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 sha256:251a68caf4367ed7a6038a812d0066f7e7d88e9fa1a1cb33c713b6c55b858b8e
+size 845033800

quant_log.csv

@@ -0,0 +1,145 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.00409379,0.01000,1.022
+0,self_attn.v_proj,0.00072114,0.01000,1.006
+0,self_attn.q_proj,0.00414090,0.01000,0.969
+0,self_attn.out_proj,0.00000870,0.01000,0.986
+0,fc1,0.00970921,0.01000,1.046
+0,fc2,0.00010505,0.01000,4.252
+1,self_attn.k_proj,0.00327041,0.01000,1.012
+1,self_attn.v_proj,0.00041319,0.01000,1.001
+1,self_attn.q_proj,0.00355976,0.01000,0.986
+1,self_attn.out_proj,0.00000244,0.01000,1.018
+1,fc1,0.01151395,0.01000,1.005
+1,fc2,0.00014460,0.01000,4.327
+2,self_attn.k_proj,0.00454492,0.01000,0.993
+2,self_attn.v_proj,0.00071424,0.01000,0.980
+2,self_attn.q_proj,0.00453008,0.01000,0.991
+2,self_attn.out_proj,0.00000383,0.01000,1.002
+2,fc1,0.01163073,0.01000,0.999
+2,fc2,0.00006701,0.01000,4.270
+3,self_attn.k_proj,0.00453221,0.01000,0.995
+3,self_attn.v_proj,0.00088928,0.01000,1.014
+3,self_attn.q_proj,0.00502093,0.01000,1.022
+3,self_attn.out_proj,0.00000183,0.01000,1.003
+3,fc1,0.01080185,0.01000,1.026
+3,fc2,0.00006996,0.01000,4.321
+4,self_attn.k_proj,0.00675831,0.01000,1.039
+4,self_attn.v_proj,0.00108673,0.01000,0.992
+4,self_attn.q_proj,0.00723823,0.01000,1.073
+4,self_attn.out_proj,0.00000383,0.01000,1.058
+4,fc1,0.01171546,0.01000,0.999
+4,fc2,0.00007058,0.01000,4.253
+5,self_attn.k_proj,0.00815600,0.01000,0.989
+5,self_attn.v_proj,0.00138022,0.01000,1.066
+5,self_attn.q_proj,0.00834911,0.01000,0.994
+5,self_attn.out_proj,0.00000388,0.01000,1.050
+5,fc1,0.01271201,0.01000,1.005
+5,fc2,0.00009196,0.01000,4.272
+6,self_attn.k_proj,0.01265277,0.01000,0.989
+6,self_attn.v_proj,0.00174527,0.01000,0.975
+6,self_attn.q_proj,0.01124555,0.01000,1.008
+6,self_attn.out_proj,0.00000933,0.01000,1.001
+6,fc1,0.01568377,0.01000,1.001
+6,fc2,0.00009791,0.01000,4.231
+7,self_attn.k_proj,0.01346123,0.01000,0.994
+7,self_attn.v_proj,0.00204103,0.01000,0.989
+7,self_attn.q_proj,0.01190130,0.01000,0.990
+7,self_attn.out_proj,0.00001416,0.01000,1.009
+7,fc1,0.01938798,0.01000,1.004
+7,fc2,0.00014014,0.01000,4.244
+8,self_attn.k_proj,0.01525222,0.01000,1.020
+8,self_attn.v_proj,0.00235129,0.01000,0.988
+8,self_attn.q_proj,0.01232455,0.01000,0.991
+8,self_attn.out_proj,0.00001867,0.01000,1.001
+8,fc1,0.02317689,0.01000,1.018
+8,fc2,0.00017385,0.01000,4.215
+9,self_attn.k_proj,0.01641444,0.01000,0.995
+9,self_attn.v_proj,0.00270767,0.01000,1.023
+9,self_attn.q_proj,0.01364542,0.01000,1.007
+9,self_attn.out_proj,0.00002797,0.01000,0.987
+9,fc1,0.02664278,0.01000,0.999
+9,fc2,2.56742547,0.01250,4.445
+10,self_attn.k_proj,0.01577057,0.01000,0.994
+10,self_attn.v_proj,0.00330441,0.01000,0.999
+10,self_attn.q_proj,0.01304028,0.01000,0.992
+10,self_attn.out_proj,0.00005218,0.01000,0.996
+10,fc1,0.02900651,0.01000,0.998
+10,fc2,0.00040414,0.01000,4.289
+11,self_attn.k_proj,0.01669788,0.01000,1.005
+11,self_attn.v_proj,0.00428681,0.01000,0.985
+11,self_attn.q_proj,0.01389177,0.01000,0.979
+11,self_attn.out_proj,0.00003902,0.01000,0.997
+11,fc1,0.03293292,0.01000,0.999
