Hugging Face's logo

buddhist-nlp
/
gemma-2-mitra-it-int8

Transformers
Inference Endpoints
Model card Files Community
snehrdich commited on
Commit
6eac43e
·
verified ·
1 Parent(s): f55d3a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -3,11 +3,10 @@ library_name: transformers
3
  tags: []
4
  ---
5
 
6
- # gemma2-mitra-it-8int
7
  This is an 8int quantized version of gemma-2-mitra-it: https://huggingface.co/buddhist-nlp/gemma-2-mitra-it
8
  The quantization was done with llm compressor: https://github.com/vllm-project/llm-compressor
9
 
10
- This is based on gemma2-mitra-base and finetuned on Translation instructions.
11
  The template for prompting the model is this:
12
  ```
13
  Please translate into <target_language>: <input_sentence> 🔽 Translation::
 
3
  tags: []
4
  ---
5
 
6
+ # gemma2-mitra-it-int8
7
  This is an 8int quantized version of gemma-2-mitra-it: https://huggingface.co/buddhist-nlp/gemma-2-mitra-it
8
  The quantization was done with llm compressor: https://github.com/vllm-project/llm-compressor
9
 
 
10
  The template for prompting the model is this:
11
  ```
12
  Please translate into <target_language>: <input_sentence> 🔽 Translation::