PrunaAI
/

microsoft-Phi-3-mini-128k-instruct-bnb-4bit-smashed

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

sharpenb commited on Apr 4

Commit

64072f6

·

verified ·

1 Parent(s): c37134d

Upload folder using huggingface_hub (#4)

- facedea677baa400c8d99d529cbd252c54f14b5acf8870c518ff67e22a87941c (bfcc9b10862a16240aded8dbe982347a5d5027b4)

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/tmp2pdlxedx3h7_ea2l",
   "architectures": [
     "Phi3ForCausalLM"
   ],

 {
+  "_name_or_path": "/tmp/models/tmpf_2mywlevftq_dc5",
   "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/tmp2pdlxedx",
     "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/tmpf_2mywle",
     "task": "",
     "save_load_fn": "llm-int8",
     "save_load_fn_args": {},