solidrust / LuminariX-8B-AWQ

huggingface.co
Total runs: 23
24-hour runs: 0
7-day runs: 4
30-day runs: 10
Model's Last Updated: September 03 2024
text-generation

Introduction of LuminariX-8B-AWQ

Model Details of LuminariX-8B-AWQ

bunnycore/LuminariX-8B AWQ

LuminariX-8B is a merge of the following models using mergekit :

🧩 Configuration
models:
  - model: Orenguteng/Llama-3-8B-Lexi-Uncensored
  - model: Weyaxi/Einstein-v6.1-Llama3-8B
  - model: cognitivecomputations/dolphin-2.9-llama3-8b-256k
merge_method: model_stock
base_model: cognitivecomputations/dolphin-2.9-llama3-8b-256k
dtype: bfloat16
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/LuminariX-8B-AWQ"
system_message = "You are LuminariX-8B, incarnated as a powerful AI. You were created by bunnycore."

# 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.

It is supported by:

Runs of solidrust LuminariX-8B-AWQ on huggingface.co

23
Total runs
0
24-hour runs
4
3-day runs
4
7-day runs
10
30-day runs

More Information About LuminariX-8B-AWQ huggingface.co Model

More LuminariX-8B-AWQ license Visit here:

https://choosealicense.com/licenses/apache-2.0

LuminariX-8B-AWQ huggingface.co

LuminariX-8B-AWQ huggingface.co is an AI model on huggingface.co that provides LuminariX-8B-AWQ's model effect (), which can be used instantly with this solidrust LuminariX-8B-AWQ model. huggingface.co supports a free trial of the LuminariX-8B-AWQ model, and also provides paid use of the LuminariX-8B-AWQ. Support call LuminariX-8B-AWQ model through api, including Node.js, Python, http.

LuminariX-8B-AWQ huggingface.co Url

https://huggingface.co/solidrust/LuminariX-8B-AWQ

solidrust LuminariX-8B-AWQ online free

LuminariX-8B-AWQ huggingface.co is an online trial and call api platform, which integrates LuminariX-8B-AWQ's modeling effects, including api services, and provides a free online trial of LuminariX-8B-AWQ, you can try LuminariX-8B-AWQ online for free by clicking the link below.

solidrust LuminariX-8B-AWQ online free url in huggingface.co:

https://huggingface.co/solidrust/LuminariX-8B-AWQ

LuminariX-8B-AWQ install

LuminariX-8B-AWQ is an open source model from GitHub that offers a free installation service, and any user can find LuminariX-8B-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of LuminariX-8B-AWQ install, users can directly use LuminariX-8B-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LuminariX-8B-AWQ install url in huggingface.co:

https://huggingface.co/solidrust/LuminariX-8B-AWQ

Url of LuminariX-8B-AWQ

LuminariX-8B-AWQ huggingface.co Url

Provider of LuminariX-8B-AWQ huggingface.co

solidrust
ORGANIZATIONS

Other API from solidrust