We have retrained our LLama-3-8b fine tune to address behavioral issues in the initial 2.9 dataset. Specifically, Systemchat was causing the model to be
too
reliant on the system prompt. Additionally, it had an occasional quirk that would cause the model to overly reference the system prompt. We also found generation length was at times not sufficient for any given task. We identified the culprit as Ultrachat. Accounting for these concerns, we removed systemchat and ultrachat from the dataset. It is otherwise identical to dolphin-2.9.
Our appreciation for the sponsors of Dolphin 2.9.1:
The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length.
It took 1.5 days on an 8x L40S provided by Crusoe Cloud
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/dolphin-2.9.1-llama-3-8b-AWQ"
system_message = "You are dolphin-2.9.1-llama-3-8b, incarnated as a powerful AI. You were created by cognitivecomputations."# 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.
dolphin-2.9.1-llama-3-8b-AWQ huggingface.co is an AI model on huggingface.co that provides dolphin-2.9.1-llama-3-8b-AWQ's model effect (), which can be used instantly with this solidrust dolphin-2.9.1-llama-3-8b-AWQ model. huggingface.co supports a free trial of the dolphin-2.9.1-llama-3-8b-AWQ model, and also provides paid use of the dolphin-2.9.1-llama-3-8b-AWQ. Support call dolphin-2.9.1-llama-3-8b-AWQ model through api, including Node.js, Python, http.
dolphin-2.9.1-llama-3-8b-AWQ huggingface.co is an online trial and call api platform, which integrates dolphin-2.9.1-llama-3-8b-AWQ's modeling effects, including api services, and provides a free online trial of dolphin-2.9.1-llama-3-8b-AWQ, you can try dolphin-2.9.1-llama-3-8b-AWQ online for free by clicking the link below.
solidrust dolphin-2.9.1-llama-3-8b-AWQ online free url in huggingface.co:
dolphin-2.9.1-llama-3-8b-AWQ is an open source model from GitHub that offers a free installation service, and any user can find dolphin-2.9.1-llama-3-8b-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of dolphin-2.9.1-llama-3-8b-AWQ install, users can directly use dolphin-2.9.1-llama-3-8b-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
dolphin-2.9.1-llama-3-8b-AWQ install url in huggingface.co: