Atotti
/

TinySwallow-GRPO-TMethod-experimental-q4f32_1-MLC

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Atotti commited on 9 days ago

Commit

8656520

·

verified ·

1 Parent(s): 422a726

Upload 38 files

Files changed (1) hide show

mlc-chat-config.json +2 -2

mlc-chat-config.json CHANGED Viewed

@@ -14,7 +14,7 @@
     "vocab_size": 151936,
     "tie_word_embeddings": true,
     "context_window_size": 32768,
-    "prefill_chunk_size": 8192,
     "tensor_parallel_shards": 1,
     "head_dim": 128,
     "dtype": "float32",
@@ -23,7 +23,7 @@
   "vocab_size": 151936,
   "context_window_size": 32768,
   "sliding_window_size": -1,
-  "prefill_chunk_size": 8192,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,

     "vocab_size": 151936,
     "tie_word_embeddings": true,
     "context_window_size": 32768,
+    "prefill_chunk_size": 2048,
     "tensor_parallel_shards": 1,
     "head_dim": 128,
     "dtype": "float32",
   "vocab_size": 151936,
   "context_window_size": 32768,
   "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,