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": 8192,
+  "hidden_size": 2048,
+  "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": 24,
+  "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": 2048
+}

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:fdf50790f50b393e413a8fe3b3270a47e8c3d5f253131bcf1d9087ac4b8deb16
+size 845033800

quant_log.csv

@@ -0,0 +1,145 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.00353451,0.01000,0.985
+0,self_attn.v_proj,0.00058977,0.01000,0.967
+0,self_attn.q_proj,0.00354618,0.01000,0.977
+0,self_attn.out_proj,0.00000845,0.01000,0.986
+0,fc1,0.00918082,0.01000,0.991
+0,fc2,0.00012097,0.01000,4.133
+1,self_attn.k_proj,0.00341375,0.01000,0.985
+1,self_attn.v_proj,0.00041851,0.01000,0.983
+1,self_attn.q_proj,0.00368894,0.01000,0.978
+1,self_attn.out_proj,0.00000219,0.01000,0.975
+1,fc1,0.01199323,0.01000,0.972
+1,fc2,0.00015632,0.01000,4.114
+2,self_attn.k_proj,0.00492218,0.01000,0.974
+2,self_attn.v_proj,0.00078813,0.01000,0.981
+2,self_attn.q_proj,0.00490565,0.01000,0.996
+2,self_attn.out_proj,0.00000534,0.01000,0.986
+2,fc1,0.01365813,0.01000,0.983
+2,fc2,0.00011579,0.01000,4.153
+3,self_attn.k_proj,0.00530104,0.01000,0.969
+3,self_attn.v_proj,0.00144508,0.01000,0.974
+3,self_attn.q_proj,0.00609475,0.01000,0.968
+3,self_attn.out_proj,0.00000768,0.01000,0.976
+3,fc1,0.01403668,0.01000,0.986
+3,fc2,0.00010727,0.01000,4.213
+4,self_attn.k_proj,0.00831477,0.01000,0.975
+4,self_attn.v_proj,0.00187180,0.01000,0.980
+4,self_attn.q_proj,0.00878986,0.01000,0.979
+4,self_attn.out_proj,0.00001110,0.01000,0.986
+4,fc1,0.01618612,0.01000,0.988
+4,fc2,0.00011802,0.01000,4.157
+5,self_attn.k_proj,0.01036577,0.01000,0.995
+5,self_attn.v_proj,0.00241232,0.01000,0.988
+5,self_attn.q_proj,0.01065748,0.01000,0.976
+5,self_attn.out_proj,0.00001253,0.01000,0.970
+5,fc1,0.01835590,0.01000,0.993
+5,fc2,0.00012848,0.01000,4.150
+6,self_attn.k_proj,0.01596541,0.01000,0.974
+6,self_attn.v_proj,0.00293466,0.01000,0.969
+6,self_attn.q_proj,0.01442928,0.01000,0.987
+6,self_attn.out_proj,0.00002641,0.01000,1.002
+6,fc1,0.02287802,0.01000,0.974
+6,fc2,0.00016784,0.01000,4.180
+7,self_attn.k_proj,0.01730689,0.01000,0.999
+7,self_attn.v_proj,0.00342599,0.01000,0.992
+7,self_attn.q_proj,0.01509144,0.01000,0.976
+7,self_attn.out_proj,0.00003264,0.01000,0.980
+7,fc1,0.02844299,0.01000,0.982
+7,fc2,0.00022774,0.01000,4.197
+8,self_attn.k_proj,0.01908275,0.01000,0.973
+8,self_attn.v_proj,0.00382682,0.01000,0.997
+8,self_attn.q_proj,0.01574800,0.01000,0.982
+8,self_attn.out_proj,0.00003932,0.01000,0.976
+8,fc1,0.03425221,0.01000,0.998
+8,fc2,0.00029699,0.01000,4.165
+9,self_attn.k_proj,0.02025209,0.01000,1.003
+9,self_attn.v_proj,0.00431333,0.01000,0.971
+9,self_attn.q_proj,0.01737337,0.01000,0.976
+9,self_attn.out_proj,0.00005814,0.01000,0.988
+9,fc1,0.03883628,0.01000,0.978
+9,fc2,0.00039988,0.01000,4.134
+10,self_attn.k_proj,0.02029791,0.01000,0.977
+10,self_attn.v_proj,0.00536017,0.01000,0.977
+10,self_attn.q_proj,0.01724341,0.01000,1.056
+10,self_attn.out_proj,0.00007856,0.01000,0.978
+10,fc1,0.04395340,0.01000,1.004
+10,fc2,0.00062550,0.01000,4.132
+11,self_attn.k_proj,0.02109379,0.01000,0.987
+11,self_attn.v_proj,0.00646726,0.01000,0.978