+11,fc2,0.00036001,0.01000,4.255
+12,self_attn.k_proj,0.01809878,0.01000,0.997
+12,self_attn.v_proj,0.00461741,0.01000,0.969
+12,self_attn.q_proj,0.01426543,0.01000,0.993
+12,self_attn.out_proj,0.00008923,0.01000,1.003
+12,fc1,0.03490859,0.01000,0.999
+12,fc2,0.00053366,0.01000,4.238
+13,self_attn.k_proj,0.02024559,0.01000,1.000
+13,self_attn.v_proj,0.00529331,0.01000,1.002
+13,self_attn.q_proj,0.01510829,0.01000,0.994
+13,self_attn.out_proj,0.00011232,0.01000,1.021
+13,fc1,0.04002735,0.01000,1.002
+13,fc2,0.00079521,0.01000,4.285
+14,self_attn.k_proj,0.02019605,0.01000,0.993
+14,self_attn.v_proj,0.00715139,0.01000,0.986
+14,self_attn.q_proj,0.01556215,0.01000,0.982
+14,self_attn.out_proj,0.00013239,0.01000,0.988
+14,fc1,0.04567505,0.01000,1.026
+14,fc2,0.00109855,0.01000,4.247
+15,self_attn.k_proj,0.01876904,0.01000,1.011
+15,self_attn.v_proj,0.00927897,0.01000,1.025
+15,self_attn.q_proj,0.01618721,0.01000,1.082
+15,self_attn.out_proj,0.00013910,0.01000,1.037
+15,fc1,0.04992504,0.01000,0.998
+15,fc2,0.00144680,0.01000,4.283
+16,self_attn.k_proj,0.01909367,0.01000,0.997
+16,self_attn.v_proj,0.01037889,0.01000,0.986
+16,self_attn.q_proj,0.01454423,0.01000,0.998
+16,self_attn.out_proj,0.00020494,0.01000,0.990
+16,fc1,0.05550109,0.01000,0.997
+16,fc2,0.00181646,0.01000,4.268
+17,self_attn.k_proj,0.01868965,0.01000,1.021
+17,self_attn.v_proj,0.01156883,0.01000,0.980
+17,self_attn.q_proj,0.01493619,0.01000,0.997
+17,self_attn.out_proj,0.00022462,0.01000,0.999
+17,fc1,0.06165383,0.01000,1.022
+17,fc2,0.00235090,0.01000,4.320
+18,self_attn.k_proj,0.01697141,0.01000,0.998
+18,self_attn.v_proj,0.01306967,0.01000,0.993
+18,self_attn.q_proj,0.01436241,0.01000,1.007
+18,self_attn.out_proj,0.00025583,0.01000,0.994
+18,fc1,0.06307104,0.01000,1.001
+18,fc2,0.00259235,0.01000,4.204
+19,self_attn.k_proj,0.01683915,0.01000,1.004
+19,self_attn.v_proj,0.01634647,0.01000,0.989
+19,self_attn.q_proj,0.01405389,0.01000,0.988
+19,self_attn.out_proj,0.00030797,0.01000,1.010
+19,fc1,0.06668582,0.01000,1.014
+19,fc2,0.00294858,0.01000,4.217
+20,self_attn.k_proj,0.01660586,0.01000,0.997
+20,self_attn.v_proj,0.01790955,0.01000,1.003
+20,self_attn.q_proj,0.01307197,0.01000,0.983
+20,self_attn.out_proj,0.00048068,0.01000,0.998
+20,fc1,0.06591332,0.01000,1.005
+20,fc2,0.00350037,0.01000,4.249
+21,self_attn.k_proj,0.01451043,0.01000,0.992
+21,self_attn.v_proj,0.01692051,0.01000,0.982
+21,self_attn.q_proj,0.01337012,0.01000,1.004
+21,self_attn.out_proj,0.00033322,0.01000,1.010
+21,fc1,0.06099212,0.01000,1.001
+21,fc2,0.00390600,0.01000,4.357
+22,self_attn.k_proj,0.01366263,0.01000,0.984
+22,self_attn.v_proj,0.01748320,0.01000,0.997
+22,self_attn.q_proj,0.01474320,0.01000,0.996
+22,self_attn.out_proj,0.00038908,0.01000,1.004
+22,fc1,0.05703627,0.01000,1.007
+22,fc2,0.00426069,0.01000,4.242
+23,self_attn.k_proj,0.01776943,0.01000,0.998
+23,self_attn.v_proj,0.01178338,0.01000,1.004
+23,self_attn.q_proj,0.03046774,0.01000,1.023
+23,self_attn.out_proj,0.00090270,0.01000,1.002
+23,fc1,0.05197454,0.01000,1.012
+23,fc2,0.00358283,0.01000,4.266

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
+}