_sliding_window": false,
|
48 |
+
"vocab_size": 151936
|
49 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.50.1"
|
14 |
+
}
|
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:e030d6f7412c3880afa81dd61b401e8f9976889f4556375554159def48331210
|
3 |
+
size 3465861184
|
quant_log.csv
ADDED
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.00069060,0.01000,1.029
|
3 |
+
0,self_attn.v_proj,0.00008147,0.01000,0.472
|
4 |
+
0,self_attn.q_proj,0.00321008,0.01000,0.482
|
5 |
+
0,self_attn.o_proj,0.00047103,0.01000,0.493
|
6 |
+
0,mlp.up_proj,0.00436171,0.01000,0.541
|
7 |
+
0,mlp.gate_proj,0.00562274,0.01000,0.505
|
8 |
+
0,mlp.down_proj,0.00085413,0.01000,3.217
|
9 |
+
1,self_attn.k_proj,0.00034248,0.01000,0.533
|
10 |
+
1,self_attn.v_proj,0.00006137,0.01000,0.472
|
11 |
+
1,self_attn.q_proj,0.00121677,0.01000,0.474
|
12 |
+
1,self_attn.o_proj,0.00011810,0.01000,0.494
|
13 |
+
1,mlp.up_proj,0.13315737,0.01000,0.513
|
14 |
+
1,mlp.gate_proj,0.17934367,0.01000,0.497
|
15 |
+
1,mlp.down_proj,0.00008329,0.01000,3.138
|
16 |
+
2,self_attn.k_proj,0.00038424,0.01000,0.557
|
17 |
+
2,self_attn.v_proj,0.00008452,0.01000,0.510
|
18 |
+
2,self_attn.q_proj,0.00170009,0.01000,0.516
|
19 |
+
2,self_attn.o_proj,0.00010261,0.01000,0.486
|
20 |
+
2,mlp.up_proj,0.05518855,0.01000,0.508
|
21 |
+
2,mlp.gate_proj,0.04516597,0.01000,0.494
|
22 |
+
2,mlp.down_proj,0.00515580,0.01000,3.216
|
23 |
+
3,self_attn.k_proj,0.00154116,0.01000,0.507
|
24 |
+
3,self_attn.v_proj,0.00029368,0.01000,0.507
|
25 |
+
3,self_attn.q_proj,0.00724024,0.01000,0.480
|
26 |
+
3,self_attn.o_proj,0.00018070,0.01000,0.490
|
27 |
+
3,mlp.up_proj,0.08040726,0.01000,0.511
|
28 |
+
3,mlp.gate_proj,0.07821976,0.01000,0.494
|
29 |
+
3,mlp.down_proj,0.00053932,0.01000,3.158
|
30 |
+
4,self_attn.k_proj,0.00095915,0.01000,0.502
|
31 |
+
4,self_attn.v_proj,0.00031529,0.01000,0.475
|
32 |
+
4,self_attn.q_proj,0.00489937,0.01000,0.478
|
33 |
+
4,self_attn.o_proj,0.00030713,0.01000,0.590
|
34 |
+
4,mlp.up_proj,0.05972803,0.01000,0.514
|
35 |
+
4,mlp.gate_proj,0.07408385,0.01000,0.552
|
36 |
+
4,mlp.down_proj,0.00066552,0.01000,3.155
|
37 |
+
5,self_attn.k_proj,0.00147027,0.01000,0.493
|
38 |
+
5,self_attn.v_proj,0.00048919,0.01000,0.505
|
39 |
+
5,self_attn.q_proj,0.00825339,0.01000,0.559
|
40 |
+
5,self_attn.o_proj,0.00023145,0.01000,0.502
|
41 |
+
5,mlp.up_proj,0.08986730,0.01000,0.519
|
42 |
+
5,mlp.gate_proj,0.10963946,0.01000,0.501
|
43 |
+
5,mlp.down_proj,0.00130154,0.01000,3.170
|
44 |
+
6,self_attn.k_proj,0.00103089,0.01000,0.504
|
45 |
+
6,self_attn.v_proj,0.00061901,0.01000,0.471
|
46 |
+
6,self_attn.q_proj,0.00609575,0.01000,0.473
|
47 |
+
6,self_attn.o_proj,0.00063878,0.01000,0.489
|
48 |
+
6,mlp.up_proj,0.11683443,0.01000,0.511
|
49 |
+
6,mlp.gate_proj,0.13332176,0.01000,0.500
|
50 |
+
6,mlp.down_proj,0.00145119,0.01000,3.157
|
