Commit
·
827b52f
1
Parent(s):
9ef394b
first commit
Browse files- .gitattributes +2 -0
- config.json +52 -0
- model.safetensors +3 -0
- quant_log.csv +197 -0
- quantize_config.json +21 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +195 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "./modelzoo/DeepSeek-R1/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Qwen2ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 151643,
|
| 9 |
+
"eos_token_id": 151643,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1536,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8960,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"max_window_layers": 21,
|
| 16 |
+
"model_type": "qwen2",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bits": 4,
|
| 22 |
+
"checkpoint_format": "gptq",
|
| 23 |
+
"desc_act": true,
|
| 24 |
+
"dynamic": null,
|
| 25 |
+
"group_size": 128,
|
| 26 |
+
"lm_head": false,
|
| 27 |
+
"meta": {
|
| 28 |
+
"damp_auto_increment": 0.0025,
|
| 29 |
+
"damp_percent": 0.01,
|
| 30 |
+
"mse": 2.4,
|
| 31 |
+
"quantizer": [
|
| 32 |
+
"gptqmodel:1.7.4"
|
| 33 |
+
],
|
| 34 |
+
"static_groups": true,
|
| 35 |
+
"true_sequential": true,
|
| 36 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 37 |
+
},
|
| 38 |
+
"quant_method": "gptq",
|
| 39 |
+
"sym": false
|
| 40 |
+
},
|
| 41 |
+
"rms_norm_eps": 1e-06,
|
| 42 |
+
"rope_scaling": null,
|
| 43 |
+
"rope_theta": 10000,
|
| 44 |
+
"sliding_window": null,
|
| 45 |
+
"tie_word_embeddings": false,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"transformers_version": "4.47.1",
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"use_mrope": false,
|
| 50 |
+
"use_sliding_window": false,
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ec79127b6b3fd34d7111d60e4ace95a811b29bcc91f052ab5c023589a8bc966
|
| 3 |
+
size 1616610504
|
quant_log.csv
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,damp,time
|
| 2 |
+
0,self_attn.k_proj,1.89329,0.01000,1.746
|
| 3 |
+
0,self_attn.v_proj,0.43324,0.01000,0.846
|
| 4 |
+
0,self_attn.q_proj,9.99789,0.01000,0.943
|
| 5 |
+
0,self_attn.o_proj,7.82858,0.01000,0.841
|
| 6 |
+
0,mlp.up_proj,9.89530,0.01000,0.943
|
| 7 |
+
0,mlp.gate_proj,12.46054,0.01000,1.023
|
| 8 |
+
0,mlp.down_proj,4.40474,0.01000,4.953
|
| 9 |
+
1,self_attn.k_proj,0.98417,0.01000,0.753
|
| 10 |
+
1,self_attn.v_proj,0.36783,0.01000,0.777
|
| 11 |
+
1,self_attn.q_proj,3.50436,0.01000,0.851
|
| 12 |
+
1,self_attn.o_proj,3.42879,0.01000,0.831
|
| 13 |
+
1,mlp.up_proj,389.92950,0.01000,0.865
|
| 14 |
+
1,mlp.gate_proj,454.26639,0.01000,0.957
|
| 15 |
+
1,mlp.down_proj,5.22624,0.01000,4.683
|
| 16 |
+
