mlc-ai
/

Llama-3-8B-Instruct-q3f16_2-MLC

Model card Files Files and versions Community

ruihanglai commited on Apr 19

Commit

8592f44

•

1 Parent(s): 0736d97

Update mlc-chat-config.json

Files changed (1) hide show

mlc-chat-config.json +4 -4

mlc-chat-config.json CHANGED Viewed

@@ -9,17 +9,17 @@
     "rms_norm_eps": 1e-05,
     "vocab_size": 128256,
     "position_embedding_base": 500000.0,
-    "context_window_size": 8192,
-    "prefill_chunk_size": 8192,
     "num_key_value_heads": 8,
     "head_dim": 128,
     "tensor_parallel_shards": 1,
     "max_batch_size": 80
   },
   "vocab_size": 128256,
-  "context_window_size": 8192,
   "sliding_window_size": -1,
-  "prefill_chunk_size": 8192,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "mean_gen_len": 128,

     "rms_norm_eps": 1e-05,
     "vocab_size": 128256,
     "position_embedding_base": 500000.0,
+    "context_window_size": 768,
+    "prefill_chunk_size": 512,
     "num_key_value_heads": 8,
     "head_dim": 128,
     "tensor_parallel_shards": 1,
     "max_batch_size": 80
   },
   "vocab_size": 128256,
+  "context_window_size": 768,
   "sliding_window_size": -1,
+  "prefill_chunk_size": 512,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "mean_gen_len": 128,