Add files using upload-large-folder tool

config.json

@@ -0,0 +1,51 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 10240,
+  "hidden_size": 2560,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:2.2.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2560
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4cf734c3d0c3930c6983fe5d5ba128cbaa365aa50207c887b008fbdb66f950
+size 1580548656

quant_log.csv

@@ -0,0 +1,193 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.00394990,0.01000,2.077
+0,self_attn.v_proj,0.00102141,0.01000,1.203
+0,self_attn.q_proj,0.00392392,0.01000,1.159
+0,self_attn.out_proj,0.00003452,0.01000,1.160
+0,fc1,0.01215448,0.01000,1.218
+0,fc2,0.00012052,0.01000,5.100
+1,self_attn.k_proj,0.01467542,0.01000,1.203
+1,self_attn.v_proj,0.00038407,0.01000,1.189
+1,self_attn.q_proj,0.00410239,0.01000,1.197
+1,self_attn.out_proj,0.00000140,0.01000,1.198
+1,fc1,0.00917357,0.01000,1.225
+1,fc2,0.00009661,0.01000,5.052
+2,self_attn.k_proj,0.01598312,0.01000,1.182
+2,self_attn.v_proj,0.00050603,0.01000,1.175
+2,self_attn.q_proj,0.00603839,0.01000,1.187
+2,self_attn.out_proj,0.00000089,0.01000,1.180
+2,fc1,0.01015421,0.01000,1.217
+2,fc2,0.00008922,0.01000,5.029
+3,self_attn.k_proj,0.00669147,0.01000,1.183
+3,self_attn.v_proj,0.00061962,0.01000,1.194
+3,self_attn.q_proj,0.00420396,0.01000,1.198
+3,self_attn.out_proj,0.00000129,0.01000,1.197
+3,fc1,0.00989648,0.01000,1.234
+3,fc2,0.00008503,0.01000,5.125
+4,self_attn.k_proj,0.00954085,0.01000,1.195
+4,self_attn.v_proj,0.00085336,0.01000,1.204
+4,self_attn.q_proj,0.00553959,0.01000,1.213
+4,self_attn.out_proj,0.00000257,0.01000,1.190
+4,fc1,0.00941784,0.01000,1.221
+4,fc2,0.00009369,0.01000,5.107
+5,self_attn.k_proj,0.00864742,0.01000,1.199
+5,self_attn.v_proj,0.00100623,0.01000,1.207
+5,self_attn.q_proj,0.00588670,0.01000,1.202
+5,self_attn.out_proj,0.00000694,0.01000,1.215
+5,fc1,0.01044408,0.01000,1.223
+5,fc2,0.00009701,0.01000,5.078
+6,self_attn.k_proj,0.00639420,0.01000,1.211
+6,self_attn.v_proj,0.00123202,0.01000,1.195
+6,self_attn.q_proj,0.00649996,0.01000,1.227
+6,self_attn.out_proj,0.00000823,0.01000,1.200
+6,fc1,0.01182344,0.01000,1.225
+6,fc2,0.00010991,0.01000,5.068
+7,self_attn.k_proj,0.00690140,0.01000,1.206
+7,self_attn.v_proj,0.00144184,0.01000,1.200
+7,self_attn.q_proj,0.00772449,0.01000,1.188
+7,self_attn.out_proj,0.00001096,0.01000,1.193
+7,fc1,0.01315037,0.01000,1.222
+7,fc2,0.00011415,0.01000,5.176
+8,self_attn.k_proj,0.01227832,0.01000,1.198
+8,self_attn.v_proj,0.00185993,0.01000,1.209
+8,self_attn.q_proj,0.00888034,0.01000,1.240
+8,self_attn.out_proj,0.00002013,0.01000,1.185
+8,fc1,0.01511053,0.01000,1.225
+8,fc2,0.00013472,0.01000,5.054
+9,self_attn.k_proj,0.01038534,0.01000,1.200
+9,self_attn.v_proj,0.00222251,0.01000,1.213
+9,self_attn.q_proj,0.00935974,0.01000,1.205
+9,self_attn.out_proj,0.00002113,0.01000,1.199
+9,fc1,0.01749250,0.01000,1.217
+9,fc2,0.00016016,0.01000,5.113