2,self_attn.k_proj,3.70178,0.01000,0.763
|
| 17 |
+
2,self_attn.v_proj,1.52171,0.01000,0.860
|
| 18 |
+
2,self_attn.q_proj,16.07162,0.01000,0.841
|
| 19 |
+
2,self_attn.o_proj,9.91449,0.01000,0.887
|
| 20 |
+
2,mlp.up_proj,308.22095,0.01000,0.842
|
| 21 |
+
2,mlp.gate_proj,420.27692,0.01000,0.884
|
| 22 |
+
2,mlp.down_proj,88.49248,0.01000,4.796
|
| 23 |
+
3,self_attn.k_proj,3.80120,0.01000,0.764
|
| 24 |
+
3,self_attn.v_proj,2.27510,0.01000,0.798
|
| 25 |
+
3,self_attn.q_proj,17.93941,0.01000,0.984
|
| 26 |
+
3,self_attn.o_proj,7.47338,0.01000,0.758
|
| 27 |
+
3,mlp.up_proj,307.73297,0.01000,0.864
|
| 28 |
+
3,mlp.gate_proj,474.15442,0.01000,0.946
|
| 29 |
+
3,mlp.down_proj,16.00202,0.01000,4.897
|
| 30 |
+
4,self_attn.k_proj,5.87368,0.01000,0.766
|
| 31 |
+
4,self_attn.v_proj,4.15553,0.01000,0.758
|
| 32 |
+
4,self_attn.q_proj,29.11426,0.01000,0.758
|
| 33 |
+
4,self_attn.o_proj,15.56469,0.01000,0.821
|
| 34 |
+
4,mlp.up_proj,209.34375,0.01000,0.853
|
| 35 |
+
4,mlp.gate_proj,321.80746,0.01000,0.852
|
| 36 |
+
4,mlp.down_proj,29.10132,0.01000,5.236
|
| 37 |
+
5,self_attn.k_proj,6.94376,0.01000,0.751
|
| 38 |
+
5,self_attn.v_proj,5.71181,0.01000,0.763
|
| 39 |
+
5,self_attn.q_proj,31.99474,0.01000,0.823
|
| 40 |
+
5,self_attn.o_proj,20.54602,0.01000,0.750
|
| 41 |
+
5,mlp.up_proj,634.95178,0.01000,0.826
|
| 42 |
+
5,mlp.gate_proj,810.21619,0.01000,0.978
|
| 43 |
+
5,mlp.down_proj,14.33534,0.01000,4.796
|
| 44 |
+
6,self_attn.k_proj,8.46896,0.01000,0.760
|
| 45 |
+
6,self_attn.v_proj,5.34005,0.01000,0.746
|
| 46 |
+
6,self_attn.q_proj,38.27160,0.01000,0.781
|
| 47 |
+
6,self_attn.o_proj,13.97896,0.01000,0.857
|
| 48 |
+
6,mlp.up_proj,201.16391,0.01000,0.840
|
| 49 |
+
6,mlp.gate_proj,245.68216,0.01000,0.915
|
| 50 |
+
6,mlp.down_proj,31.48331,0.01000,5.693
|
| 51 |
+
7,self_attn.k_proj,4.06347,0.01000,0.769
|
| 52 |
+
7,self_attn.v_proj,3.30292,0.01000,0.753
|
| 53 |
+
7,self_attn.q_proj,19.85328,0.01000,0.793
|
| 54 |
+
7,self_attn.o_proj,16.42201,0.01000,0.761
|
| 55 |
+
7,mlp.up_proj,189.11932,0.01000,0.850
|
| 56 |
+
7,mlp.gate_proj,215.05936,0.01000,0.868
|
| 57 |
+
7,mlp.down_proj,33.96938,0.01000,5.062
|
| 58 |
+
8,self_attn.k_proj,7.65138,0.01000,0.778
|
| 59 |
+
8,self_attn.v_proj,5.60814,0.01000,0.808
|
| 60 |
+
8,self_attn.q_proj,39.91741,0.01000,1.094
|
| 61 |
+
8,self_attn.o_proj,26.49549,0.01000,0.801
|
| 62 |
+
8,mlp.up_proj,201.79288,0.01000,0.857
|
| 63 |
+
8,mlp.gate_proj,229.11200,0.01000,0.915
|
| 64 |
+
8,mlp.down_proj,34.69388,0.01000,5.004
|
| 65 |
+
9,self_attn.k_proj,7.74939,0.01000,0.766
|
| 66 |
+
9,self_attn.v_proj,4.70283,0.01000,0.801
|
| 67 |
+
