Edit model card

Cypher aloobun h2oai1.8B

  • This is an experimental model, Finetuned h2oai/h2o-danube-1.8b-chat, on variety of CoT tasks.
  • The original idea was to use this 1.8B model, divide the dataset based on task specific capabilities, train models and transform them into a mixture of experts.
  • Hyperparameters: adamw with eps of 1e-8, cosine decay w/ 20% warmup, lr=2e-5.

Format:

<|system|></s><|prompt|></s><|answer|>

Benchamrks:

WIP

Example:

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, StoppingCriteria
import torch

class MyStoppingCriteria(StoppingCriteria):
  def __init__(self, target_sequence, prompt):
    self.target_sequence = target_sequence
    self.prompt=prompt

  def __call__(self, input_ids, scores, **kwargs):
    generated_text = tokenizer.decode(input_ids[0])
    generated_text = generated_text.replace(self.prompt,'')
    if self.target_sequence in generated_text:
        return True 
    return False 

  def __len__(self):
    return 1

  def __iter__(self):
    yield self

modelpath="aloobun/Cypher-CoT-1.8B"

model = AutoModelForCausalLM.from_pretrained(
    modelpath,
    torch_dtype=torch.bfloat16,
    device_map="cuda",
    trust_remote_code=True,       
)

tokenizer = AutoTokenizer.from_pretrained(
    modelpath,
    trust_remote_code=True,      
    use_fast=False,
)

prompt = "<|prompt|>James takes a spinning class 3 times a week. He works out for 1.5 hours each class and burns 7 calories per minute. How many calories does he burn per week?</s><|answer|>"
encoded_input = tokenizer(prompt, return_tensors='pt')
input_ids=encoded_input['input_ids'].cuda()
streamer = TextStreamer(tokenizer=tokenizer, skip_prompt=True)
op = model.generate(
    input_ids,
    streamer=streamer,
    pad_token_id=tokenizer.eos_token_id,
    do_sample=True,
    temperature=0.7,
    top_p=0.8,
    max_new_tokens=512,
    stopping_criteria=MyStoppingCriteria("</s>", prompt)
)

Output:

James takes a spinning class 3 times a week, so he spends a total of 3 * 1.5 = 4.5 hours in the class each week. Since there are 60 minutes in an hour, this is equivalent to 4.5 * 60 = 270 minutes. If he burns 7 calories per minute, then he burns a total of 270 * 7 = 1890 calories per week. ####1890 The answer is: 1890

Downloads last month
7
Safetensors
Model size
1.83B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for aloobun/Cypher-CoT-1.8B

Merges
1 model

Dataset used to train aloobun/Cypher-CoT-1.8B