+10,self_attn.k_proj,0.01146444,0.01000,1.200
+10,self_attn.v_proj,0.00256414,0.01000,1.189
+10,self_attn.q_proj,0.01083466,0.01000,1.207
+10,self_attn.out_proj,0.00003377,0.01000,1.187
+10,fc1,0.02200724,0.01000,1.246
+10,fc2,0.00023786,0.01000,5.080
+11,self_attn.k_proj,0.01244001,0.01000,1.199
+11,self_attn.v_proj,0.00304534,0.01000,1.229
+11,self_attn.q_proj,0.01194046,0.01000,1.203
+11,self_attn.out_proj,0.00003740,0.01000,1.182
+11,fc1,0.02627137,0.01000,1.219
+11,fc2,0.00024376,0.01000,5.084
+12,self_attn.k_proj,0.01390320,0.01000,1.195
+12,self_attn.v_proj,0.00363379,0.01000,1.192
+12,self_attn.q_proj,0.01290092,0.01000,1.201
+12,self_attn.out_proj,0.00004900,0.01000,1.181
+12,fc1,0.03056903,0.01000,1.218
+12,fc2,0.00030255,0.01000,5.100
+13,self_attn.k_proj,0.01644090,0.01000,1.204
+13,self_attn.v_proj,0.00411961,0.01000,1.190
+13,self_attn.q_proj,0.01511327,0.01000,1.203
+13,self_attn.out_proj,0.00009101,0.01000,1.200
+13,fc1,0.03606411,0.01000,1.212
+13,fc2,0.00038431,0.01000,5.066
+14,self_attn.k_proj,0.01776866,0.01000,1.207
+14,self_attn.v_proj,0.00495395,0.01000,1.211
+14,self_attn.q_proj,0.01613377,0.01000,1.210
+14,self_attn.out_proj,0.00009793,0.01000,1.188
+14,fc1,0.04128723,0.01000,1.205
+14,fc2,0.00050071,0.01000,5.064
+15,self_attn.k_proj,0.02192250,0.01000,1.196
+15,self_attn.v_proj,0.00563364,0.01000,1.204
+15,self_attn.q_proj,0.01936727,0.01000,1.242
+15,self_attn.out_proj,0.00018638,0.01000,1.184
+15,fc1,0.04553729,0.01000,1.217
+15,fc2,0.00064369,0.01000,5.201
+16,self_attn.k_proj,0.02319060,0.01000,1.194
+16,self_attn.v_proj,0.00663496,0.01000,1.188
+16,self_attn.q_proj,0.02020913,0.01000,1.201
+16,self_attn.out_proj,0.00021892,0.01000,1.233
+16,fc1,0.05039033,0.01000,1.239
+16,fc2,0.00109865,0.01000,5.104
+17,self_attn.k_proj,0.02345077,0.01000,1.192
+17,self_attn.v_proj,0.00807686,0.01000,1.190
+17,self_attn.q_proj,0.02011927,0.01000,1.200
+17,self_attn.out_proj,0.00025877,0.01000,1.199
+17,fc1,0.05574853,0.01000,1.232
+17,fc2,0.00141325,0.01000,5.056
+18,self_attn.k_proj,0.02450161,0.01000,1.201
+18,self_attn.v_proj,0.00966819,0.01000,1.188
+18,self_attn.q_proj,0.02183347,0.01000,1.193
+18,self_attn.out_proj,0.00027320,0.01000,1.202
+18,fc1,0.06218845,0.01000,1.222
+18,fc2,0.00187777,0.01000,5.135
+19,self_attn.k_proj,0.02378891,0.01000,1.200
+19,self_attn.v_proj,0.01167217,0.01000,1.199
+19,self_attn.q_proj,0.01957743,0.01000,1.225
+19,self_attn.out_proj,0.00038118,0.01000,1.218
+19,fc1,0.07038191,0.01000,1.241
+19,fc2,0.00238876,0.01000,5.082
+20,self_attn.k_proj,0.02468025,0.01000,1.197
+20,self_attn.v_proj,0.01396945,0.01000,1.191
+20,self_attn.q_proj,0.02122129,0.01000,1.197
+20,self_attn.out_proj,0.00036665,0.01000,1.191
+20,fc1,0.07806558,0.01000,1.215
+20,fc2,0.00294969,0.01000,5.041
+21,self_attn.k_proj,0.02351781,0.01000,1.208
+21,self_attn.v_proj,0.01587440,0.01000,1.186
+21,self_attn.q_proj,0.02154187,0.01000,1.197
+21,self_attn.out_proj,0.00039672,0.01000,1.187
