Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- Models/25/chat_template.jinja +1 -0
- Models/25/config.json +193 -0
- Models/25/generation_config.json +11 -0
- Models/25/model.safetensors +3 -0
- Models/25/quant_log.csv +161 -0
- Models/25/quantize_config.json +47 -0
- Models/25/tokenizer.json +3 -0
- Models/25/tokenizer_config.json +13 -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 |
+
Models/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Models/25/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
Models/25/config.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Phi3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 10 |
+
"AutoTokenizer": "Xenova/gpt-4o"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 199999,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"embd_pdrop": 0.0,
|
| 15 |
+
"eos_token_id": 199999,
|
| 16 |
+
"full_attn_mod": 1,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 3072,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 8192,
|
| 21 |
+
"interpolate_factor": 1,
|
| 22 |
+
"lm_head_bias": false,
|
| 23 |
+
"max_position_embeddings": 131072,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"model_type": "phi3",
|
| 26 |
+
"num_attention_heads": 24,
|
| 27 |
+
"num_hidden_layers": 32,
|
| 28 |
+
"num_key_value_heads": 8,
|
| 29 |
+
"original_max_position_embeddings": 4096,
|
| 30 |
+
"pad_token_id": 199999,
|
| 31 |
+
"partial_rotary_factor": 0.75,
|
| 32 |
+
"quantization_config": {
|
| 33 |
+
"bits": 4,
|
| 34 |
+
"checkpoint_format": "gptq",
|
| 35 |
+
"desc_act": false,
|
| 36 |
+
"format": "gptq",
|
| 37 |
+
"group_size": 128,
|
| 38 |
+
"lm_head": false,
|
| 39 |
+
"meta": {
|
| 40 |
+
"act_group_aware": true,
|
| 41 |
+
"auto_forward_data_parallel": true,
|
| 42 |
+
"damp_auto_increment": 0.01,
|
| 43 |
+
"damp_percent": 0.05,
|
| 44 |
+
"dense_vram_strategy": "exclusive",
|
| 45 |
+
"dense_vram_strategy_devices": null,
|
| 46 |
+
"fallback": {
|
| 47 |
+
"smooth": null,
|
| 48 |
+
"strategy": "rtn",
|
| 49 |
+
"threshold": "0.5%"
|
| 50 |
+
},
|
| 51 |
+
"foem": null,
|
| 52 |
+
"gc_mode": "interval",
|
| 53 |
+
"gptaq": null,
|
| 54 |
+
"hessian": {
|
| 55 |
+
"chunk_bytes": null,
|
| 56 |
+
"chunk_size": null,
|
| 57 |
+
"staging_dtype": "float32"
|
| 58 |
+
},
|
| 59 |
+
"mock_quantization": false,
|
| 60 |
+
"moe_vram_strategy": "exclusive",
|
| 61 |
+
"moe_vram_strategy_devices": null,
|
| 62 |
+
"mse": 0.0,
|
| 63 |
+
"offload_to_disk": true,
|
| 64 |
+
"offload_to_disk_path": "/tmp/gptqmodel_8flwr4py",
|
| 65 |
+
"pack_impl": "cpu",
|
| 66 |
+
"quantizer": [
|
| 67 |
+
"gptqmodel:7.0.0"
|
| 68 |
+
],
|
| 69 |
+
"static_groups": false,
|
| 70 |
+
"true_sequential": true,
|
| 71 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 72 |
+
