Antares 11B V2 by decapoda-research

 »  All LLMs  »  decapoda-research  »  Antares 11B V2   URL Share it on

  Autotrain compatible   Conversational   Dataset:jondurbin/bagel-v0.3   Endpoints compatible   Gguf   Llama   Model-index   Q4   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Antares 11B V2 Benchmarks

Antares 11B V2 (decapoda-research/Antares-11b-v2)

Antares 11B V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
This fine-tune has had zero alignment, safety data, or anything else introduced during training.
Training Details 
Data Sources:
OpenHermes, Platypus, Capybara, Jon Durbin's Bagel v0.3
Methodology:
Trained using QLORA via the Axolotl tool.
Hardware Used:
8x4090s
LLM NameAntares 11B V2
Repository 🤗https://huggingface.co/decapoda-research/Antares-11b-v2 
Base Model(s)  decapod-research/Antares-11b-v1   decapod-research/Antares-11b-v1
Model Size11b
Required VRAM21.5 GB
Updated2025-01-06
Maintainerdecapoda-research
Model Typellama
Model Files  6.1 GB   10.0 GB: 1-of-3   9.8 GB: 2-of-3   1.7 GB: 3-of-3
GGUF QuantizationYes
Quantization Typegguf|q4
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Antares 11B V2

Best Alternatives
Context / RAM
Downloads
Likes
Fimbulvetr 11B V2 Q5 K S GGUF4K / 7.5 GB380
...istral 11B Omni OPA U1k Ver0.732K / 21.4 GB18060
Mistral 11B OP U1k Ver0.732K / 21.4 GB18060
Mistral 11B Omni OP U1k Ver0.532K / 21.4 GB18010
...istral 11B V2 HQQ 4bit Smashed8K / 6 GB170
...mbulvetr 11B V2.6.0bpw H6 EXL24K / 8.2 GB1784
...mbulvetr 11B V2.8.0bpw H8 EXL24K / 10.9 GB177
...mbulvetr 11B V2.4.0bpw H6 EXL24K / 5.6 GB150
...mbulvetr 11B V2.3.0bpw H6 EXL24K / 4.3 GB111
Solstice 11B V1.8.0bpw H8 EXL24K / 10.9 GB130
Note: green Score (e.g. "73.2") means that the model is better than decapoda-research/Antares-11b-v2.

Rank the Antares 11B V2 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? 40923 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227