Create README.md

README.md

@@ -0,0 +1,37 @@
+---
+license: other
+tags:
+- yi
+- moe
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+---
+
+
+
+* this is 4bit 60B MoE model trained by SFTTrainer based on [cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO]
+* nampdn-ai/tiny-codes sampling about 2000 cases
+* Metrics not Test
+
+  code example
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+model_path = "cloudyu/60B-MoE-Coder-v2"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+        model_path, torch_dtype=torch.bfloat16, device_map='auto',local_files_only=False, load_in_4bit=True
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=1500,repetition_penalty=1.1
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")