"wait_for_submodule_finalizers": false
|
| 73 |
+
},
|
| 74 |
+
"method": "gptq",
|
| 75 |
+
"pack_dtype": "int32",
|
| 76 |
+
"quant_method": "gptq",
|
| 77 |
+
"sym": true
|
| 78 |
+
},
|
| 79 |
+
"resid_pdrop": 0.0,
|
| 80 |
+
"rms_norm_eps": 1e-05,
|
| 81 |
+
"rope_parameters": {
|
| 82 |
+
"long_factor": [
|
| 83 |
+
1,
|
| 84 |
+
1.118320672,
|
| 85 |
+
1.250641126,
|
| 86 |
+
1.398617824,
|
| 87 |
+
1.564103225,
|
| 88 |
+
1.74916897,
|
| 89 |
+
1.956131817,
|
| 90 |
+
2.187582649,
|
| 91 |
+
2.446418898,
|
| 92 |
+
2.735880826,
|
| 93 |
+
3.059592084,
|
| 94 |
+
3.421605075,
|
| 95 |
+
3.826451687,
|
| 96 |
+
4.279200023,
|
| 97 |
+
4.785517845,
|
| 98 |
+
5.351743533,
|
| 99 |
+
5.984965424,
|
| 100 |
+
6.693110555,
|
| 101 |
+
7.485043894,
|
| 102 |
+
8.370679318,
|
| 103 |
+
9.36110372,
|
| 104 |
+
10.4687158,
|
| 105 |
+
11.70738129,
|
| 106 |
+
13.09260651,
|
| 107 |
+
14.64173252,
|
| 108 |
+
16.37415215,
|
| 109 |
+
18.31155283,
|
| 110 |
+
20.47818807,
|
| 111 |
+
22.90118105,
|
| 112 |
+
25.61086418,
|
| 113 |
+
28.64115884,
|
| 114 |
+
32.03,
|
| 115 |
+
32.1,
|
| 116 |
+
32.13,
|
| 117 |
+
32.23,
|
| 118 |
+
32.6,
|
| 119 |
+
32.61,
|
| 120 |
+
32.64,
|
| 121 |
+
32.66,
|
| 122 |
+
32.7,
|
| 123 |
+
32.71,
|
| 124 |
+
32.93,
|
| 125 |
+
32.97,
|
| 126 |
+
33.28,
|
| 127 |
+
33.49,
|
| 128 |
+
33.5,
|
| 129 |
+
44.16,
|
| 130 |
+
47.77
|
| 131 |
+
],
|
| 132 |
+
"original_max_position_embeddings": 4096,
|
| 133 |
+
"partial_rotary_factor": 0.75,
|
| 134 |
+
"rope_theta": 10000.0,
|
| 135 |
+
"rope_type": "longrope",
|
| 136 |
+
"short_factor": [
|
| 137 |
+
1.0,
|
| 138 |
+
1.0,
|
| 139 |
+
1.0,
|
| 140 |
+
1.0,
|
| 141 |
+
1.0,
|
| 142 |
+
1.0,
|
| 143 |
+
1.0,
|
| 144 |
+
1.0,
|
| 145 |
+
1.0,
|
| 146 |
+
1.0,
|
| 147 |
+
1.0,
|
| 148 |
+
1.0,
|
| 149 |
+
1.0,
|
| 150 |
+
1.0,
|
| 151 |
+
1.0,
|
| 152 |
+
1.0,
|
| 153 |
+
1.0,
|
| 154 |
+
1.0,
|
| 155 |
+
1.0,
|
| 156 |
+
1.0,
|
| 157 |
+
1.0,
|
| 158 |
+
1.0,
|
| 159 |
+
1.0,
|
| 160 |
+
1.0,
|
| 161 |
+
1.0,
|
| 162 |
+
1.0,
|
| 163 |
+
1.0,
|
| 164 |
+
1.0,
|
| 165 |
+
1.0,
|
| 166 |
+
1.0,
|
| 167 |
+
1.0,
|
| 168 |
+
1.0,
|
| 169 |
+
1.0,
|
| 170 |
+
1.0,
|
| 171 |
+
1.0,
|
| 172 |
+
1.0,
|
| 173 |
+
1.0,
|
| 174 |
+
1.0,
|
| 175 |
+
1.0,
|
| 176 |
+
1.0,
|
| 177 |
+
1.0,
|
| 178 |
+
1.0,
|
| 179 |
+
1.0,
|
| 180 |
+
1.0,
|
| 181 |
+
1.0,
|
| 182 |
+
1.0,
|
| 183 |
+
1.0,
|
| 184 |
+
1.0
|
| 185 |
+
],
|
| 186 |
+
"type": "longrope"
|
| 187 |
+
},
|
| 188 |
+
"sliding_window": 262144,
|
| 189 |
+
"tie_word_embeddings": true,
|
| 190 |
+
"transformers_version": "5.8.0",
|
| 191 |
+
"use_cache": true,
|
| 192 |
+
"vocab_size": 200064
|
| 193 |
+
}
|
Models/25/generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 199999,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
200020,