+11,self_attn.q_proj,0.01758398,0.01000,0.974
+11,self_attn.out_proj,0.00010376,0.01000,0.978
+11,fc1,0.04890034,0.01000,1.010
+11,fc2,0.00082190,0.01000,4.149
+12,self_attn.k_proj,0.02365618,0.01000,0.981
+12,self_attn.v_proj,0.00702407,0.01000,0.981
+12,self_attn.q_proj,0.01871167,0.01000,0.999
+12,self_attn.out_proj,0.00017479,0.01000,0.971
+12,fc1,0.05111321,0.01000,0.977
+12,fc2,0.00105926,0.01000,4.121
+13,self_attn.k_proj,0.02559538,0.01000,0.974
+13,self_attn.v_proj,0.00761801,0.01000,0.987
+13,self_attn.q_proj,0.01913078,0.01000,0.972
+13,self_attn.out_proj,0.00017100,0.01000,0.978
+13,fc1,0.05634150,0.01000,0.994
+13,fc2,0.00141263,0.01000,4.137
+14,self_attn.k_proj,0.02446801,0.01000,1.026
+14,self_attn.v_proj,0.00951312,0.01000,0.971
+14,self_attn.q_proj,0.01863108,0.01000,0.990
+14,self_attn.out_proj,0.00018884,0.01000,0.975
+14,fc1,0.06176755,0.01000,0.981
+14,fc2,0.00190128,0.01000,4.100
+15,self_attn.k_proj,0.02212356,0.01000,0.988
+15,self_attn.v_proj,0.01194986,0.01000,0.973
+15,self_attn.q_proj,0.01872810,0.01000,1.001
+15,self_attn.out_proj,0.00019521,0.01000,0.980
+15,fc1,0.06548359,0.01000,1.006
+15,fc2,0.00242290,0.01000,4.177
+16,self_attn.k_proj,0.02222240,0.01000,0.980
+16,self_attn.v_proj,0.01270989,0.01000,0.977
+16,self_attn.q_proj,0.01654256,0.01000,0.981
+16,self_attn.out_proj,0.00027436,0.01000,0.980
+16,fc1,0.07119486,0.01000,0.983
+16,fc2,0.00302200,0.01000,4.142
+17,self_attn.k_proj,0.02143056,0.01000,0.980
+17,self_attn.v_proj,0.01383860,0.01000,0.985
+17,self_attn.q_proj,0.01645198,0.01000,0.980
+17,self_attn.out_proj,0.00032416,0.01000,0.986
+17,fc1,0.07789719,0.01000,0.999
+17,fc2,0.00390024,0.01000,4.210
+18,self_attn.k_proj,0.01963866,0.01000,0.987
+18,self_attn.v_proj,0.01575041,0.01000,0.970
+18,self_attn.q_proj,0.01586412,0.01000,0.998
+18,self_attn.out_proj,0.00036916,0.01000,0.981
+18,fc1,0.08195859,0.01000,0.987
+18,fc2,0.00470324,0.01000,4.138
+19,self_attn.k_proj,0.02000524,0.01000,1.005
+19,self_attn.v_proj,0.02052886,0.01000,0.984
+19,self_attn.q_proj,0.01599333,0.01000,0.982
+19,self_attn.out_proj,0.00053542,0.01000,1.004
+19,fc1,0.08814689,0.01000,0.996
+19,fc2,0.00577823,0.01000,4.178
+20,self_attn.k_proj,0.02025632,0.01000,0.984
+20,self_attn.v_proj,0.02278810,0.01000,0.991
+20,self_attn.q_proj,0.01540255,0.01000,0.992
+20,self_attn.out_proj,0.00058181,0.01000,0.985
+20,fc1,0.09119438,0.01000,0.986
+20,fc2,0.00718106,0.01000,4.163
+21,self_attn.k_proj,0.01847481,0.01000,0.998
+21,self_attn.v_proj,0.02326399,0.01000,0.994
+21,self_attn.q_proj,0.01673961,0.01000,0.987
+21,self_attn.out_proj,0.00048029,0.01000,0.973
+21,fc1,0.09254406,0.01000,0.976
+21,fc2,0.00840400,0.01000,4.179
+22,self_attn.k_proj,0.01888512,0.01000,0.975
+22,self_attn.v_proj,0.02509475,0.01000,0.958
+22,self_attn.q_proj,0.02004961,0.01000,1.003
+22,self_attn.out_proj,0.00058037,0.01000,0.983
+22,fc1,0.09147193,0.01000,0.987
+22,fc2,0.00895930,0.01000,4.147
+23,self_attn.k_proj,0.02566331,0.01000,0.992
+23,self_attn.v_proj,0.01643573,0.01000,0.980
+23,self_attn.q_proj,0.06567268,0.01000,1.002
+23,self_attn.out_proj,0.00118536,0.01000,0.979
+23,fc1,0.08527403,0.01000,0.988
+23,fc2,0.00677233,0.01000,4.161

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
+}