Update README.md

README.md

@@ -4,14 +4,41 @@ language:
 - fr
 - en
 - zh
+widget:
+- text: "<s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]"
 ---
-Merging stuff to make a potato. Idk about it might delete later. 
+Merging stuff to make a potato. Idk about it, might delete later. 
 
 Merge of MiniMerlin via Task arithmetic using mergekit. 
 There was no goal except merging. Interest in the outcome tho. I might need to fine-tune it more.
 
 FT on more french data (Merlin). 
 
-Actually I think it's the best french model of that size. Just try it out. It's definetely not perfect but it do the job for a 3B model. 
+Je pense qu'il s'agit du meilleur model français en 3B. Essayez le.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "teilomillet/Potato-3B",
+    revision="0.1",
+    return_dict=True,
+    torch_dtype=torch.bfloat16,
+    device_map='auto'
+)
+
+tokenizer = AutoTokenizer.from_pretrained("teilomillet/Potato-3B")
+tokenizer.pad_token = tokenizer.eos_token
+
+text = "[|User|] Comment faire un bon plat ? </s>[|Assistant|]"
+inputs = tokenizer(text, return_tensors="pt").to(0)
+
+outputs = model.generate(**inputs, max_new_tokens=800)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```
+
+
 
 #merge