GPTQ commit model & tokenizer

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "abacusai/Smaug-Llama-3-70B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 8,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "group_size": 128,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_flash_attention_2": true,
+  "vocab_size": 128256
+}

gptq_model-8bit-128g-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9397f4f92a4350f6c22dd01adbe28e47228a68710e8db2edeff640b9ff90299f
+size 9985701816

gptq_model-8bit-128g-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738dfad4236d160c957144b0e7f879f68aa23919b47d441ae4a7942b0a8aca0d
+size 9791101440

gptq_model-8bit-128g-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca02383d04174b656390b2f38886a9ae720b0a01953a64e211a73aee3a4d4133
+size 9876853960

gptq_model-8bit-128g-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4364b1d99004329d2ddedfe095b3e6985f547cf741d71124ca4a0a3a74db8dcf
+size 9876853952

gptq_model-8bit-128g-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3fa22bf950be3c20a868eb2e4f50d0c233c810f0ea5c3c4a27c272cf9add59
+size 9962920712

gptq_model-8bit-128g-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0c47b2291c7c6897c89c7daac7ee780269d194251b031bb2ed1328f5dcadd5
+size 9945568912

gptq_model-8bit-128g-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887e3a8fed53a283fabda315d62c6c3300802b667b0167aa7e3cebddd1e47bcd
+size 9876853952

gptq_model-8bit-128g-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beee7702c0dddf05bc2a682238b04bbdffe215ea9310b6fc23ed2cb707854216
+size 4970015736

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 8,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
+}