9,self_attn.q_proj,36.21487,0.01000,1.024
|
| 68 |
+
9,self_attn.o_proj,21.40422,0.01000,0.803
|
| 69 |
+
9,mlp.up_proj,197.66116,0.01000,0.897
|
| 70 |
+
9,mlp.gate_proj,214.60152,0.01000,1.296
|
| 71 |
+
9,mlp.down_proj,39.45992,0.01000,4.795
|
| 72 |
+
10,self_attn.k_proj,8.52659,0.01000,0.769
|
| 73 |
+
10,self_attn.v_proj,7.38195,0.01000,0.796
|
| 74 |
+
10,self_attn.q_proj,41.32335,0.01000,0.787
|
| 75 |
+
10,self_attn.o_proj,33.53540,0.01000,0.898
|
| 76 |
+
10,mlp.up_proj,208.71655,0.01000,0.855
|
| 77 |
+
10,mlp.gate_proj,228.96078,0.01000,1.121
|
| 78 |
+
10,mlp.down_proj,42.96235,0.01000,4.770
|
| 79 |
+
11,self_attn.k_proj,8.45725,0.01000,0.838
|
| 80 |
+
11,self_attn.v_proj,6.02392,0.01000,0.771
|
| 81 |
+
11,self_attn.q_proj,40.64444,0.01000,1.032
|
| 82 |
+
11,self_attn.o_proj,26.50191,0.01000,0.787
|
| 83 |
+
11,mlp.up_proj,199.81430,0.01000,0.877
|
| 84 |
+
11,mlp.gate_proj,224.07779,0.01000,0.909
|
| 85 |
+
11,mlp.down_proj,38.30075,0.01000,4.759
|
| 86 |
+
12,self_attn.k_proj,11.49251,0.01000,0.765
|
| 87 |
+
12,self_attn.v_proj,7.52434,0.01000,0.753
|
| 88 |
+
12,self_attn.q_proj,52.59334,0.01000,0.892
|
| 89 |
+
12,self_attn.o_proj,27.97810,0.01000,0.762
|
| 90 |
+
12,mlp.up_proj,210.21582,0.01000,0.873
|
| 91 |
+
12,mlp.gate_proj,221.40839,0.01000,1.325
|
| 92 |
+
12,mlp.down_proj,43.06434,0.01000,4.997
|
| 93 |
+
13,self_attn.k_proj,6.90525,0.01000,0.824
|
| 94 |
+
13,self_attn.v_proj,4.90251,0.01000,0.805
|
| 95 |
+
13,self_attn.q_proj,32.36589,0.01000,0.920
|
| 96 |
+
13,self_attn.o_proj,29.61114,0.01000,0.803
|
| 97 |
+
13,mlp.up_proj,203.14102,0.01000,0.873
|
| 98 |
+
13,mlp.gate_proj,204.16193,0.01000,0.922
|
| 99 |
+
13,mlp.down_proj,45.87091,0.01000,5.545
|
| 100 |
+
14,self_attn.k_proj,14.47985,0.01000,0.804
|
| 101 |
+
14,self_attn.v_proj,11.73034,0.01000,0.797
|
| 102 |
+
14,self_attn.q_proj,82.33146,0.01000,1.285
|
| 103 |
+
14,self_attn.o_proj,38.59476,0.01000,0.881
|
| 104 |
+
14,mlp.up_proj,247.11208,0.01000,0.888
|
| 105 |
+
14,mlp.gate_proj,239.02837,0.01000,0.926
|
| 106 |
+
14,mlp.down_proj,57.56989,0.01000,4.754
|
| 107 |
+
15,self_attn.k_proj,9.06570,0.01000,0.774
|
| 108 |
+
15,self_attn.v_proj,10.10736,0.01000,0.816
|
| 109 |
+
15,self_attn.q_proj,46.24096,0.01000,0.777
|
| 110 |
+
15,self_attn.o_proj,51.95690,0.01000,0.773
|
| 111 |
+
15,mlp.up_proj,219.63980,0.01000,0.853
|
| 112 |
+
15,mlp.gate_proj,222.62167,0.01000,1.106
|
| 113 |
+
15,mlp.down_proj,50.96349,0.01000,4.934
|
| 114 |
+
16,self_attn.k_proj,11.42252,0.01000,0.765
|
| 115 |
+
16,self_attn.v_proj,12.53406,0.01000,0.753
|
| 116 |
+
16,self_attn.q_proj,62.26286,0.01000,0.790
|
| 117 |
