README.md

metadata

license: apache-2.0
tags:
  - merge

SuperChat-7B

SuperChat-7B is a merge of the following models:

• openchat/openchat-3.5-0106
• OpenPipe/mistral-ft-optimized-1227
• berkeley-nest/Starling-LM-7B-alpha
• jan-hq/supermario-v2

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Yash21/SuperChat-7B"
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"])

To support my efforts please reach out at [email protected]