edbeeching HF staff commited on
Commit
f928d4f
·
verified ·
1 Parent(s): 98dc221

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -3
README.md CHANGED
@@ -46,13 +46,32 @@ pipe = pipeline("text-generation", model="open-r1/NormolLM-coder-7b-v02.12", tor
46
 
47
  # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
48
  messages = [
49
- {"role": "user", "content": "Write a python program to calulate the 10th fibonaci number"},
50
  ]
51
  prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
52
  outputs = pipe(prompt, max_new_tokens=8000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
53
  print(outputs[0]["generated_text"])
54
  #<|im_start|>user
55
- #Write a python program to calulate the 10th fibonaci number<|im_end|>
56
  #<|im_start|>assistant
57
  #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...
58
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
  # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
48
  messages = [
49
+ {"role": "user", "content": "Write a python program to calculate the 10th Fibonacci number"},
50
  ]
51
  prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
52
  outputs = pipe(prompt, max_new_tokens=8000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
53
  print(outputs[0]["generated_text"])
54
  #<|im_start|>user
55
+ #Write a python program to calculate the 10th fibonacci number<|im_end|>
56
  #<|im_start|>assistant
57
  #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...
58
+ ```
59
+
60
+
61
+ ## Training procedure
62
+ ### Training hyper-parameters
63
+ The following hyperparameters were used during training:
64
+
65
+ learning_rate: 4.0e-5
66
+ train_batch_size: 2
67
+ seed: 42
68
+ packing: false
69
+ distributed_type: deepspeed-zero-3
70
+ num_devices: 8
71
+ gradient_accumulation_steps: 8
72
+ total_train_batch_size: 16
73
+ optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ lr_scheduler_type: cosine_with_min_lr
75
+ min_lr_rate: 0.1
76
+ lr_scheduler_warmup_ratio: 0.03
77
+ num_epochs: 10.0