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 sha256:1fdc52cf6152a71be7ec16ab1b22c8af5892676eed314b2b59ecbf1222f690c6
+size 845033800

quant_log.csv

@@ -0,0 +1,145 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.01193101,0.01000,0.766
+0,self_attn.v_proj,0.00204742,0.01000,0.744
+0,self_attn.q_proj,0.01151794,0.01000,0.751
+0,self_attn.out_proj,0.00000879,0.01000,0.750
+0,fc1,0.07220605,0.01000,0.777
+0,fc2,0.00009904,0.01000,3.377
+1,self_attn.k_proj,0.02748547,0.01000,0.773
+1,self_attn.v_proj,0.00377348,0.01000,0.771
+1,self_attn.q_proj,0.03053766,0.01000,0.799
+1,self_attn.out_proj,0.00000212,0.01000,0.788
+1,fc1,0.10564113,0.01000,0.766
+1,fc2,0.00011769,0.01000,3.389
+2,self_attn.k_proj,0.03364365,0.01000,0.774
+2,self_attn.v_proj,0.00638163,0.01000,0.770
+2,self_attn.q_proj,0.03404787,0.01000,0.763
+2,self_attn.out_proj,0.00000442,0.01000,0.761
+2,fc1,0.10685527,0.01000,0.783
+2,fc2,0.00007892,0.01000,3.447
+3,self_attn.k_proj,0.03226093,0.01000,0.772
+3,self_attn.v_proj,0.00772221,0.01000,0.755
+3,self_attn.q_proj,0.03518277,0.01000,0.763
+3,self_attn.out_proj,0.00000809,0.01000,0.790
+3,fc1,0.09162843,0.01000,0.769
+3,fc2,0.00007157,0.01000,3.342
+4,self_attn.k_proj,0.03976664,0.01000,0.771
+4,self_attn.v_proj,0.00833308,0.01000,0.770
+4,self_attn.q_proj,0.04298474,0.01000,0.770
+4,self_attn.out_proj,0.00001194,0.01000,0.785
+4,fc1,0.08744164,0.01000,0.789
+4,fc2,0.00008075,0.01000,3.376
+5,self_attn.k_proj,0.04211287,0.01000,0.773
+5,self_attn.v_proj,0.00969345,0.01000,0.766
+5,self_attn.q_proj,0.04678004,0.01000,0.765
+5,self_attn.out_proj,0.00001155,0.01000,0.764
+5,fc1,0.08947679,0.01000,0.773
+5,fc2,0.00009699,0.01000,3.370
+6,self_attn.k_proj,0.06050922,0.01000,0.801
+6,self_attn.v_proj,0.01090727,0.01000,0.750
+6,self_attn.q_proj,0.05891616,0.01000,0.755
+6,self_attn.out_proj,0.00003464,0.01000,0.763
+6,fc1,0.09683321,0.01000,0.768
+6,fc2,0.00013900,0.01000,3.376
+7,self_attn.k_proj,0.06143640,0.01000,0.792
+7,self_attn.v_proj,0.01166906,0.01000,0.763
+7,self_attn.q_proj,0.05640485,0.01000,0.786
+7,self_attn.out_proj,0.00004408,0.01000,0.763
+7,fc1,0.10895248,0.01000,0.778
+7,fc2,0.00020347,0.01000,3.344
+8,self_attn.k_proj,0.06507521,0.01000,0.768
+8,self_attn.v_proj,0.01208323,0.01000,0.777
+8,self_attn.q_proj,0.05399566,0.01000,0.760
+8,self_attn.out_proj,0.00005616,0.01000,0.763
+8,fc1,0.11881161,0.01000,0.782
+8,fc2,0.00026443,0.01000,3.333
+9,self_attn.k_proj,0.06506123,0.01000,0.786
+9,self_attn.v_proj,0.01248781,0.01000,0.765
+9,self_attn.q_proj,0.05453248,0.01000,0.783
+9,self_attn.out_proj,0.00007938,0.01000,0.764
+9,fc1,0.12274915,0.01000,0.769
+9,fc2,0.00035536,0.01000,3.326
+10,self_attn.k_proj,0.06140727,0.01000,0.768
+10,self_attn.v_proj,0.01420014,0.01000,0.767
+10,self_attn.q_proj,0.05016806,0.01000,0.763
+10,self_attn.out_proj,0.00011017,0.01000,0.760
+10,fc1,0.12526228,0.01000,0.774
+10,fc2,0.00056714,0.01000,3.383
+11,self_attn.k_proj,0.05852431,0.01000,0.759
+11,self_attn.v_proj,0.01596023,0.01000,0.767
+11,self_attn.q_proj,0.04750057,0.01000,0.764
+11,self_attn.out_proj,0.00014029,0.01000,0.774
+11,fc1,0.12785329,0.01000,0.775
