HuggingFaceTB
/

SmolLM2-1.7B-Instruct

Text Generation

Transformers

TensorBoard

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

anton-l HF staff

jonathanjordan21 commited on 3 days ago

Commit

bbab860

•

1 Parent(s): 84c598e

fix: typo in python code of summarization example (#10)

Browse files

- fix: typo in python code of summarization example (95ef1a7f0a59b6c1115abadb82c19fb881cf39d2)

Co-authored-by: Jonathan Jordan <jonathanjordan21@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -116,7 +116,7 @@ Hey there! I noticed that the CI isn't passing after your latest commit. Could y
 ```python
 system_prompt_summarize = "Provide a concise, objective summary of the input text in up to three sentences, focusing on key actions and intentions without using second or third person pronouns."
-messages = [{"role": "system", "content": system_prompt_rewrite}, {"role": "user", "content": INSERT_LONG_EMAIL]
 input_text=tokenizer.apply_chat_template(messages, tokenize=False)
 inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)

 ```python
 system_prompt_summarize = "Provide a concise, objective summary of the input text in up to three sentences, focusing on key actions and intentions without using second or third person pronouns."
+messages = [{"role": "system", "content": system_prompt_summarize}, {"role": "user", "content": INSERT_LONG_EMAIL}]
 input_text=tokenizer.apply_chat_template(messages, tokenize=False)
 inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)