mlc-ai
/

internlm2_5-7b-chat-q4f16_1-MLC

Model card Files Files and versions Community

ruihanglai commited on Dec 5, 2024

Commit

651cd3a

·

verified ·

1 Parent(s): a776767

Update mlc-chat-config.json

Files changed (1) hide show

mlc-chat-config.json +2 -2

mlc-chat-config.json CHANGED Viewed

@@ -17,7 +17,7 @@
     "bos_token_id": 1,
     "eos_token_id": 2,
     "context_window_size": 32768,
-    "prefill_chunk_size": 8192,
     "tensor_parallel_shards": 1,
     "max_batch_size": 128,
     "head_dim": 128
@@ -25,7 +25,7 @@
   "vocab_size": 92544,
   "context_window_size": 32768,
   "sliding_window_size": -1,
-  "prefill_chunk_size": 8192,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,

     "bos_token_id": 1,
     "eos_token_id": 2,
     "context_window_size": 32768,
+    "prefill_chunk_size": 2048,
     "tensor_parallel_shards": 1,
     "max_batch_size": 128,
     "head_dim": 128
   "vocab_size": 92544,
   "context_window_size": 32768,
   "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,