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:ed124f61348da0cb4e0a7c799ec5329571a4befcade8d125a62a086d4e5e120b
+size 845033800

quant_log.csv

@@ -0,0 +1,145 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.00353451,0.01000,0.969
+0,self_attn.v_proj,0.00058977,0.01000,0.974
+0,self_attn.q_proj,0.00354618,0.01000,0.978
+0,self_attn.out_proj,0.00000824,0.01000,0.970
+0,fc1,0.00833520,0.01000,1.004
+0,fc2,0.00010249,0.01000,4.179
+1,self_attn.k_proj,0.00306776,0.01000,0.981
+1,self_attn.v_proj,0.00038127,0.01000,0.983
+1,self_attn.q_proj,0.00334425,0.01000,0.977
+1,self_attn.out_proj,0.00000175,0.01000,0.984
+1,fc1,0.00991357,0.01000,1.006
+1,fc2,0.00011309,0.01000,4.198
+2,self_attn.k_proj,0.00421192,0.01000,1.006
+2,self_attn.v_proj,0.00065938,0.01000,1.016
+2,self_attn.q_proj,0.00423529,0.01000,1.001
+2,self_attn.out_proj,0.00000309,0.01000,0.978
+2,fc1,0.01081147,0.01000,0.995
+2,fc2,0.00007957,0.01000,4.203
+3,self_attn.k_proj,0.00461946,0.01000,0.982
+3,self_attn.v_proj,0.00091849,0.01000,0.968
+3,self_attn.q_proj,0.00513186,0.01000,0.985
+3,self_attn.out_proj,0.00000551,0.01000,0.970
+3,fc1,0.01119875,0.01000,1.003
+3,fc2,0.00016196,0.01000,4.206
+4,self_attn.k_proj,0.00732114,0.01000,0.975
+4,self_attn.v_proj,0.00129839,0.01000,0.987
+4,self_attn.q_proj,0.00789255,0.01000,0.991
+4,self_attn.out_proj,0.00001026,0.01000,0.971
+4,fc1,0.01312019,0.01000,1.002
+4,fc2,0.00010168,0.01000,4.180
+5,self_attn.k_proj,0.00943032,0.01000,0.995
+5,self_attn.v_proj,0.00169851,0.01000,0.983
+5,self_attn.q_proj,0.00934376,0.01000,0.988
+5,self_attn.out_proj,0.00001065,0.01000,0.976
+5,fc1,0.01450417,0.01000,0.995
+5,fc2,0.00010014,0.01000,4.242
+6,self_attn.k_proj,0.01406881,0.01000,0.979
+6,self_attn.v_proj,0.00209196,0.01000,1.001
+6,self_attn.q_proj,0.01253495,0.01000,0.997
+6,self_attn.out_proj,0.00002485,0.01000,0.986
+6,fc1,0.01773035,0.01000,0.989
+6,fc2,0.00012900,0.01000,4.185
+7,self_attn.k_proj,0.01532272,0.01000,1.006
+7,self_attn.v_proj,0.00260288,0.01000,1.008
+7,self_attn.q_proj,0.01319375,0.01000,0.989
+7,self_attn.out_proj,0.00003269,0.01000,0.982
+7,fc1,0.02224689,0.01000,1.003
+7,fc2,0.00018148,0.01000,4.185
+8,self_attn.k_proj,0.01737493,0.01000,1.003
+8,self_attn.v_proj,0.00307547,0.01000,0.988
+8,self_attn.q_proj,0.01380688,0.01000,1.017
+8,self_attn.out_proj,0.00004196,0.01000,0.998
+8,fc1,0.02693362,0.01000,0.998
+8,fc2,0.00022905,0.01000,4.197
+9,self_attn.k_proj,0.01874729,0.01000,0.995
+9,self_attn.v_proj,0.00358431,0.01000,0.974
+9,self_attn.q_proj,0.01549898,0.01000,0.986
+9,self_attn.out_proj,0.00006392,0.01000,0.976
+9,fc1,0.03071506,0.01000,1.002
+9,fc2,0.00029924,0.01000,4.202
+10,self_attn.k_proj,0.01883435,0.01000,0.986
+10,self_attn.v_proj,0.00462759,0.01000,0.981
+10,self_attn.q_proj,0.01545094,0.01000,1.009
+10,self_attn.out_proj,0.00007908,0.01000,0.976
+10,fc1,0.03539471,0.01000,1.005
+10,fc2,0.00047551,0.01000,4.169
+11,self_attn.k_proj,0.01965953,0.01000,0.976
+11,self_attn.v_proj,0.00583622,0.01000,1.063
+11,self_attn.q_proj,0.01612123,0.01000,0.979
+11,self_attn.out_proj,0.00011278,0.01000,0.987
+11,fc1,0.04005920,0.01000,1.000
