ZirTech commited on
Commit
83129c1
·
verified ·
1 Parent(s): d91622a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -7
README.md CHANGED
@@ -72,15 +72,29 @@ vllm serve your-username/OmniMath-2B --tensor-parallel-size 1 --max-model-len 40
72
  ```
73
 
74
  ```python
75
- from openai import OpenAI
 
76
 
77
- client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
78
- response = client.chat.completions.create(
79
- model="your-username/OmniMath-2B",
80
- messages=[{"role": "user", "content": "Solve: 3(x - 4) = 9"}],
81
- temperature=0.6,
 
 
82
  )
83
- print(response.choices[0].message.content)
 
 
 
 
 
 
 
 
 
 
 
84
  ```
85
 
86
  ---
 
72
  ```
73
 
74
  ```python
75
+ import torch
76
+ from transformers import AutoModelForCausalLM, AutoTokenizer
77
 
78
+ model_name = "ZirTech/OmniMath-2B"
79
+ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
80
+ model = AutoModelForCausalLM.from_pretrained(
81
+ model_name,
82
+ torch_dtype=torch.float16,
83
+ device_map="auto",
84
+ trust_remote_code=True
85
  )
86
+ model.eval()
87
+
88
+ def ask(question):
89
+ prompt = f"<|im_start|>system\nYou are a helpful math assistant.<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n"
90
+ inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
91
+ outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.0, do_sample=False)
92
+ response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
93
+ if "user" in response:
94
+ response = response.split("user")[0].strip()
95
+ return response
96
+
97
+ print(ask("Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q. Give me the answer."))
98
  ```
99
 
100
  ---