File size: 2,216 Bytes
f3e39d1 1948215 f3e39d1 1948215 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
---
library_name: transformers
license: apache-2.0
datasets:
- kaist-ai/CoT-Collection
tags:
- finetune
- gpt4
- synthetic data
- custom_code
- h2oai
---
- This is an experimental model, Finetuned [h2oai/h2o-danube-1.8b-chat](https://huggingface.co/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|>Avery opens a flower shop. She ties 8 bunches of flowers with 9 flowers in each bunch. How many bunches would she have if she put 12 flowers in each bunch instead?</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:
|