+
16,self_attn.o_proj,43.35579,0.01000,0.865
|
| 118 |
+
16,mlp.up_proj,262.81763,0.01000,0.894
|
| 119 |
+
16,mlp.gate_proj,265.67303,0.01000,0.964
|
| 120 |
+
16,mlp.down_proj,64.78954,0.01000,5.125
|
| 121 |
+
17,self_attn.k_proj,10.09072,0.01000,0.794
|
| 122 |
+
17,self_attn.v_proj,13.81983,0.01000,0.766
|
| 123 |
+
17,self_attn.q_proj,61.49398,0.01000,0.770
|
| 124 |
+
17,self_attn.o_proj,44.81610,0.01000,0.920
|
| 125 |
+
17,mlp.up_proj,284.46274,0.01000,0.875
|
| 126 |
+
17,mlp.gate_proj,284.11169,0.01000,1.002
|
| 127 |
+
17,mlp.down_proj,87.89337,0.01000,4.614
|
| 128 |
+
18,self_attn.k_proj,9.79322,0.01000,0.760
|
| 129 |
+
18,self_attn.v_proj,10.86682,0.01000,0.799
|
| 130 |
+
18,self_attn.q_proj,52.46346,0.01000,0.848
|
| 131 |
+
18,self_attn.o_proj,68.46169,0.01000,0.752
|
| 132 |
+
18,mlp.up_proj,305.25970,0.01000,0.859
|
| 133 |
+
18,mlp.gate_proj,305.96844,0.01000,0.919
|
| 134 |
+
18,mlp.down_proj,119.15056,0.01000,4.879
|
| 135 |
+
19,self_attn.k_proj,9.69815,0.01000,0.783
|
| 136 |
+
19,self_attn.v_proj,21.15154,0.01000,0.804
|
| 137 |
+
19,self_attn.q_proj,62.57669,0.01000,0.821
|
| 138 |
+
19,self_attn.o_proj,86.32372,0.01000,0.791
|
| 139 |
+
19,mlp.up_proj,404.95178,0.01000,0.870
|
| 140 |
+
19,mlp.gate_proj,377.98557,0.01000,0.851
|
| 141 |
+
19,mlp.down_proj,205.39980,0.01000,4.900
|
| 142 |
+
20,self_attn.k_proj,12.49226,0.01000,0.794
|
| 143 |
+
20,self_attn.v_proj,34.53724,0.01000,0.774
|
| 144 |
+
20,self_attn.q_proj,91.20848,0.01000,0.821
|
| 145 |
+
20,self_attn.o_proj,131.75328,0.01000,0.766
|
| 146 |
+
20,mlp.up_proj,448.83029,0.01000,0.883
|
| 147 |
+
20,mlp.gate_proj,438.14526,0.01000,0.969
|
| 148 |
+
20,mlp.down_proj,220.01596,0.01000,4.792
|
| 149 |
+
21,self_attn.k_proj,11.06214,0.01000,0.749
|
| 150 |
+
21,self_attn.v_proj,25.78180,0.01000,0.742
|
| 151 |
+
21,self_attn.q_proj,81.67937,0.01000,0.790
|
| 152 |
+
21,self_attn.o_proj,71.25956,0.01000,0.863
|
| 153 |
+
21,mlp.up_proj,614.54694,0.01000,0.870
|
| 154 |
+
21,mlp.gate_proj,612.60046,0.01000,0.887
|
| 155 |
+
21,mlp.down_proj,327.72821,0.01000,4.504
|
| 156 |
+
22,self_attn.k_proj,13.41208,0.01000,0.773
|
| 157 |
+
22,self_attn.v_proj,31.07106,0.01000,0.931
|
| 158 |
+
22,self_attn.q_proj,77.69290,0.01000,0.783
|
| 159 |
+
22,self_attn.o_proj,132.03172,0.01000,0.760
|
| 160 |
+
22,mlp.up_proj,690.63879,0.01000,0.883
|
| 161 |
+
22,mlp.gate_proj,700.29004,0.01000,0.900
|
| 162 |
+
22,mlp.down_proj,378.98236,0.01000,4.869
|
| 163 |
+
23,self_attn.k_proj,12.78569,0.01000,0.749
|
| 164 |
+
23,self_attn.v_proj,43.66894,0.01000,0.794
|
| 165 |
+
23,self_attn.q_proj,89.66914,0.01000,0.763
|