+11,fc2,0.00075469,0.01000,3.320
+12,self_attn.k_proj,0.06211779,0.01000,0.773
+12,self_attn.v_proj,0.01650352,0.01000,0.763
+12,self_attn.q_proj,0.04717031,0.01000,0.777
+12,self_attn.out_proj,0.00022129,0.01000,0.761
+12,fc1,0.12406510,0.01000,0.769
+12,fc2,0.00102223,0.01000,3.390
+13,self_attn.k_proj,0.06443056,0.01000,0.781
+13,self_attn.v_proj,0.01726957,0.01000,0.772
+13,self_attn.q_proj,0.04661303,0.01000,0.758
+13,self_attn.out_proj,0.00023633,0.01000,0.765
+13,fc1,0.13054048,0.01000,0.792
+13,fc2,0.00139816,0.01000,3.390
+14,self_attn.k_proj,0.05847587,0.01000,0.771
+14,self_attn.v_proj,0.02090536,0.01000,0.770
+14,self_attn.q_proj,0.04376426,0.01000,0.788
+14,self_attn.out_proj,0.00027757,0.01000,0.761
+14,fc1,0.13830929,0.01000,0.779
+14,fc2,0.00192462,0.01000,3.343
+15,self_attn.k_proj,0.05246258,0.01000,0.773
+15,self_attn.v_proj,0.02610055,0.01000,0.773
+15,self_attn.q_proj,0.04327298,0.01000,0.758
+15,self_attn.out_proj,0.00027173,0.01000,0.767
+15,fc1,0.14475755,0.01000,0.775
+15,fc2,0.00244589,0.01000,3.321
+16,self_attn.k_proj,0.05219132,0.01000,0.786
+16,self_attn.v_proj,0.02799954,0.01000,0.762
+16,self_attn.q_proj,0.03783621,0.01000,0.763
+16,self_attn.out_proj,0.00039026,0.01000,0.769
+16,fc1,0.15572587,0.01000,0.782
+16,fc2,0.00316169,0.01000,3.376
+17,self_attn.k_proj,0.05054565,0.01000,0.830
+17,self_attn.v_proj,0.03031302,0.01000,0.771
+17,self_attn.q_proj,0.03752312,0.01000,0.761
+17,self_attn.out_proj,0.00044570,0.01000,0.765
+17,fc1,0.16843134,0.01000,0.772
+17,fc2,0.00403455,0.01000,3.315
+18,self_attn.k_proj,0.04542822,0.01000,0.766
+18,self_attn.v_proj,0.03442155,0.01000,0.753
+18,self_attn.q_proj,0.03605321,0.01000,0.759
+18,self_attn.out_proj,0.00034129,0.01000,0.769
+18,fc1,0.17829082,0.01000,0.769
+18,fc2,0.00384275,0.01000,3.513
+19,self_attn.k_proj,0.04639758,0.01000,0.772
+19,self_attn.v_proj,0.04432996,0.01000,0.771
+19,self_attn.q_proj,0.03613599,0.01000,0.770
+19,self_attn.out_proj,0.00052690,0.01000,0.781
+19,fc1,0.19145459,0.01000,0.782
+19,fc2,0.00470920,0.01000,3.507
+20,self_attn.k_proj,0.04799912,0.01000,0.791
+20,self_attn.v_proj,0.05039908,0.01000,0.762
+20,self_attn.q_proj,0.03520311,0.01000,0.781
+20,self_attn.out_proj,0.00063094,0.01000,0.774
+20,fc1,0.19941745,0.01000,0.783
+20,fc2,0.00606712,0.01000,3.514
+21,self_attn.k_proj,0.04461705,0.01000,0.797
+21,self_attn.v_proj,0.05256410,0.01000,0.784
+21,self_attn.q_proj,0.03900132,0.01000,0.821
+21,self_attn.out_proj,0.00054641,0.01000,0.773
+21,fc1,0.20300829,0.01000,0.783
+21,fc2,0.00714681,0.01000,3.591
+22,self_attn.k_proj,0.04705104,0.01000,0.829
+22,self_attn.v_proj,0.06090737,0.01000,0.750
+22,self_attn.q_proj,0.04897617,0.01000,0.805
+22,self_attn.out_proj,0.00065823,0.01000,0.755
+22,fc1,0.20262627,0.01000,0.766
+22,fc2,0.00769133,0.01000,3.481
+23,self_attn.k_proj,0.06682779,0.01000,0.775
+23,self_attn.v_proj,0.04476626,0.01000,0.787
+23,self_attn.q_proj,0.11386553,0.01000,0.775
+23,self_attn.out_proj,0.00203764,0.01000,0.774
+23,fc1,0.19634233,0.01000,0.810
+23,fc2,0.00576396,0.01000,3.536

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
+}