Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "garage-bAInd/Platypus2-70B-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afa83ead7564fd35c7349eeaf2dcde0bccdae590897da3a10e0291486d9bdd3
+size 36653074331

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b19a472b0f1a740e617e6ca1670b31ac9af9cfb18bb2fe4b5c1354c8b94edb
+size 36652345632

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "Platypus2-70B-instruct-4bit",
+  "model_file_base_name": "gptq_model-4bit-128g"
+}