+21,fc1,0.08287902,0.01000,1.235
+21,fc2,0.00356286,0.01000,5.060
+22,self_attn.k_proj,0.02510822,0.01000,1.204
+22,self_attn.v_proj,0.01696502,0.01000,1.221
+22,self_attn.q_proj,0.02051033,0.01000,1.224
+22,self_attn.out_proj,0.00058326,0.01000,1.174
+22,fc1,0.09057487,0.01000,1.234
+22,fc2,0.00434268,0.01000,5.093
+23,self_attn.k_proj,0.02305048,0.01000,1.205
+23,self_attn.v_proj,0.01852468,0.01000,1.179
+23,self_attn.q_proj,0.02109080,0.01000,1.227
+23,self_attn.out_proj,0.00045792,0.01000,1.214
+23,fc1,0.09620518,0.01000,1.216
+23,fc2,0.00486809,0.01000,5.072
+24,self_attn.k_proj,0.02279006,0.01000,1.187
+24,self_attn.v_proj,0.02133971,0.01000,1.194
+24,self_attn.q_proj,0.02080431,0.01000,1.192
+24,self_attn.out_proj,0.00079423,0.01000,1.199
+24,fc1,0.10291621,0.01000,1.218
+24,fc2,0.00596800,0.01000,5.054
+25,self_attn.k_proj,0.02235756,0.01000,1.220
+25,self_attn.v_proj,0.02586158,0.01000,1.202
+25,self_attn.q_proj,0.02162791,0.01000,1.198
+25,self_attn.out_proj,0.00092192,0.01000,1.191
+25,fc1,0.10848137,0.01000,1.224
+25,fc2,0.00664149,0.01000,5.109
+26,self_attn.k_proj,0.02296433,0.01000,1.195
+26,self_attn.v_proj,0.02654539,0.01000,1.187
+26,self_attn.q_proj,0.02132273,0.01000,1.203
+26,self_attn.out_proj,0.00105593,0.01000,1.192
+26,fc1,0.11584188,0.01000,1.205
+26,fc2,0.00829924,0.01000,5.138
+27,self_attn.k_proj,0.02253344,0.01000,1.211
+27,self_attn.v_proj,0.03002428,0.01000,1.236
+27,self_attn.q_proj,0.02269228,0.01000,1.201
+27,self_attn.out_proj,0.00074054,0.01000,1.208
+27,fc1,0.11827446,0.01000,1.216
+27,fc2,0.00945978,0.01000,5.088
+28,self_attn.k_proj,0.02344959,0.01000,1.201
+28,self_attn.v_proj,0.03120596,0.01000,1.199
+28,self_attn.q_proj,0.02303211,0.01000,1.202
+28,self_attn.out_proj,0.00140934,0.01000,1.246
+28,fc1,0.12195188,0.01000,1.220
+28,fc2,0.01116386,0.01000,5.036
+29,self_attn.k_proj,0.02414516,0.01000,1.184
+29,self_attn.v_proj,0.03367308,0.01000,1.196
+29,self_attn.q_proj,0.02733649,0.01000,1.210
+29,self_attn.out_proj,0.00086731,0.01000,1.195
+29,fc1,0.11979358,0.01000,1.209
+29,fc2,0.01215415,0.01000,5.011
+30,self_attn.k_proj,0.02487144,0.01000,1.172
+30,self_attn.v_proj,0.03512698,0.01000,1.186
+30,self_attn.q_proj,0.02941238,0.01000,1.186
+30,self_attn.out_proj,0.00075273,0.01000,1.231
+30,fc1,0.11724092,0.01000,1.202
+30,fc2,0.01190732,0.01000,5.066
+31,self_attn.k_proj,0.02410964,0.01000,1.177
+31,self_attn.v_proj,0.03215169,0.01000,1.197
+31,self_attn.q_proj,0.03200582,0.01000,1.194
+31,self_attn.out_proj,0.00138725,0.01000,1.186
+31,fc1,0.10804088,0.01000,1.251
+31,fc2,0.00846135,0.01000,5.037

quantize_config.json

@@ -0,0 +1,21 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": false,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:2.2.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.0025,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2TokenizerFast",
+  "unk_token": "</s>",
+  "_commit_hash": null
+}