Text Generation
Transformers
Safetensors
Thai
English
qwen2
text-generation-inference
sft
trl
4-bit precision
bitsandbytes
LoRA
Fine-Tuning with LoRA
LLM
GenAI
NT GenAI
ntgenai
lahnmah
NT Thai GPT
ntthaigpt
medical
medtech
HealthGPT
หลานม่า
NT Academy
conversational
Inference Endpoints
4-bit precision
Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +0 -4
special_tokens_map.json
CHANGED
@@ -21,11 +21,5 @@
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
-
"pad_token":
|
25 |
-
"content": "<|im_end|>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
}
|
31 |
}
|
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
+
"pad_token": "<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
tokenizer_config.json
CHANGED
@@ -199,13 +199,9 @@
|
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
-
"max_length": 512,
|
203 |
"model_max_length": 131072,
|
204 |
"pad_token": "<|im_end|>",
|
205 |
"split_special_tokens": false,
|
206 |
-
"stride": 0,
|
207 |
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
-
"truncation_side": "right",
|
209 |
-
"truncation_strategy": "longest_first",
|
210 |
"unk_token": null
|
211 |
}
|
|
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
|
|
202 |
"model_max_length": 131072,
|
203 |
"pad_token": "<|im_end|>",
|
204 |
"split_special_tokens": false,
|
|
|
205 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
|
206 |
"unk_token": null
|
207 |
}
|