|
| 7 |
+
199999
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "5.8.0"
|
| 11 |
+
}
|
Models/25/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1022e3696108a483894e85e8289d66d373c199e57f1f32e30980be0eaef8402
|
| 3 |
+
size 2905820840
|
Models/25/quant_log.csv
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.qkv_proj,0.0000037035,0.05000,1.695
|
| 3 |
+
0,self_attn.o_proj,0.0000001912,0.05000,0.993
|
| 4 |
+
0,mlp.up_proj,0.0000102369,0.05000,2.424
|
| 5 |
+
0,mlp.gate_proj,0.0000107023,0.05000,2.453
|
| 6 |
+
0,mlp.down_proj,0.0000007776,0.05000,2.854
|
| 7 |
+
1,self_attn.qkv_proj,0.0000286602,0.05000,1.281
|
| 8 |
+
1,self_attn.o_proj,0.0000004302,0.05000,1.073
|
| 9 |
+
1,mlp.gate_proj,0.0000156239,0.05000,2.984
|
| 10 |
+
1,mlp.up_proj,0.0000145528,0.05000,3.031
|
| 11 |
+
1,mlp.down_proj,0.0000015817,0.05000,3.079
|
| 12 |
+
2,self_attn.qkv_proj,0.0000670091,0.05000,1.059
|
| 13 |
+
2,self_attn.o_proj,0.0000003938,0.05000,1.070
|
| 14 |
+
2,mlp.up_proj,0.0000224096,0.05000,2.395
|
| 15 |
+
2,mlp.gate_proj,0.0000242441,0.05000,2.416
|
| 16 |
+
2,mlp.down_proj,0.0000015780,0.05000,2.917
|
| 17 |
+
3,self_attn.qkv_proj,0.0000974988,0.05000,1.073
|
| 18 |
+
3,self_attn.o_proj,0.0000007507,0.05000,1.034
|
| 19 |
+
3,mlp.up_proj,0.0000273527,0.05000,2.420
|
| 20 |
+
3,mlp.gate_proj,0.0000303579,0.05000,2.439
|
| 21 |
+
3,mlp.down_proj,0.0002998998,0.05000,2.971
|
| 22 |
+
4,self_attn.qkv_proj,0.0000910987,0.05000,1.059
|
| 23 |
+
4,self_attn.o_proj,0.0000010523,0.05000,1.028
|
| 24 |
+
4,mlp.up_proj,0.0000352418,0.05000,2.337
|
| 25 |
+
4,mlp.gate_proj,0.0000410384,0.05000,2.362
|
| 26 |
+
4,mlp.down_proj,0.0000039988,0.05000,2.978
|
| 27 |
+
5,self_attn.qkv_proj,0.0001155192,0.05000,1.047
|
| 28 |
+
5,self_attn.o_proj,0.0000016719,0.05000,1.026
|
| 29 |
+
5,mlp.gate_proj,0.0000496211,0.05000,2.362
|
| 30 |
+
5,mlp.up_proj,0.0000416632,0.05000,2.390
|
| 31 |
+
5,mlp.down_proj,0.0000057624,0.05000,3.039
|
| 32 |
+
6,self_attn.qkv_proj,0.0000936164,0.05000,1.020
|
| 33 |
+
6,self_attn.o_proj,0.0000023169,0.05000,1.018
|
| 34 |
+
6,mlp.gate_proj,0.0000478458,0.05000,2.404
|
| 35 |
+
6,mlp.up_proj,0.0000420634,0.05000,2.419
|
| 36 |
+
6,mlp.down_proj,0.0000064274,0.05000,3.008
|
| 37 |
+
7,self_attn.qkv_proj,0.0001384777,0.05000,1.049
|
| 38 |
+
7,self_attn.o_proj,0.0000026701,0.05000,1.038
|
| 39 |
+
7,mlp.gate_proj,0.0000488039,0.05000,2.357
|
| 40 |
+
7,mlp.up_proj,0.0000447177,0.05000,2.384
|
| 41 |
+
7,mlp.down_proj,0.0000080068,0.05000,2.957
|
| 42 |
+
8,self_attn.qkv_proj,0.0001268911,0.05000,1.066
|
| 43 |
+
8,self_attn.o_proj,0.0000035567,0.05000,1.000
|
| 44 |
+
8,mlp.gate_proj,0.0000463068,0.05000,2.386
|
| 45 |
+
8,mlp.up_proj,0.0000451744,0.05000,2.408
|
| 46 |
+
8,mlp.down_proj,0.0000082719,0.05000,2.994
|
| 47 |
