Update README.md

README.md

@@ -8,11 +8,11 @@ tags:
 - sft
 - transformers
 - trl
-licence: license
+licence: cc-by-nc-4.0
 pipeline_tag: text-generation
 ---
 
-# Model Card for smol-code-finetuned
+# Model Card for SmolLLM2-135M-Code
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,12 +20,19 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
-from transformers import pipeline
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+model = AutoPeftModelForCausalLM.from_pretrained("ereniko/SmolLLM2-135M-Code")
+tokenizer = AutoTokenizer.from_pretrained("ereniko/SmolLLM2-135M-Code")
+
+def ask(instruction):
+    prompt = f"### Instruction:\n{instruction}\n\n### Input:\n\n### Output:\n"
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7, do_sample=True)
+    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+ask("Write a Python function to reverse a string")
 ```
 
 ## Training procedure