Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "VMware/xgen-7b-8k-open-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "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": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664209bb4079dce4b55b59e630191acb85bac1d5e4cbe625dcb331f7de4d3c02
+size 4211586583

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": null,
+  "model_file_base_name": null
+}