GPTQ commit model & tokenizer

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "VAGOsolutions/Llama-3-SauerkrautLM-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 sha256:87b2c77eedc3a87e02b9c01edccb1ccd39effa6c043b98876732d6d34b3045b6
+size 9985701816

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916d3f25b0cc0c2652aa6bcb5bd3c081c64515cb32c676488f63e61b4de549f7
+size 9791101440

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558fed72f9325b1d95c09779e406e2126c9d9b7af3faa748422efc79aabc9212
+size 9876853960

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8b2a4973955c1ec24a3d7040c0d82b12f633a3583de33e82df0a7b500b5e41
+size 9876853952

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9de172b05e05aa9d30b47b1b6e43e178e9c625315dea291dfdc190da5052ca
+size 9962920712

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1eee7206f9d6bc64c645900ea2a7a470cf2e83121096b2e37d3748017cb96df
+size 9945568912

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96ee0b0e0dd3f4a777f59b7f6cfe94a3804a15e981902c2385623e7e10816e1
+size 9876853952

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33df02f2f05ab05144dc6254c857e1a2fc49897f6641ee68c826795ae489e83
+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"
+}