Minitron 8B Derivative
Collection
Derived from the Nemo minitron 8B prune.
β’
7 items
β’
Updated
β’
1
Fatgirl_v2_DPO_8B is a merge of the following models using LazyMergekit:
models:
- model: FourOhFour/Fatgirl_v2_8B+jeiku/Fatgirl_DPO_LoRA
merge_method: passthrough
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jeiku/Fatgirl_v2_DPO_8B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])