51 |
+
7,self_attn.k_proj,0.00135148,0.01000,0.495
|
52 |
+
7,self_attn.v_proj,0.00083617,0.01000,0.468
|
53 |
+
7,self_attn.q_proj,0.00884062,0.01000,0.472
|
54 |
+
7,self_attn.o_proj,0.00045116,0.01000,0.491
|
55 |
+
7,mlp.up_proj,0.12256874,0.01000,0.532
|
56 |
+
7,mlp.gate_proj,0.14637680,0.01000,0.573
|
57 |
+
7,mlp.down_proj,0.00233087,0.01000,3.185
|
58 |
+
8,self_attn.k_proj,0.00143536,0.01000,0.500
|
59 |
+
8,self_attn.v_proj,0.00096026,0.01000,0.524
|
60 |
+
8,self_attn.q_proj,0.00936532,0.01000,0.530
|
61 |
+
8,self_attn.o_proj,0.00049681,0.01000,0.540
|
62 |
+
8,mlp.up_proj,0.12503704,0.01000,0.526
|
63 |
+
8,mlp.gate_proj,0.17915115,0.01000,0.505
|
64 |
+
8,mlp.down_proj,0.00234245,0.01000,3.183
|
65 |
+
9,self_attn.k_proj,0.00143120,0.01000,0.505
|
66 |
+
9,self_attn.v_proj,0.00079513,0.01000,0.479
|
67 |
+
9,self_attn.q_proj,0.00797836,0.01000,0.478
|
68 |
+
9,self_attn.o_proj,0.00068180,0.01000,0.495
|
69 |
+
9,mlp.up_proj,0.11117899,0.01000,0.518
|
70 |
+
9,mlp.gate_proj,0.16715510,0.01000,0.498
|
71 |
+
9,mlp.down_proj,0.00310383,0.01000,3.162
|
72 |
+
10,self_attn.k_proj,0.00160306,0.01000,0.492
|
73 |
+
10,self_attn.v_proj,0.00109001,0.01000,0.470
|
74 |
+
10,self_attn.q_proj,0.01080495,0.01000,0.478
|
75 |
+
10,self_attn.o_proj,0.00084409,0.01000,0.504
|
76 |
+
10,mlp.up_proj,0.08392834,0.01000,0.521
|
77 |
+
10,mlp.gate_proj,0.12971427,0.01000,0.562
|
78 |
+
10,mlp.down_proj,0.00405339,0.01000,3.183
|
79 |
+
11,self_attn.k_proj,0.00122218,0.01000,0.493
|
80 |
+
11,self_attn.v_proj,0.00099423,0.01000,0.550
|
81 |
+
11,self_attn.q_proj,0.00794288,0.01000,0.553
|
82 |
+
11,self_attn.o_proj,0.00098513,0.01000,0.497
|
83 |
+
11,mlp.up_proj,0.04812239,0.01000,0.509
|
84 |
+
11,mlp.gate_proj,0.06757517,0.01000,0.493
|
85 |
+
11,mlp.down_proj,0.00568819,0.01000,3.207
|
86 |
+
12,self_attn.k_proj,0.00135649,0.01000,0.495
|
87 |
+
12,self_attn.v_proj,0.00095998,0.01000,0.483
|
88 |
+
12,self_attn.q_proj,0.00892941,0.01000,0.483
|
89 |
+
12,self_attn.o_proj,0.00108744,0.01000,0.522
|
90 |
+
12,mlp.up_proj,0.05381161,0.01000,0.529
|
91 |
+
12,mlp.gate_proj,0.07598484,0.01000,0.505
|
92 |
+
12,mlp.down_proj,0.00539491,0.01000,3.291
|
93 |
+
13,self_attn.k_proj,0.00178134,0.01000,0.527
|
94 |
+
13,self_attn.v_proj,0.00058557,0.01000,0.491
|
95 |
+
13,self_attn.q_proj,0.00892488,0.01000,0.516
|
96 |
+
13,self_attn.o_proj,0.00064293,0.01000,0.504
|
97 |
+
13,mlp.up_proj,0.04396489,0.01000,0.554
|
98 |
+
13,mlp.gate_proj,0.04568858,0.01000,0.527
|
99 |
+
13,mlp.down_proj,0.00565900,0.01000,3.395
|
100 |
+
14,self_attn.k_proj,0.00135609,0.01000,0.493
|
101 |
+
14,self_attn.v_proj,0.00082203,0.01000,0.547
|
102 |
+
14,self_attn.q_proj,0.00883573,0.01000,0.470
|
103 |
+
14,self_attn.o_proj,0.00131206,0.01000,0.507
|
104 |
+
14,mlp.up_proj,0.04743307,0.01000,0.513
|
105 |
+