+
9,self_attn.qkv_proj,0.0001118555,0.05000,1.019
|
| 48 |
+
9,self_attn.o_proj,0.0000036070,0.05000,1.045
|
| 49 |
+
9,mlp.up_proj,0.0000490196,0.05000,2.307
|
| 50 |
+
9,mlp.gate_proj,0.0000489556,0.05000,2.306
|
| 51 |
+
9,mlp.down_proj,0.0000078682,0.05000,2.932
|
| 52 |
+
10,self_attn.qkv_proj,0.0001195859,0.05000,1.039
|
| 53 |
+
10,self_attn.o_proj,0.0000053637,0.05000,1.004
|
| 54 |
+
10,mlp.gate_proj,0.0000508104,0.05000,2.384
|
| 55 |
+
10,mlp.up_proj,0.0000506414,0.05000,2.403
|
| 56 |
+
10,mlp.down_proj,0.0000088444,0.05000,2.987
|
| 57 |
+
11,self_attn.qkv_proj,0.0001189149,0.05000,1.026
|
| 58 |
+
11,self_attn.o_proj,0.0000047267,0.05000,1.049
|
| 59 |
+
11,mlp.up_proj,0.0000525891,0.05000,2.311
|
| 60 |
+
11,mlp.gate_proj,0.0000505481,0.05000,2.330
|
| 61 |
+
11,mlp.down_proj,0.0000090989,0.05000,3.007
|
| 62 |
+
12,self_attn.qkv_proj,0.0001222839,0.05000,1.036
|
| 63 |
+
12,self_attn.o_proj,0.0000046178,0.05000,1.048
|
| 64 |
+
12,mlp.up_proj,0.0000535870,0.05000,2.276
|
| 65 |
+
12,mlp.gate_proj,0.0000492890,0.05000,2.301
|
| 66 |
+
12,mlp.down_proj,0.0000108105,0.05000,2.947
|
| 67 |
+
13,self_attn.qkv_proj,0.0001456172,0.05000,1.026
|
| 68 |
+
13,self_attn.o_proj,0.0000059778,0.05000,1.031
|
| 69 |
+
13,mlp.gate_proj,0.0000507735,0.05000,2.282
|
| 70 |
+
13,mlp.up_proj,0.0000571203,0.05000,2.302
|
| 71 |
+
13,mlp.down_proj,0.0000114501,0.05000,2.939
|
| 72 |
+
14,self_attn.qkv_proj,0.0001290736,0.05000,1.052
|
| 73 |
+
14,self_attn.o_proj,0.0000053882,0.05000,1.012
|
| 74 |
+
14,mlp.gate_proj,0.0000560465,0.05000,2.260
|
| 75 |
+
14,mlp.up_proj,0.0000626098,0.05000,2.263
|
| 76 |
+
14,mlp.down_proj,0.0000130744,0.05000,2.974
|
| 77 |
+
15,self_attn.qkv_proj,0.0001434816,0.05000,1.038
|
| 78 |
+
15,self_attn.o_proj,0.0000051712,0.05000,1.004
|
| 79 |
+
15,mlp.up_proj,0.0000692544,0.05000,2.446
|
| 80 |
+
15,mlp.gate_proj,0.0000621178,0.05000,2.473
|
| 81 |
+
15,mlp.down_proj,0.0000150576,0.05000,2.920
|
| 82 |
+
16,self_attn.qkv_proj,0.0001369979,0.05000,1.019
|
| 83 |
+
16,self_attn.o_proj,0.0000090328,0.05000,1.007
|
| 84 |
+
16,mlp.gate_proj,0.0000653503,0.05000,2.323
|
| 85 |
+
16,mlp.up_proj,0.0000734144,0.05000,2.352
|
| 86 |
+
16,mlp.down_proj,0.0000200746,0.05000,2.964
|
| 87 |
+
17,self_attn.qkv_proj,0.0001395030,0.05000,1.015
|
| 88 |
+
17,self_attn.o_proj,0.0000068804,0.05000,1.013
|
| 89 |
+
17,mlp.gate_proj,0.0000694652,0.05000,2.324
|
| 90 |
+
17,mlp.up_proj,0.0000789464,0.05000,2.343
|
| 91 |
+
17,mlp.down_proj,0.0000242481,0.05000,2.968
|
| 92 |
+
18,self_attn.qkv_proj,0.0001378879,0.05000,1.040
|
| 93 |
+
18,self_attn.o_proj,0.0000118515,0.05000,1.062
|
| 94 |
+
18,mlp.up_proj,0.0000885018,0.05000,2.303
|
| 95 |
+
18,mlp.gate_proj,0.0000787926,0.05000,2.330
|
| 96 |
+
18,mlp.down_proj,0.0000361241,0.05000,2.967
