Hugging Face's logo

typhoon-ai
/
typhoon-translate-4b-mlx-4bit

Text Generation
MLX
Safetensors
Thai
English
gemma3
conversational
4-bit precision
Model card Files
xet
 Community
kunato commited on
Commit
2bd2fa4
·
verified ·
1 Parent(s): e52ec6b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -4,6 +4,10 @@ library_name: mlx
4
  pipeline_tag: text-generation
5
  tags:
6
  - mlx
 
 
 
 
7
  ---
8
 
9
  # scb10x/typhoon-translate-4b-mlx-4bit
@@ -36,4 +40,4 @@ messages = [
36
  prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
37
 
38
  response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=2048)
39
- ```
 
4
  pipeline_tag: text-generation
5
  tags:
6
  - mlx
7
+ license: gemma
8
+ language:
9
+ - th
10
+ - en
11
  ---
12
 
13
  # scb10x/typhoon-translate-4b-mlx-4bit
 
40
  prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
41
 
42
  response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=2048)
43
+ ```