14,mlp.gate_proj,0.04887400,0.01000,0.497
|
106 |
+
14,mlp.down_proj,0.00661326,0.01000,3.147
|
107 |
+
15,self_attn.k_proj,0.00155714,0.01000,0.506
|
108 |
+
15,self_attn.v_proj,0.00092119,0.01000,0.479
|
109 |
+
15,self_attn.q_proj,0.00995570,0.01000,0.539
|
110 |
+
15,self_attn.o_proj,0.00136074,0.01000,0.500
|
111 |
+
15,mlp.up_proj,0.04853380,0.01000,0.511
|
112 |
+
15,mlp.gate_proj,0.04559516,0.01000,0.495
|
113 |
+
15,mlp.down_proj,0.00638492,0.01000,3.148
|
114 |
+
16,self_attn.k_proj,0.00198390,0.01000,0.530
|
115 |
+
16,self_attn.v_proj,0.00113709,0.01000,0.507
|
116 |
+
16,self_attn.q_proj,0.01223878,0.01000,0.475
|
117 |
+
16,self_attn.o_proj,0.00148312,0.01000,0.489
|
118 |
+
16,mlp.up_proj,0.04892960,0.01000,0.541
|
119 |
+
16,mlp.gate_proj,0.05012077,0.01000,0.561
|
120 |
+
16,mlp.down_proj,0.00597043,0.01000,3.166
|
121 |
+
17,self_attn.k_proj,0.00280038,0.01000,0.496
|
122 |
+
17,self_attn.v_proj,0.00146818,0.01000,0.540
|
123 |
+
17,self_attn.q_proj,0.01687030,0.01000,0.497
|
124 |
+
17,self_attn.o_proj,0.00135879,0.01000,0.496
|
125 |
+
17,mlp.up_proj,0.04682782,0.01000,0.510
|
126 |
+
17,mlp.gate_proj,0.04579859,0.01000,0.492
|
127 |
+
17,mlp.down_proj,0.00761481,0.01000,3.238
|
128 |
+
18,self_attn.k_proj,0.00169533,0.01000,0.504
|
129 |
+
18,self_attn.v_proj,0.00126828,0.01000,0.471
|
130 |
+
18,self_attn.q_proj,0.01179836,0.01000,0.482
|
131 |
+
18,self_attn.o_proj,0.00126228,0.01000,0.522
|
132 |
+
18,mlp.up_proj,0.04505775,0.01000,0.512
|
133 |
+
18,mlp.gate_proj,0.04577068,0.01000,0.498
|
134 |
+
18,mlp.down_proj,0.00619347,0.01000,3.186
|
135 |
+
19,self_attn.k_proj,0.00236209,0.01000,0.514
|
136 |
+
19,self_attn.v_proj,0.00123736,0.01000,0.491
|
137 |
+
19,self_attn.q_proj,0.01400776,0.01000,0.526
|
138 |
+
19,self_attn.o_proj,0.00176100,0.01000,0.493
|
139 |
+
19,mlp.up_proj,0.04820779,0.01000,0.553
|
140 |
+
19,mlp.gate_proj,0.04570930,0.01000,0.600
|
141 |
+
19,mlp.down_proj,0.00793979,0.01000,3.357
|
142 |
+
20,self_attn.k_proj,0.00256892,0.01000,0.493
|
143 |
+
20,self_attn.v_proj,0.00260168,0.01000,0.550
|
144 |
+
20,self_attn.q_proj,0.02125032,0.01000,0.477
|
145 |
+
20,self_attn.o_proj,0.00280044,0.01000,0.497
|
146 |
+
20,mlp.up_proj,0.05057632,0.01000,0.519
|
147 |
+
20,mlp.gate_proj,0.04847589,0.01000,0.495
|
148 |
+
20,mlp.down_proj,0.00903307,0.01000,3.187
|
149 |
+
21,self_attn.k_proj,0.00277045,0.01000,0.500
|
150 |
+
21,self_attn.v_proj,0.00198452,0.01000,0.478
|
151 |
+
21,self_attn.q_proj,0.01851394,0.01000,0.479
|
152 |
+
21,self_attn.o_proj,0.00218527,0.01000,0.496
|
153 |
+
21,mlp.up_proj,0.05114579,0.01000,0.519
|
154 |
+
21,mlp.gate_proj,0.05338387,0.01000,0.499
|
155 |
+
21,mlp.down_proj,0.00733775,0.01000,3.188
|
156 |
+
22,self_attn.k_proj,0.00326175,0.01000,0.494
|
157 |
+
22,self_attn.v_proj,0.00250720,0.01000,0.475
|
158 |
+
