We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from
Openchat-3.5-0106
with our new reward model
Nexusflow/Starling-RM-34B
and policy optimization method
Fine-Tuning Language Models from Human Preferences (PPO)
.
Harnessing the power of our ranking dataset,
berkeley-nest/Nectar
, our upgraded reward model,
Starling-RM-34B
, and our new reward training and policy tuning pipeline, Starling-LM-7B-beta scores an improved 8.12 in MT Bench with GPT-4 as a judge. Stay tuned for our forthcoming code and paper, which will provide more details on the whole process.
How to use
Install the necessary packages
pip install --upgrade autoawq autoawq-kernels
Example Python code
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Starling-LM-7B-beta-AWQ"
system_message = "You are Starling, incarnated as a powerful AI."# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\<|im_start|>system{system_message}<|im_end|><|im_start|>user{prompt}<|im_end|><|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
Starling-LM-7B-beta-AWQ huggingface.co is an AI model on huggingface.co that provides Starling-LM-7B-beta-AWQ's model effect (), which can be used instantly with this solidrust Starling-LM-7B-beta-AWQ model. huggingface.co supports a free trial of the Starling-LM-7B-beta-AWQ model, and also provides paid use of the Starling-LM-7B-beta-AWQ. Support call Starling-LM-7B-beta-AWQ model through api, including Node.js, Python, http.
Starling-LM-7B-beta-AWQ huggingface.co is an online trial and call api platform, which integrates Starling-LM-7B-beta-AWQ's modeling effects, including api services, and provides a free online trial of Starling-LM-7B-beta-AWQ, you can try Starling-LM-7B-beta-AWQ online for free by clicking the link below.
solidrust Starling-LM-7B-beta-AWQ online free url in huggingface.co:
Starling-LM-7B-beta-AWQ is an open source model from GitHub that offers a free installation service, and any user can find Starling-LM-7B-beta-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of Starling-LM-7B-beta-AWQ install, users can directly use Starling-LM-7B-beta-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Starling-LM-7B-beta-AWQ install url in huggingface.co: