You can deploy this model and start earning money today!

RichardErkhov/
saltlux_-_luxia-21.4b-alignment-v1.0-gguf

Name: saltlux_-_luxia-21.4b-alignment-v1.0-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

luxia-21.4b-alignment-v1.0 - GGUF

Model creator: https://huggingface.co/saltlux/
Original model: https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0/

Name	Quant method	Size
luxia-21.4b-alignment-v1.0.Q2_K.gguf	Q2_K	7.56GB
luxia-21.4b-alignment-v1.0.Q3_K_S.gguf	Q3_K_S	8.78GB
luxia-21.4b-alignment-v1.0.Q3_K.gguf	Q3_K	9.75GB
luxia-21.4b-alignment-v1.0.Q3_K_M.gguf	Q3_K_M	9.75GB
luxia-21.4b-alignment-v1.0.Q3_K_L.gguf	Q3_K_L	10.59GB
luxia-21.4b-alignment-v1.0.IQ4_XS.gguf	IQ4_XS	10.89GB
luxia-21.4b-alignment-v1.0.Q4_0.gguf	Q4_0	11.36GB
luxia-21.4b-alignment-v1.0.IQ4_NL.gguf	IQ4_NL	11.47GB
luxia-21.4b-alignment-v1.0.Q4_K_S.gguf	Q4_K_S	11.44GB
luxia-21.4b-alignment-v1.0.Q4_K.gguf	Q4_K	12.03GB
luxia-21.4b-alignment-v1.0.Q4_K_M.gguf	Q4_K_M	12.03GB
luxia-21.4b-alignment-v1.0.Q4_1.gguf	Q4_1	12.58GB
luxia-21.4b-alignment-v1.0.Q5_0.gguf	Q5_0	13.79GB
luxia-21.4b-alignment-v1.0.Q5_K_S.gguf	Q5_K_S	13.79GB
luxia-21.4b-alignment-v1.0.Q5_K.gguf	Q5_K	14.13GB
luxia-21.4b-alignment-v1.0.Q5_K_M.gguf	Q5_K_M	14.13GB
luxia-21.4b-alignment-v1.0.Q5_1.gguf	Q5_1	15.0GB
luxia-21.4b-alignment-v1.0.Q6_K.gguf	Q6_K	16.37GB
luxia-21.4b-alignment-v1.0.Q8_0.gguf	Q8_0	21.2GB

Original model description:

license: apache-2.0 language:

Introduction

We introduce luxia-21.4b-alignment-v1.0, an instruction-tuned and alignment model based on luxia-21.4b. Please refer to the evaluation results table for details.

Instruction Fine-tuning Strategy

We utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO)

Data Contamination Test Results

Results will be updated soon.

Evaluation Results

Results will be updated soon.

Usage Instructions

How to use

python

# pip install transformers==4.35.2
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("saltlux/luxia-21.4b-alignment-v0.1")
model = AutoModelForCausalLM.from_pretrained(
    "saltlux/luxia-21.4b-alignment-v0.1",
    device_map="auto",
    torch_dtype=torch.float16,
)

License

saltlux/luxia-21.4b-alignment-v1.0: apache-2.0

Contact Us

Any questions and suggestions are welcomed at the discussion tab.

RichardErkhov/saltlux_-_luxia-21.4b-alignment-v1.0-gguf