| 166 |
+
23,self_attn.o_proj,170.13953,0.01000,0.764
|
| 167 |
+
23,mlp.up_proj,816.83069,0.01000,0.887
|
| 168 |
+
23,mlp.gate_proj,809.42603,0.01000,0.899
|
| 169 |
+
23,mlp.down_proj,437.69730,0.01000,5.426
|
| 170 |
+
24,self_attn.k_proj,13.16276,0.01000,0.800
|
| 171 |
+
24,self_attn.v_proj,57.13885,0.01000,0.842
|
| 172 |
+
24,self_attn.q_proj,88.28597,0.01000,0.804
|
| 173 |
+
24,self_attn.o_proj,187.65466,0.01000,0.874
|
| 174 |
+
24,mlp.up_proj,840.97058,0.01000,0.859
|
| 175 |
+
24,mlp.gate_proj,799.67664,0.01000,0.982
|
| 176 |
+
24,mlp.down_proj,538.40942,0.01000,4.866
|
| 177 |
+
25,self_attn.k_proj,10.99807,0.01000,0.763
|
| 178 |
+
25,self_attn.v_proj,55.68272,0.01000,0.749
|
| 179 |
+
25,self_attn.q_proj,96.86578,0.01000,0.809
|
| 180 |
+
25,self_attn.o_proj,160.76529,0.01000,0.769
|
| 181 |
+
25,mlp.up_proj,908.64429,0.01000,0.877
|
| 182 |
+
25,mlp.gate_proj,822.07965,0.01000,1.087
|
| 183 |
+
25,mlp.down_proj,694.99799,0.01000,4.828
|
| 184 |
+
26,self_attn.k_proj,15.25856,0.01000,0.803
|
| 185 |
+
26,self_attn.v_proj,80.93269,0.01000,0.781
|
| 186 |
+
26,self_attn.q_proj,98.17717,0.01000,0.775
|
| 187 |
+
26,self_attn.o_proj,167.09735,0.01000,0.808
|
| 188 |
+
26,mlp.up_proj,916.04517,0.01000,0.889
|
| 189 |
+
26,mlp.gate_proj,813.28882,0.01000,0.941
|
| 190 |
+
26,mlp.down_proj,890.39935,0.01000,4.783
|
| 191 |
+
27,self_attn.k_proj,14.69835,0.01000,0.774
|
| 192 |
+
27,self_attn.v_proj,86.89336,0.01000,0.754
|
| 193 |
+
27,self_attn.q_proj,118.33353,0.01000,0.796
|
| 194 |
+
27,self_attn.o_proj,461.98041,0.01000,0.807
|
| 195 |
+
27,mlp.up_proj,952.01959,0.01000,0.897
|
| 196 |
+
27,mlp.gate_proj,915.62085,0.01000,0.950
|
| 197 |
+
27,mlp.down_proj,1378.75830,0.01000,4.682
|
quantize_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"dynamic": null,
|
| 4 |
+
"group_size": 128,
|
| 5 |
+
"desc_act": true,
|
| 6 |
+
"sym": false,
|
| 7 |
+
"lm_head": false,
|
| 8 |
+
"quant_method": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"meta": {
|
| 11 |
+
"quantizer": [
|
| 12 |
+
"gptqmodel:1.7.4"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.01,
|
| 16 |
+
"damp_auto_increment": 0.0025,
|
| 17 |
+
"static_groups": true,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 2.4
|
| 20 |
+
}
|
| 21 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|end▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|User|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|Assistant|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|begin▁of▁sentence|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin��>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|