Upload Phi3ForCausalLM

config.json

@@ -24,19 +24,15 @@
   "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
   "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": true,
-    "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"
+    "bits": 4,
+    "damp_percent": 0.1,
+    "dataset": "wikitext2",
+    "desc_act": false,
+    "group_size": 128,
+    "modules_in_block_to_quantize": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true
   },
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afd3681888f095180a4010a0889d2f6ed55fb35fb91c7e4d877c2d038ef1320
-size 2264109944
+oid sha256:8cc2aa9e1daa06456ef8061063e9bade3fd2103ffb3eadcc5370c9a2888dda7b
+size 2279413824