Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+base_model: facebook/opt-30b
+---
+
+
+Quantized using Intel's [AutoRound](https://github.com/intel/auto-round) quantization tool.
+~~~
+auto-round-best --model facebook/opt-30b --scheme "w4a16"
+~~~

config.json

@@ -0,0 +1,42 @@
+{
+  "_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,
+  "dtype": "float16",
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 28672,
+  "hidden_size": 7168,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "quantization_config": {
+    "autoround_version": "0.7.1",
+    "bits": 4,
+    "data_type": "int",
+    "group_size": 128,
+    "iters": 1000,
+    "low_gpu_mem_usage": true,
+    "nsamples": 512,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 7168
+}

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": "4.57.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c3fa94d3e68604a1be254907165fa51cbdb3f2d540280d5707b2bdde2c2c83
+size 4996914936

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8be09fe610afa163ef9a8962da8cfab89d9124439b4d7de76af5cc24b2f48e1
+size 4941268792

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47daa4891252831952da481e167d08389b00db54cfba8866845a078e852614c
+size 4994642672

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ea99e1187131f0fa908943bc25b8d4f83774626ca6d11b29bf6599cf58b80d
+size 1201927704

quantization_config.json

@@ -0,0 +1,12 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "iters": 1000,
+  "nsamples": 512,
+  "low_gpu_mem_usage": true,
+  "autoround_version": "0.7.1",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}