GPTQ commit model & tokenizer

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "meta-llama/Meta-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,
+  "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:ea667ab3685edc219afbd2a9c9d5d01c05e893b5cd96157d85a0c493e31f0106
+size 9985701816

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da39f4dfd1ae3c03837b07991c4e4a2fb1944b92b58dc155af92fc6381b48a4
+size 9791101440

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259a5ea283d8eb3ee8af214848403838f2d0ab02e50bc9a2738ff9bee79dc874
+size 9876853960

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68c2dcd5ffe95d7d7708923d5df0c4bdeb33b3efa6b92caba9d4e7d9ec070af
+size 9876853952

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae24f7ba3dbd6e48ae79e0bf910d9eb0909864bf825e0116edc27b5acfd97b5
+size 9962920712

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c67820b4c551e18ff85b4c505ec62375c02cde004c78e9f4821cdd596a7824
+size 9945568912

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e926964290b69db7e17847900185de44a210a8f83a0d563cb1ea69ed601b6909
+size 9876853952

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a70e17a609779ff72f24098fc44174d9a76faf8fdd70c246ddc97753821bd6
+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"
+}