ilsp
/

Meltemi-7B-Instruct-v1-AWQ

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

geopar commited on Mar 29

Commit

0f5f40e

•

1 Parent(s): ef52388

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -58,7 +58,7 @@ messages = [
     {"role": "user", "content": "Πες μου αν έχεις συνείδηση."},
 ]
-prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 input_prompt = prompt.to(device)
 outputs = model.generate(input_prompt, max_new_tokens=256, do_sample=True)
@@ -71,7 +71,7 @@ messages.extend([
 ])
-prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 input_prompt = prompt.to(device)
 outputs = model.generate(input_prompt, max_new_tokens=256, do_sample=True)

     {"role": "user", "content": "Πες μου αν έχεις συνείδηση."},
 ]
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_tensors="pt")
 input_prompt = prompt.to(device)
 outputs = model.generate(input_prompt, max_new_tokens=256, do_sample=True)
 ])
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_tensors="pt")
 input_prompt = prompt.to(device)
 outputs = model.generate(input_prompt, max_new_tokens=256, do_sample=True)