LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Bagel 8x7b V0.2 3.5bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Bagel 8x7b V0.2 3.5bpw H6 EXL2   URL Share it on

  4   
  Autotrain compatible   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...   Endpoints compatible   Exl2   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/bagel-8x7b-v0.2-3.5bpw-h6-exl2 

Bagel 8x7b V0.2 3.5bpw H6 EXL2 Benchmarks

LLME Score: 0.12988
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bagel 8x7b V0.2 3.5bpw H6 EXL2 (LoneStriker/bagel-8x7b-v0.2-3.5bpw-h6-exl2)
🌟 Advertise your project 🚀

Bagel 8x7b V0.2 3.5bpw H6 EXL2 Parameters and Internals

Additional Notes 
The fine-tuning includes OpenAI generated data, so users should consider potential legal implications and seek legal advice if needed.
Training Details 
Data Sources:
ai2_arc, airoboros, apps, belebele, bluemoon, boolq, capybara, cinematika, drop, emobank, gutenberg, lmsys_chat_1m, mathinstruct, mmlu, natural_instructions, openbookqa, pippa, piqa, python_alpaca, rosetta_code, slimorca, spider, squad_v2, synthia, winogrande
Methodology:
Fine-tuning using 4 prompt formats: vicuna, llama-2, alpaca, and chat-ml.
Training Time:
4 days, 15 hours, 6 minutes and 42 seconds
Hardware Used:
8x a6000 instance
LLM NameBagel 8x7b V0.2 3.5bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/bagel-8x7b-v0.2-3.5bpw-h6-exl2 
Model Size1m
Required VRAM20.7 GB
Updated2025-09-23
MaintainerLoneStriker
Model Typemixtral
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   3.5 GB: 3-of-3
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Bagel 8x7b V0.2 3.5bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...l DPO 8x7b V0.2 3.5bpw H6 EXL232K / 20.7 GB42
...l DPO 8x7b V0.2 6.0bpw H6 EXL232K / 35.3 GB51
TinyMistral 6x248M Instruct32K / 4 GB64610
TinyMistral 6x248M32K / 4 GB64514
...ama Llama Dolphin Laser 1B MoE4K / 6.8 GB81
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/bagel-8x7b-v0.2-3.5bpw-h6-exl2.

Rank the Bagel 8x7b V0.2 3.5bpw H6 EXL2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51534 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer