mohitsha
/

Llama-2-7b-chat-hf-FP8-FNUZ-KV-AMMO

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mohitsha HF staff commited on Jun 25

Commit

6e114cb

•

1 Parent(s): 9e904e9

Upload folder using huggingface_hub

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "kv_cache_dtype": "float8_e4m3fnuz",
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",

   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "kv_cache_torch_dtype": "float8_e4m3fnuz",
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",