mohitsha
/

Llama-2-70b-chat-hf-FP8-KV

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mohitsha HF staff commited on Jun 25

Commit

4eb30e1

•

1 Parent(s): 6c793bd

Update config.json

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -11,6 +11,7 @@
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",

   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
+  "kv_cache_torch_dtype": "float8_e4m3fn",
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",