solidrust / Kilo-2x8B-AWQ

huggingface.co
Total runs: 23
24-hour runs: -1
7-day runs: -1
30-day runs: 6
Model's Last Updated: September 03 2024
text-generation

Introduction of Kilo-2x8B-AWQ

Model Details of Kilo-2x8B-AWQ

Alsebay/Kilo-2x8B AWQ

Model Summary

MoE model of 2 Llama-3 models:

  • vicgalle/Roleplay-Llama-3-8B
  • Sao10K/L3-Solana-8B-v1
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/Kilo-2x8B-AWQ"
system_message = "You are Kilo-2x8B, incarnated as a powerful AI. You were created by Alsebay."

# 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 Kilo-2x8B-AWQ on huggingface.co

23
Total runs
-1
24-hour runs
-3
3-day runs
-1
7-day runs
6
30-day runs

More Information About Kilo-2x8B-AWQ huggingface.co Model

Kilo-2x8B-AWQ huggingface.co

Kilo-2x8B-AWQ huggingface.co is an AI model on huggingface.co that provides Kilo-2x8B-AWQ's model effect (), which can be used instantly with this solidrust Kilo-2x8B-AWQ model. huggingface.co supports a free trial of the Kilo-2x8B-AWQ model, and also provides paid use of the Kilo-2x8B-AWQ. Support call Kilo-2x8B-AWQ model through api, including Node.js, Python, http.

Kilo-2x8B-AWQ huggingface.co Url

https://huggingface.co/solidrust/Kilo-2x8B-AWQ

solidrust Kilo-2x8B-AWQ online free

Kilo-2x8B-AWQ huggingface.co is an online trial and call api platform, which integrates Kilo-2x8B-AWQ's modeling effects, including api services, and provides a free online trial of Kilo-2x8B-AWQ, you can try Kilo-2x8B-AWQ online for free by clicking the link below.

solidrust Kilo-2x8B-AWQ online free url in huggingface.co:

https://huggingface.co/solidrust/Kilo-2x8B-AWQ

Kilo-2x8B-AWQ install

Kilo-2x8B-AWQ is an open source model from GitHub that offers a free installation service, and any user can find Kilo-2x8B-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of Kilo-2x8B-AWQ install, users can directly use Kilo-2x8B-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Kilo-2x8B-AWQ install url in huggingface.co:

https://huggingface.co/solidrust/Kilo-2x8B-AWQ

Url of Kilo-2x8B-AWQ

Kilo-2x8B-AWQ huggingface.co Url

Provider of Kilo-2x8B-AWQ huggingface.co

solidrust
ORGANIZATIONS

Other API from solidrust