You can deploy this model and start earning money today!

RichardErkhov/
4yo1_-_llama3-pre1-pre2-lora3-mergkit-base22-gguf

Name: 4yo1_-_llama3-pre1-pre2-lora3-mergkit-base22-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3-pre1-pre2-lora3-mergkit-base22 - GGUF

Model creator: https://huggingface.co/4yo1/
Original model: https://huggingface.co/4yo1/llama3-pre1-pre2-lora3-mergkit-base22/

Name	Quant method	Size
llama3-pre1-pre2-lora3-mergkit-base22.Q2_K.gguf	Q2_K	2.96GB
llama3-pre1-pre2-lora3-mergkit-base22.IQ3_XS.gguf	IQ3_XS	3.28GB
llama3-pre1-pre2-lora3-mergkit-base22.IQ3_S.gguf	IQ3_S	3.43GB
llama3-pre1-pre2-lora3-mergkit-base22.Q3_K_S.gguf	Q3_K_S	3.41GB
llama3-pre1-pre2-lora3-mergkit-base22.IQ3_M.gguf	IQ3_M	3.52GB
llama3-pre1-pre2-lora3-mergkit-base22.Q3_K.gguf	Q3_K	3.74GB
llama3-pre1-pre2-lora3-mergkit-base22.Q3_K_M.gguf	Q3_K_M	3.74GB
llama3-pre1-pre2-lora3-mergkit-base22.Q3_K_L.gguf	Q3_K_L	4.03GB
llama3-pre1-pre2-lora3-mergkit-base22.IQ4_XS.gguf	IQ4_XS	4.18GB
llama3-pre1-pre2-lora3-mergkit-base22.Q4_0.gguf	Q4_0	4.34GB
llama3-pre1-pre2-lora3-mergkit-base22.IQ4_NL.gguf	IQ4_NL	4.38GB
llama3-pre1-pre2-lora3-mergkit-base22.Q4_K_S.gguf	Q4_K_S	4.37GB
llama3-pre1-pre2-lora3-mergkit-base22.Q4_K.gguf	Q4_K	4.58GB
llama3-pre1-pre2-lora3-mergkit-base22.Q4_K_M.gguf	Q4_K_M	4.58GB
llama3-pre1-pre2-lora3-mergkit-base22.Q4_1.gguf	Q4_1	4.78GB
llama3-pre1-pre2-lora3-mergkit-base22.Q5_0.gguf	Q5_0	5.21GB
llama3-pre1-pre2-lora3-mergkit-base22.Q5_K_S.gguf	Q5_K_S	5.21GB
llama3-pre1-pre2-lora3-mergkit-base22.Q5_K.gguf	Q5_K	5.34GB
llama3-pre1-pre2-lora3-mergkit-base22.Q5_K_M.gguf	Q5_K_M	5.34GB
llama3-pre1-pre2-lora3-mergkit-base22.Q5_1.gguf	Q5_1	5.65GB
llama3-pre1-pre2-lora3-mergkit-base22.Q6_K.gguf	Q6_K	6.14GB
llama3-pre1-pre2-lora3-mergkit-base22.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers language:

en
ko pipeline_tag: translation license: mit datasets:
pre

Model Card for Model ID

Model Details

Model Card: 4yo1/llama3-pre1-pre2-lora3-mergkit-base2 with Fine-Tuning Model Overview Model Name: 4yo1/llama3-pre1-pre2-lora3-mergkit-base2

Model Type: Transformer-based Language Model

Model Size: 8 billion parameters

by: 4yo1

Languages: English and Korean

how to use - sample code

python

from transformers import AutoConfig, AutoModel, AutoTokenizer

config = AutoConfig.from_pretrained("4yo1/4yo1/llama3-pre1-pre2-lora3-mergkit-base2")
model = AutoModel.from_pretrained("4yo1/llama3-pre1-pre2-lora3-mergkit-base2")
tokenizer = AutoTokenizer.from_pretrained("4yo1/llama3-pre1-pre2-lora3-mergkit-base2")

datasets:

140kgpt

license: mit

RichardErkhov/4yo1_-_llama3-pre1-pre2-lora3-mergkit-base22-gguf

Original model description:

Model Card for Model ID

Model Details

how to use - sample code

RichardErkhov/
4yo1_-_llama3-pre1-pre2-lora3-mergkit-base22-gguf