Upload GPTNeoXForCausalLM

config.json

@@ -19,11 +19,26 @@
   "num_attention_heads": 8,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "use_parallel_residual": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3549d3d2a785b94af370c0d0dfa9e4c464b85baba7c03d4e5ee1cb0baa7736
-size 281715176
+oid sha256:f412b68b0502219928444040879b846679572d2e233599fefc3035dfcda21ea3
+size 113742442