solidrust / L3-8B-Stheno-v3.2-AWQ

huggingface.co
Total runs: 103
24-hour runs: -3
7-day runs: -25
30-day runs: -199
Model's Last Updated: September 03 2024
text-generation

Introduction of L3-8B-Stheno-v3.2-AWQ

Model Details of L3-8B-Stheno-v3.2-AWQ

Sao10K/L3-8B-Stheno-v3.2 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/L3-8B-Stheno-v3.2-AWQ"
system_message = "You are L3-8B-Stheno-v3.2, incarnated as a powerful AI. You were created by Sao10K."

# 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 L3-8B-Stheno-v3.2-AWQ on huggingface.co

103
Total runs
-3
24-hour runs
-10
3-day runs
-25
7-day runs
-199
30-day runs

More Information About L3-8B-Stheno-v3.2-AWQ huggingface.co Model

L3-8B-Stheno-v3.2-AWQ huggingface.co

L3-8B-Stheno-v3.2-AWQ huggingface.co is an AI model on huggingface.co that provides L3-8B-Stheno-v3.2-AWQ's model effect (), which can be used instantly with this solidrust L3-8B-Stheno-v3.2-AWQ model. huggingface.co supports a free trial of the L3-8B-Stheno-v3.2-AWQ model, and also provides paid use of the L3-8B-Stheno-v3.2-AWQ. Support call L3-8B-Stheno-v3.2-AWQ model through api, including Node.js, Python, http.

L3-8B-Stheno-v3.2-AWQ huggingface.co Url

https://huggingface.co/solidrust/L3-8B-Stheno-v3.2-AWQ

solidrust L3-8B-Stheno-v3.2-AWQ online free

L3-8B-Stheno-v3.2-AWQ huggingface.co is an online trial and call api platform, which integrates L3-8B-Stheno-v3.2-AWQ's modeling effects, including api services, and provides a free online trial of L3-8B-Stheno-v3.2-AWQ, you can try L3-8B-Stheno-v3.2-AWQ online for free by clicking the link below.

solidrust L3-8B-Stheno-v3.2-AWQ online free url in huggingface.co:

https://huggingface.co/solidrust/L3-8B-Stheno-v3.2-AWQ

L3-8B-Stheno-v3.2-AWQ install

L3-8B-Stheno-v3.2-AWQ is an open source model from GitHub that offers a free installation service, and any user can find L3-8B-Stheno-v3.2-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of L3-8B-Stheno-v3.2-AWQ install, users can directly use L3-8B-Stheno-v3.2-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

L3-8B-Stheno-v3.2-AWQ install url in huggingface.co:

https://huggingface.co/solidrust/L3-8B-Stheno-v3.2-AWQ

Url of L3-8B-Stheno-v3.2-AWQ

L3-8B-Stheno-v3.2-AWQ huggingface.co Url

Provider of L3-8B-Stheno-v3.2-AWQ huggingface.co

solidrust
ORGANIZATIONS

Other API from solidrust