+11,fc2,0.00065392,0.01000,4.175
+12,self_attn.k_proj,0.02262860,0.01000,0.982
+12,self_attn.v_proj,0.00656720,0.01000,0.983
+12,self_attn.q_proj,0.01734480,0.01000,1.003
+12,self_attn.out_proj,0.00019552,0.01000,0.971
+12,fc1,0.04258961,0.01000,0.996
+12,fc2,0.00086177,0.01000,4.204
+13,self_attn.k_proj,0.02449026,0.01000,1.010
+13,self_attn.v_proj,0.00719500,0.01000,0.972
+13,self_attn.q_proj,0.01807458,0.01000,0.984
+13,self_attn.out_proj,0.00020925,0.01000,0.986
+13,fc1,0.04750419,0.01000,1.048
+13,fc2,0.00113821,0.01000,4.242
+14,self_attn.k_proj,0.02323671,0.01000,0.980
+14,self_attn.v_proj,0.00916689,0.01000,0.992
+14,self_attn.q_proj,0.01773284,0.01000,0.984
+14,self_attn.out_proj,0.00023394,0.01000,0.986
+14,fc1,0.05279522,0.01000,1.008
+14,fc2,0.00154404,0.01000,4.219
+15,self_attn.k_proj,0.02133237,0.01000,0.974
+15,self_attn.v_proj,0.01157838,0.01000,0.985
+15,self_attn.q_proj,0.01792355,0.01000,0.985
+15,self_attn.out_proj,0.00021368,0.01000,0.977
+15,fc1,0.05596036,0.01000,0.992
+15,fc2,0.00193929,0.01000,4.221
+16,self_attn.k_proj,0.02109856,0.01000,0.973
+16,self_attn.v_proj,0.01237937,0.01000,1.001
+16,self_attn.q_proj,0.01584957,0.01000,0.985
+16,self_attn.out_proj,0.00034128,0.01000,0.977
+16,fc1,0.06065808,0.01000,0.993
+16,fc2,0.00244585,0.01000,4.189
+17,self_attn.k_proj,0.02028195,0.01000,0.977
+17,self_attn.v_proj,0.01342661,0.01000,0.991
+17,self_attn.q_proj,0.01595530,0.01000,0.993
+17,self_attn.out_proj,0.00040838,0.01000,0.981
+17,fc1,0.06696854,0.01000,0.992
+17,fc2,0.00311560,0.01000,4.158
+18,self_attn.k_proj,0.01867285,0.01000,0.974
+18,self_attn.v_proj,0.01530573,0.01000,0.976
+18,self_attn.q_proj,0.01553169,0.01000,0.966
+18,self_attn.out_proj,0.00042700,0.01000,0.964
+18,fc1,0.07043907,0.01000,1.026
+18,fc2,0.00372020,0.01000,4.228
+19,self_attn.k_proj,0.01878069,0.01000,0.981
+19,self_attn.v_proj,0.01981840,0.01000,0.984
+19,self_attn.q_proj,0.01559329,0.01000,1.002
+19,self_attn.out_proj,0.00065731,0.01000,0.973
+19,fc1,0.07642501,0.01000,0.999
+19,fc2,0.00461285,0.01000,4.212
+20,self_attn.k_proj,0.01907601,0.01000,0.976
+20,self_attn.v_proj,0.02192091,0.01000,0.999
+20,self_attn.q_proj,0.01519119,0.01000,0.988
+20,self_attn.out_proj,0.00074141,0.01000,0.981
+20,fc1,0.07924981,0.01000,0.996
+20,fc2,0.00593197,0.01000,4.169
+21,self_attn.k_proj,0.01771271,0.01000,0.975
+21,self_attn.v_proj,0.02231180,0.01000,0.977
+21,self_attn.q_proj,0.01639184,0.01000,0.989
+21,self_attn.out_proj,0.00067609,0.01000,0.972
+21,fc1,0.07996578,0.01000,0.996
+21,fc2,0.00687802,0.01000,4.204
+22,self_attn.k_proj,0.01819149,0.01000,0.976
+22,self_attn.v_proj,0.02417441,0.01000,0.978
+22,self_attn.q_proj,0.01968422,0.01000,0.975
+22,self_attn.out_proj,0.00073485,0.01000,0.996
+22,fc1,0.07849728,0.01000,0.997
+22,fc2,0.00727349,0.01000,4.153
+23,self_attn.k_proj,0.02505763,0.01000,0.992
+23,self_attn.v_proj,0.01610191,0.01000,0.979
+23,self_attn.q_proj,0.05779545,0.01000,0.980
+23,self_attn.out_proj,0.00132728,0.01000,0.974
+23,fc1,0.07213598,0.01000,1.002
+23,fc2,0.00554883,0.01000,4.210

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
+}