|
| 97 |
+
19,self_attn.qkv_proj,0.0001587094,0.05000,1.029
|
| 98 |
+
19,self_attn.o_proj,0.0000144369,0.05000,1.015
|
| 99 |
+
19,mlp.gate_proj,0.0000868370,0.05000,2.312
|
| 100 |
+
19,mlp.up_proj,0.0000961948,0.05000,2.332
|
| 101 |
+
19,mlp.down_proj,0.0000418560,0.05000,2.953
|
| 102 |
+
20,self_attn.qkv_proj,0.0001532980,0.05000,1.032
|
| 103 |
+
20,self_attn.o_proj,0.0000176382,0.05000,1.009
|
| 104 |
+
20,mlp.gate_proj,0.0001063069,0.05000,2.306
|
| 105 |
+
20,mlp.up_proj,0.0001176227,0.05000,2.338
|
| 106 |
+
20,mlp.down_proj,0.0000541321,0.05000,2.950
|
| 107 |
+
21,self_attn.qkv_proj,0.0001821614,0.05000,1.026
|
| 108 |
+
21,self_attn.o_proj,0.0000128516,0.05000,1.015
|
| 109 |
+
21,mlp.up_proj,0.0001266831,0.05000,2.502
|
| 110 |
+
21,mlp.gate_proj,0.0001130891,0.05000,2.516
|
| 111 |
+
21,mlp.down_proj,0.0000670870,0.05000,3.011
|
| 112 |
+
22,self_attn.qkv_proj,0.0001746809,0.05000,1.028
|
| 113 |
+
22,self_attn.o_proj,0.0000238040,0.05000,1.043
|
| 114 |
+
22,mlp.up_proj,0.0001363046,0.05000,2.250
|
| 115 |
+
22,mlp.gate_proj,0.0001202949,0.05000,2.275
|
| 116 |
+
22,mlp.down_proj,0.0000788939,0.05000,2.992
|
| 117 |
+
23,self_attn.qkv_proj,0.0001925415,0.05000,1.013
|
| 118 |
+
23,self_attn.o_proj,0.0000102084,0.05000,1.015
|
| 119 |
+
23,mlp.gate_proj,0.0001299220,0.05000,2.277
|
| 120 |
+
23,mlp.up_proj,0.0001462273,0.05000,2.299
|
| 121 |
+
23,mlp.down_proj,0.0000795165,0.05000,2.962
|
| 122 |
+
24,self_attn.qkv_proj,0.0002069782,0.05000,1.031
|
| 123 |
+
24,self_attn.o_proj,0.0000115072,0.05000,1.051
|
| 124 |
+
24,mlp.gate_proj,0.0001396862,0.05000,2.344
|
| 125 |
+
24,mlp.up_proj,0.0001586309,0.05000,2.348
|
| 126 |
+
24,mlp.down_proj,0.0000930914,0.05000,2.952
|
| 127 |
+
25,self_attn.qkv_proj,0.0002230113,0.05000,1.052
|
| 128 |
+
25,self_attn.o_proj,0.0000204678,0.05000,0.996
|
| 129 |
+
25,mlp.gate_proj,0.0001546881,0.05000,2.336
|
| 130 |
+
25,mlp.up_proj,0.0001761131,0.05000,2.359
|
| 131 |
+
25,mlp.down_proj,0.0001077607,0.05000,2.968
|
| 132 |
+
26,self_attn.qkv_proj,0.0001977103,0.05000,1.014
|
| 133 |
+
26,self_attn.o_proj,0.0000338197,0.05000,1.015
|
| 134 |
+
26,mlp.up_proj,0.0001833882,0.05000,2.316
|
| 135 |
+
26,mlp.gate_proj,0.0001614466,0.05000,2.336
|
| 136 |
+
26,mlp.down_proj,0.0001312572,0.05000,2.941
|
| 137 |
+
27,self_attn.qkv_proj,0.0001965278,0.05000,1.011
|
| 138 |
+
27,self_attn.o_proj,0.0000231340,0.05000,1.005
|
| 139 |
+
27,mlp.gate_proj,0.0001804944,0.05000,2.462
|
| 140 |
+
27,mlp.up_proj,0.0002018597,0.05000,2.477
|
| 141 |
+
27,mlp.down_proj,0.0001707861,0.05000,2.984
|
| 142 |
+
28,self_attn.qkv_proj,0.0002510537,0.05000,1.017
|
| 143 |
+
28,self_attn.o_proj,0.0000287529,0.05000,1.024
|
| 144 |
+
28,mlp.up_proj,0.0002194517,0.05000,2.276
|
| 145 |
+
