build: AutoGPTQ for ehartford/WizardLM-7B-Uncensored: 4bits, gr128, desc_act=False

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "wizardlm-7b-uncensored-gptq",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120e074faf9e1238f2d880213476069691f64f7ec68d63ba4821ac7c093b6018
+size 3897030167

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748d22b0f8c6f9ccd49b0df4e03e44de7d0c27d851a1aa6992974149a96b1e55
+size 3896706880

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "wizardlm-7b-uncensored-gptq",
+  "model_file_base_name": "gptq_model-4bit-128g"
+}