22,self_attn.q_proj,0.02128556,0.01000,0.477
|
159 |
+
22,self_attn.o_proj,0.00235567,0.01000,0.492
|
160 |
+
22,mlp.up_proj,0.05586936,0.01000,0.570
|
161 |
+
22,mlp.gate_proj,0.05644500,0.01000,0.512
|
162 |
+
22,mlp.down_proj,0.00800653,0.01000,3.235
|
163 |
+
23,self_attn.k_proj,0.00299606,0.01000,0.494
|
164 |
+
23,self_attn.v_proj,0.00155715,0.01000,0.471
|
165 |
+
23,self_attn.q_proj,0.01925512,0.01000,0.473
|
166 |
+
23,self_attn.o_proj,0.00178259,0.01000,0.536
|
167 |
+
23,mlp.up_proj,0.06007682,0.01000,0.521
|
168 |
+
23,mlp.gate_proj,0.05663780,0.01000,0.496
|
169 |
+
23,mlp.down_proj,0.00945445,0.01000,9.186
|
170 |
+
24,self_attn.k_proj,0.00225264,0.01000,0.980
|
171 |
+
24,self_attn.v_proj,0.00187703,0.01000,1.371
|
172 |
+
24,self_attn.q_proj,0.01681715,0.01000,6.686
|
173 |
+
24,self_attn.o_proj,0.00246775,0.01000,1.328
|
174 |
+
24,mlp.up_proj,0.06072681,0.01000,0.944
|
175 |
+
24,mlp.gate_proj,0.05807892,0.01000,1.001
|
176 |
+
24,mlp.down_proj,0.00991773,0.01000,18.358
|
177 |
+
25,self_attn.k_proj,0.00229649,0.01000,8.503
|
178 |
+
25,self_attn.v_proj,0.00291831,0.01000,4.319
|
179 |
+
25,self_attn.q_proj,0.02437538,0.01000,3.804
|
180 |
+
25,self_attn.o_proj,0.00237260,0.01000,1.286
|
181 |
+
25,mlp.up_proj,0.06846089,0.01000,10.826
|
182 |
+
25,mlp.gate_proj,0.06569070,0.01000,9.100
|
183 |
+
25,mlp.down_proj,0.01337931,0.01000,33.601
|
184 |
+
26,self_attn.k_proj,0.00267915,0.01000,1.255
|
185 |
+
26,self_attn.v_proj,0.00322842,0.01000,3.481
|
186 |
+
26,self_attn.q_proj,0.02083185,0.01000,5.436
|
187 |
+
26,self_attn.o_proj,0.00308602,0.01000,7.156
|
188 |
+
26,mlp.up_proj,0.08263549,0.01000,1.335
|
189 |
+
26,mlp.gate_proj,0.07662739,0.01000,3.503
|
190 |
+
26,mlp.down_proj,0.01771094,0.01000,21.777
|
191 |
+
27,self_attn.k_proj,0.00287940,0.01000,3.159
|
192 |
+
27,self_attn.v_proj,0.00416089,0.01000,4.204
|
193 |
+
27,self_attn.q_proj,0.03279902,0.01000,1.774
|
194 |
+
27,self_attn.o_proj,0.00550491,0.01000,3.372
|
195 |
+
27,mlp.up_proj,0.09059777,0.01000,3.954
|
196 |
+
27,mlp.gate_proj,0.08867668,0.01000,9.505
|
197 |
+
27,mlp.down_proj,0.02109897,0.01000,30.538
|
198 |
+
28,self_attn.k_proj,0.00278399,0.01000,7.684
|
199 |
+
28,self_attn.v_proj,0.00438421,0.01000,1.185
|
200 |
+
28,self_attn.q_proj,0.02441998,0.01000,1.490
|
201 |
+
28,self_attn.o_proj,0.00504620,0.01000,1.659
|
202 |
+
28,mlp.up_proj,0.10423768,0.01000,6.048
|
203 |
+
28,mlp.gate_proj,0.10313836,0.01000,2.000
|
204 |
+
28,mlp.down_proj,0.02453683,0.01000,25.117
|
205 |
+
29,self_attn.k_proj,0.00324912,0.01000,7.286
|
206 |
+
29,self_attn.v_proj,0.00431707,0.01000,3.652
|
207 |
+
29,self_attn.q_proj,0.02698709,0.01000,9.020
|
208 |
+
29,self_attn.o_proj,0.00393811,0.01000,1.285
|
209 |
+
29,mlp.up_proj,0.13072219,0.01000,7.825
|
210 |
+
29,mlp.gate_proj,0.12731788,0.01000,1.260
|
211 |
+