28,mlp.gate_proj,0.0002030963,0.05000,2.300
|
| 146 |
+
28,mlp.down_proj,0.0002290906,0.05000,2.962
|
| 147 |
+
29,self_attn.qkv_proj,0.0002273341,0.05000,1.045
|
| 148 |
+
29,self_attn.o_proj,0.0000351872,0.05000,1.027
|
| 149 |
+
29,mlp.gate_proj,0.0002264227,0.05000,2.352
|
| 150 |
+
29,mlp.up_proj,0.0002236534,0.05000,2.373
|
| 151 |
+
29,mlp.down_proj,0.0003785557,0.05000,2.977
|
| 152 |
+
30,self_attn.qkv_proj,0.0001608474,0.05000,1.024
|
| 153 |
+
30,self_attn.o_proj,0.0000363605,0.05000,1.023
|
| 154 |
+
30,mlp.gate_proj,0.0002430771,0.05000,2.505
|
| 155 |
+
30,mlp.up_proj,0.0002131529,0.05000,2.513
|
| 156 |
+
30,mlp.down_proj,0.0014835209,0.05000,2.926
|
| 157 |
+
31,self_attn.qkv_proj,0.0000034551,0.05000,1.074
|
| 158 |
+
31,self_attn.o_proj,0.0000042867,0.05000,1.011
|
| 159 |
+
31,mlp.gate_proj,0.0001017404,0.05000,2.333
|
| 160 |
+
31,mlp.up_proj,0.0000593105,0.05000,2.351
|
| 161 |
+
31,mlp.down_proj,0.0004770287,0.05000,2.931
|
Models/25/quantize_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": false,
|
| 5 |
+
"lm_head": false,
|
| 6 |
+
"method": "gptq",
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"format": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"pack_dtype": "int32",
|
| 11 |
+
"meta": {
|
| 12 |
+
"quantizer": [
|
| 13 |
+
"gptqmodel:7.0.0"
|
| 14 |
+
],
|
| 15 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 16 |
+
"damp_percent": 0.05,
|
| 17 |
+
"damp_auto_increment": 0.01,
|
| 18 |
+
"static_groups": false,
|
| 19 |
+
"true_sequential": true,
|
| 20 |
+
"mse": 0.0,
|
| 21 |
+
"gptaq": null,
|
| 22 |
+
"foem": null,
|
| 23 |
+
"act_group_aware": true,
|
| 24 |
+
"fallback": {
|
| 25 |
+
"strategy": "rtn",
|
| 26 |
+
"threshold": "0.5%",
|
| 27 |
+
"smooth": null
|
| 28 |
+
},
|
| 29 |
+
"offload_to_disk": true,
|
| 30 |
+
"offload_to_disk_path": "/tmp/gptqmodel_8flwr4py",
|
| 31 |
+
"pack_impl": "cpu",
|
| 32 |
+
"gc_mode": "interval",
|
| 33 |
+
"wait_for_submodule_finalizers": false,
|
| 34 |
+
"auto_forward_data_parallel": true,
|
| 35 |
+
"dense_vram_strategy": "exclusive",
|
| 36 |
+
"dense_vram_strategy_devices": null,
|
| 37 |
+
"moe_vram_strategy": "exclusive",
|
| 38 |
+
"moe_vram_strategy_devices": null,
|
| 39 |
+
"mock_quantization": false,
|
| 40 |
+
"hessian": {
|
| 41 |
+
"chunk_size": null,
|
| 42 |
+
"chunk_bytes": null,
|
| 43 |
+
"staging_dtype": "float32"
|
| 44 |
+
}
|
| 45 |
+
},
|
| 46 |
+
"sym": true
|
| 47 |
+
}
|
Models/25/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37e9231f9dff6188c8297dc9cef50053d1267dce7835784fe92da4da5a9fcf4f
|
| 3 |
+
size 15524754
|
Models/25/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 131072,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"tokenizer_class": "TokenizersBackend",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|