solidrust / Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

huggingface.co
Total runs: 261
24-hour runs: -8
7-day runs: -48
30-day runs: -147
Model's Last Updated: September 03 2024
text-generation

Introduction of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

Model Details of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated AWQ

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/Meta-Llama-3.1-8B-Instruct-abliterated-AWQ"
system_message = "You are Meta-Llama-3.1-8B-Instruct-abliterated, incarnated as a powerful AI. You were created by mlabonne."

# 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 Meta-Llama-3.1-8B-Instruct-abliterated-AWQ on huggingface.co

261
Total runs
-8
24-hour runs
-26
3-day runs
-48
7-day runs
-147
30-day runs

More Information About Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co Model

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co is an AI model on huggingface.co that provides Meta-Llama-3.1-8B-Instruct-abliterated-AWQ's model effect (), which can be used instantly with this solidrust Meta-Llama-3.1-8B-Instruct-abliterated-AWQ model. huggingface.co supports a free trial of the Meta-Llama-3.1-8B-Instruct-abliterated-AWQ model, and also provides paid use of the Meta-Llama-3.1-8B-Instruct-abliterated-AWQ. Support call Meta-Llama-3.1-8B-Instruct-abliterated-AWQ model through api, including Node.js, Python, http.

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co Url

https://huggingface.co/solidrust/Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

solidrust Meta-Llama-3.1-8B-Instruct-abliterated-AWQ online free

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co is an online trial and call api platform, which integrates Meta-Llama-3.1-8B-Instruct-abliterated-AWQ's modeling effects, including api services, and provides a free online trial of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ, you can try Meta-Llama-3.1-8B-Instruct-abliterated-AWQ online for free by clicking the link below.

solidrust Meta-Llama-3.1-8B-Instruct-abliterated-AWQ online free url in huggingface.co:

https://huggingface.co/solidrust/Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ install

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ is an open source model from GitHub that offers a free installation service, and any user can find Meta-Llama-3.1-8B-Instruct-abliterated-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ install, users can directly use Meta-Llama-3.1-8B-Instruct-abliterated-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ install url in huggingface.co:

https://huggingface.co/solidrust/Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

Url of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ

Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co Url

Provider of Meta-Llama-3.1-8B-Instruct-abliterated-AWQ huggingface.co

solidrust
ORGANIZATIONS

Other API from solidrust