AutoGPTQ model for facebook/opt-125m: 8bits, gr128, desc_act=False

config.json

@@ -23,8 +23,35 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "prefix": "</s>",
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 2,
+    "block_name_to_quantize": "model.decoder.layers",
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "disable_exllama": false,
+    "exllama_config": {
+      "version": 2
+    },
+    "exllama_version": 2,
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": 2048,
+    "module_name_preceding_first_block": [
+      "model.decoder.embed_tokens",
+      "model.decoder.embed_positions",
+      "model.decoder.final_layer_norm"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
   "torch_dtype": "float16",
-  "transformers_version": "4.36.0.dev0",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 50272,
   "word_embed_proj_dim": 768

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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044bae54d8c04c7672f7d2d529e50c2211ad2776f41b697fa686fd9fec0fe2fd
+size 103713936