LLM EXPLORER 59,962 MODELS INDEXED

Bagel DPO 8x7b V0.2 GGUF by TheBloke

By TheBloke · 222 downloads
HF Repo ↗ Copy URL

Bagel DPO 8x7b V0.2 GGUF is an open-source language model by TheBloke. Features: 1m LLM, VRAM: 17.3GB, License: apache-2.0, MoE, Quantized, LLM Explorer Score: 0.11.

Base model:jondurbin/bagel-dpo... Base model:quantized:jondurbin...   Conversational   Dataset:ai2 arc Dataset:allenai/ultrafeedback ...   Dataset:boolq   Dataset:cais/mmlu   Dataset:cakiki/rosetta-code   Dataset:codeparrot/apps   Dataset:datasets/winogrande   Dataset:drop   Dataset:facebook/belebele   Dataset:intel/orca dpo pairs Dataset:jondurbin/airoboros-3.... Dataset:jondurbin/cinematika-v... Dataset:jondurbin/truthy-dpo-v...   Dataset:julielab/emobank   Dataset:kingbri/pippa-sharegpt   Dataset:ldjnr/capybara   Dataset:lmsys/lmsys-chat-1m Dataset:migtissera/synthia-v1.... Dataset:muennighoff/natural-in...   Dataset:nvidia/helpsteer   Dataset:open-orca/slimorca   Dataset:openbookqa   Dataset:piqa   Dataset:spider   Dataset:squad v2 Dataset:squish42/bluemoon-fand...   Dataset:tiger-lab/mathinstruct Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth...   Gguf   Mixtral   Moe   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/bagel-dpo-8x7b-v0.2-GGUF 

Bagel DPO 8x7b V0.2 GGUF Parameters and Internals

Model Type 
mixtral
Additional Notes 
An experimental fine-tune of mixtral-8x7b-v0.1 using bagel. The default system prompt is: 'You are a helpful, unbiased, uncensored assistant.'
Training Details 
Data Sources:
ai2_arc, jondurbin/airoboros-3.2, codeparrot/apps, facebook/belebele, boolq, jondurbin/cinematika-v0.1, drop, lmsys/lmsys-chat-1m, TIGER-Lab/MathInstruct, cais/mmlu, Muennighoff/natural-instructions, openbookqa, piqa, Vezora/Tested-22k-Python-Alpaca, cakiki/rosetta-code, Open-Orca/SlimOrca, spider, squad_v2, migtissera/Synthia-v1.3, datasets/winogrande, nvidia/HelpSteer, Intel/orca_dpo_pairs, unalignment/toxic-dpo-v0.1, jondurbin/truthy-dpo-v0.1, allenai/ultrafeedback_binarized_cleaned, Squish42/bluemoon-fandom-1-1-rp-cleaned, LDJnr/Capybara, JULIELab/EmoBank, kingbri/PIPPA-shareGPT
Methodology:
Experimental fine-tune of mixtral-8x7b-v0.1 using both SFT and DPO phases.
Input Output 
Input Format:
Instruction format: Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
LLM NameBagel DPO 8x7b V0.2 GGUF
Repository 🤗https://huggingface.co/TheBloke/bagel-dpo-8x7b-v0.2-GGUF 
Model NameBagel DPO 8X7B V0.2
Model CreatorJon Durbin
Base Model(s)  jondurbin/bagel-dpo-8x7b-v0.2   jondurbin/bagel-dpo-8x7b-v0.2
Model Size1m
Required VRAM17.3 GB
Updated2026-07-30
MaintainerTheBloke
Model Typemixtral
Model Files  17.3 GB   22.5 GB   26.4 GB   28.4 GB   32.2 GB   33.2 GB   38.4 GB   49.6 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Bagel DPO 8x7b V0.2 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Triangulum 1B GGUF0K / 0.8 GB431
Llama Deepsync 1B GGUF0K / 0.8 GB103
... SmolTalk 3.2 1B Instruct GGUF0K / 0.8 GB1074
Mergekit Slerp Ozbsicw GGUF0K / 2.5 GB6260
Tinyllama 1B Alpaca Gguf0K / 0.7 GB300
Prem 1B Chat GGUF0K / 0.7 GB261
Bagel 8x7b V0.2 GGUF0K / 15.6 GB1608
...inyllama 2 1B Miniguanaco GGUF0K / 0.5 GB198217
Medical0K / 0 GB150
Llama 3.2 1B Creative Lora0K / 0 GB04
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/bagel-dpo-8x7b-v0.2-GGUF.