PrunaAI
/

microsoft-Phi-3-mini-4k-instruct-bnb-4bit-smashed

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

sharpenb commited on Apr 4

Commit

cfbe604

·

verified ·

1 Parent(s): 589a06c

Upload folder using huggingface_hub (#4)

- e20093f7307c179b0689534c652a21979702af473af6112e49c4d5bc0815ae85 (abce3c974273528fe08a379bdeb07f24791f9004)

Files changed (2) hide show

config.json +1 -1
smash_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/models/tmpg84jb_1p3js754wb",
   "architectures": [
     "Phi3ForCausalLM"
   ],

 {
+  "_name_or_path": "/tmp/models/tmpx_fzfa65zxgimdt6",
   "architectures": [
     "Phi3ForCausalLM"
   ],

smash_config.json CHANGED Viewed

@@ -15,7 +15,7 @@
     "quant_llm-int8_weight_bits": 4,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/tmp/models/tmpg84jb_1p",
     "task": "",
     "save_load_fn": "llm-int8",
     "save_load_fn_args": {},

     "quant_llm-int8_weight_bits": 4,
     "max_batch_size": 1,
     "device": "cuda",
+    "cache_dir": "/tmp/models/tmpx_fzfa65",
     "task": "",
     "save_load_fn": "llm-int8",
     "save_load_fn_args": {},