animaRegem
/

llama-3-gaya-3-malayalam-model-vllm-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

animaRegem commited on May 8

Commit

ca4693f

•

1 Parent(s): 34e87cd

Trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -2056,7 +2056,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 16384,
   "pad_token": "<|reserved_special_token_250|>",
   "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"

     "input_ids",
     "attention_mask"
   ],
+  "model_max_length": 8192,
   "pad_token": "<|reserved_special_token_250|>",
   "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"