Create README.md

README.md

@@ -0,0 +1,35 @@
+---
+license: llama3
+---
+finetuned by simplescaling/s1K
+
+example code
+
+```python
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/S1-Llama-3.2-3Bx4-MoE"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, trust_remote_code=True,device_map='mps'
+)
+print(model)
+print(model.lm_head.weight)
+
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("mps")
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")
+
+
+```