nytopop
/

Llama-3.2-3B-Instruct-abliterated.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

nytopop commited on Apr 19

Commit

9b4bd43

·

verified ·

1 Parent(s): b987274

Upload config.json with huggingface_hub

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -57,7 +57,7 @@
       }
     },
     "format": "int-quantized",
-    "global_compression_ratio": 2.0728733847843293,
     "ignore": [
       "lm_head"
     ],
@@ -75,7 +75,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_cache": true,
   "vocab_size": 128256

       }
     },
     "format": "int-quantized",
+    "global_compression_ratio": 1.5267954166889706,
     "ignore": [
       "lm_head"
     ],
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "use_cache": true,
   "vocab_size": 128256