PrunaAI
/

teknium-OpenHermes-2.5-Mistral-7B-bnb-4bit-smashed

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

sharpenb commited on Apr 4

Commit

67e1c34

·

verified ·

1 Parent(s): d4c467a

Upload folder using huggingface_hub (#4)

- ae255071f6c1ec0f6d9a3c6ac1f5a56397c2eb56a3d5982522da8ecada8f75b2 (4d58ae621425610e55f917c87cc01443df863b3b)

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/tmpqu1t5fy_hge0kx_y",
   "architectures": [
     "MistralForCausalLM"
   ],

 {
+  "_name_or_path": "/tmp/models/tmpbxz4q61fm6nhz9oz",
   "architectures": [
     "MistralForCausalLM"
   ],

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/tmpqu1t5fy_",
     "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/tmpbxz4q61f",
     "task": "",
     "save_load_fn": "llm-int8",
     "save_load_fn_args": {},