29,mlp.down_proj,0.03455354,0.01000,31.130
|
212 |
+
30,self_attn.k_proj,0.00299078,0.01000,3.355
|
213 |
+
30,self_attn.v_proj,0.00842608,0.01000,1.227
|
214 |
+
30,self_attn.q_proj,0.02935425,0.01000,9.509
|
215 |
+
30,self_attn.o_proj,0.00491209,0.01000,6.748
|
216 |
+
30,mlp.up_proj,0.17074524,0.01000,1.335
|
217 |
+
30,mlp.gate_proj,0.15690112,0.01000,1.254
|
218 |
+
30,mlp.down_proj,0.09282688,0.01000,20.732
|
219 |
+
31,self_attn.k_proj,0.00382955,0.01000,8.693
|
220 |
+
31,self_attn.v_proj,0.01071948,0.01000,5.567
|
221 |
+
31,self_attn.q_proj,0.03053109,0.01000,1.216
|
222 |
+
31,self_attn.o_proj,0.00866138,0.01000,2.271
|
223 |
+
31,mlp.up_proj,0.20006534,0.01000,9.636
|
224 |
+
31,mlp.gate_proj,0.17307433,0.01000,4.535
|
225 |
+
31,mlp.down_proj,0.08568206,0.01000,26.561
|
226 |
+
32,self_attn.k_proj,0.00522043,0.01000,4.314
|
227 |
+
32,self_attn.v_proj,0.03462721,0.01000,9.529
|
228 |
+
32,self_attn.q_proj,0.04134069,0.01000,2.139
|
229 |
+
32,self_attn.o_proj,0.00988561,0.01000,2.949
|
230 |
+
32,mlp.up_proj,0.19264194,0.01000,2.229
|
231 |
+
32,mlp.gate_proj,0.16856745,0.01000,4.380
|
232 |
+
32,mlp.down_proj,0.08202425,0.01000,25.548
|
233 |
+
33,self_attn.k_proj,0.00480200,0.01000,1.251
|
234 |
+
33,self_attn.v_proj,0.07019998,0.01000,1.479
|
235 |
+
33,self_attn.q_proj,0.05121958,0.01000,7.949
|
236 |
+
33,self_attn.o_proj,0.01627044,0.01000,5.901
|
237 |
+
33,mlp.up_proj,0.17824389,0.01000,1.281
|
238 |
+
33,mlp.gate_proj,0.14435218,0.01000,3.857
|
239 |
+
33,mlp.down_proj,0.14946091,0.01000,24.800
|
240 |
+
34,self_attn.k_proj,0.00254513,0.01000,8.091
|
241 |
+
34,self_attn.v_proj,0.00760822,0.01000,1.215
|
242 |
+
34,self_attn.q_proj,0.02376374,0.01000,1.308
|
243 |
+
34,self_attn.o_proj,0.01036366,0.01000,12.004
|
244 |
+
34,mlp.up_proj,0.18489864,0.01000,3.845
|
245 |
+
34,mlp.gate_proj,0.15819445,0.01000,1.324
|
246 |
+
34,mlp.down_proj,0.09072845,0.01000,20.542
|
247 |
+
35,self_attn.k_proj,0.00257981,0.01000,1.463
|
248 |
+
35,self_attn.v_proj,0.00711143,0.01000,7.436
|
249 |
+
35,self_attn.q_proj,0.02256388,0.01000,4.156
|
250 |
+
35,self_attn.o_proj,0.00808490,0.01000,1.323
|
251 |
+
35,mlp.up_proj,0.23674777,0.01000,13.245
|
252 |
+
35,mlp.gate_proj,0.22639820,0.01000,13.503
|
253 |
+
35,mlp.down_proj,0.13450164,0.01000,23.163
|
quantize_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 8,
|
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:2.1.1-dev"
|
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": "<|fim_pad|>"
|
25 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) 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{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|fim_pad|>",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
207 |
+
"unk_token": null,
|
208 |
+
"_commit_hash": null
|
209 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|