Model Comparison

lmg-anon/vntl-llama3-8b-v2-ggufvsmradermacher/mn-12b-mag-mell-r1-gguf

Side-by-side comparison of lmg-anon/vntl-llama3-8b-v2-gguf and mradermacher/mn-12b-mag-mell-r1-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".

mradermacher/mn-12b-mag-mell-r1-gguf

mradermacher · —

## About static quants of https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1 weighted/imatrix quants are available at https://huggingface.co/mradermacher/MN-12B-Mag-Mell-R1-i1-GGUF

Side-by-side Specifications

	lmg-anon/vntl-llama3-8b-v2-gguf	mradermacher/mn-12b-mag-mell-r1-gguf
Author	lmg-anon	mradermacher
Pipeline Task	translation	—
Library	—	transformers
Downloads	1,522,503	50,033
Likes	13	47
License	Unknown	Unknown
Context Length	—	—
Created	2025-01-02	2024-09-16
Last Modified	2025-01-02	2024-09-17
Tags	gguftranslationjaendataset:lmg-anon/VNTL-v5-1kbase_model:rinna/llama-3-youko-8bbase_model:quantized:rinna/llama-3-youko-8blicense:llama3endpoints_compatibleregion:us	transformersggufmergekitmergeenbase_model:inflatebot/MN-12B-Mag-Mell-R1base_model:quantized:inflatebot/MN-12B-Mag-Mell-R1endpoints_compatibleregion:usconversational

View full details: lmg-anon/vntl-llama3-8b-v2-gguf · mradermacher/mn-12b-mag-mell-r1-gguf