nm-testing
/

TinyLlama-1.1B-Chat-v1.0-FP8_DYNAMIC-e2e

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

nm-autobot commited on 26 days ago

Commit

6597bde

•

1 Parent(s): 0bb1451

Upload LlamaForCausalLM

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -28,7 +28,7 @@
           "dynamic": true,
           "group_size": null,
           "num_bits": 8,
-          "observer": "memoryless",
           "observer_kwargs": {},
           "strategy": "token",
           "symmetric": true,
@@ -53,7 +53,7 @@
       }
     },
     "format": "float-quantized",
-    "global_compression_ratio": 1.2383372224751887,
     "ignore": [
       "lm_head"
     ],

           "dynamic": true,
           "group_size": null,
           "num_bits": 8,
+          "observer": null,
           "observer_kwargs": {},
           "strategy": "token",
           "symmetric": true,
       }
     },
     "format": "float-quantized",
+    "global_compression_ratio": 1.4555025329431568,
     "ignore": [
       "lm_head"
     ],