GraySoft
Download guIDE →
Model Comparison

lmg-anon/vntl-llama3-8b-v2-ggufvsthebloke/mixtral-8x7b-instruct-v0.1-gguf

Side-by-side comparison of lmg-anon/vntl-llama3-8b-v2-gguf and thebloke/mixtral-8x7b-instruct-v0.1-gguf: downloads, license, context length, tasks, and benchmarks.

lmg-anon/vntl-llama3-8b-v2-gguf

lmg-anon · translation

This is a LLaMA 3 Youko qlora fine-tune, created using a new version of the VNTL dataset. The purpose of this fine-tune is to improve performance of LLMs at translating Japanese visual novels to English. Unlike the previous version, this one doesn't includes the "chat mode".

thebloke/mixtral-8x7b-instruct-v0.1-gguf

TheBloke · —

Side-by-side Specifications

lmg-anon/vntl-llama3-8b-v2-ggufthebloke/mixtral-8x7b-instruct-v0.1-gguf
Authorlmg-anonTheBloke
Pipeline Tasktranslation—
Library—transformers
Downloads1,522,50320,561
Likes13655
LicenseUnknownUnknown
Context Length——
Created2025-01-022023-12-11
Last Modified2025-01-022023-12-14
Tags
gguftranslationjaendataset:lmg-anon/VNTL-v5-1kbase_model:rinna/llama-3-youko-8bbase_model:quantized:rinna/llama-3-youko-8blicense:llama3endpoints_compatibleregion:us
transformersggufmixtralfritdeesenbase_model:mistralai/Mixtral-8x7B-Instruct-v0.1base_model:quantized:mistralai/Mixtral-8x7B-Instruct-v0.1

View full details: lmg-anon/vntl-llama3-8b-v2-gguf · thebloke/mixtral-8x7b-instruct-v0.1-gguf