arzeth
/

TowerInstruct-7B-v0.2-GGUF

text-generation-inference

Model card Files Files and versions Community

arzeth commited on Feb 24

Commit

e2d293e

•

1 Parent(s): 0668613

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -22,7 +22,8 @@ quantized_by: arzeth
 # Model Info
 - Model creator: [Unbabel](https://huggingface.co/Unbabel)
-- Original card: https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2
 - Context size: 4096, but according to the model's card it was trained with `max_seq_length: 2048`, so make sure your input is ≤2048 tokens (is that ~1500 words?).
 - Template: The model was trained using the ChatML prompt templates **WITHOUT ANY SYSTEM PROMPTS !!!**, i.e. there's no `<|im_start|>system`, it's just
 ```

 # Model Info
 - Model creator: [Unbabel](https://huggingface.co/Unbabel)
+- Original card (has more info): https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2
+- Languages: English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian.
 - Context size: 4096, but according to the model's card it was trained with `max_seq_length: 2048`, so make sure your input is ≤2048 tokens (is that ~1500 words?).
 - Template: The model was trained using the ChatML prompt templates **WITHOUT ANY SYSTEM PROMPTS !!!**, i.e. there's no `<|im_start|>system`, it's just
 ```