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

Odin 9B by Delta-Vector

 »  All LLMs  »  Delta-Vector  »  Odin 9B   URL Share it on

  4925   
  Chat Dataset:anthracite-org/c2 logs... Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:anthracite-org/nopm cl... Dataset:epiculous/synthrp-gens... Dataset:epiculous/synthstruct-... Dataset:lodrick-the-lafted/kal... Dataset:neweden/claude-instruc...   Gemma2   Instruct   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Odin-9B 

Odin 9B Benchmarks

MMLU Pro: 33.85
GPQA: 12.19
MUSR: 17.56
BBH: 34.83
IFEval: 36.92 vs 88 (so35)-58%
MATH Lvl 5: 14.12
LLME Score: 0.3445
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Odin 9B (Delta-Vector/Odin-9B)

Odin 9B Parameters and Internals

Model Type 
text generation, chat
Additional Notes 
A checkpoint of an unreleased model with similar configurations to Tor-8B and Darkens-8B. This version focuses on eliminating excessive suggestiveness found in Magnum models.
Supported Languages 
En (proficient)
Training Details 
Data Sources:
NewEden/Claude-Instruct-5K, anthracite-org/kalo-opus-instruct-22k-no-refusal, Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned, lodrick-the-lafted/kalo-opus-instruct-3k-filtered, anthracite-org/nopm_claude_writing_fixed, Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned, anthracite-org/kalo_opus_misc_240827, anthracite-org/kalo_misc_part2
Methodology:
The model was fine-tuned for creative writing and roleplay tasks.
Context Length:
8192
Hardware Used:
8 x NVIDIA H100 GPUs
Input Output 
Input Format:
ChatML formatting
Accepted Modalities:
text
Performance Tips:
Use a minp value of 0.02 to prevent poor performance
LLM NameOdin 9B
Repository 🤗https://huggingface.co/Delta-Vector/Odin-9B 
Model Size9b
Required VRAM18.6 GB
Updated2025-02-05
MaintainerDelta-Vector
Model Typegemma2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.7 GB: 4-of-4
Model ArchitectureGemma2ForCausalLM
Licenseagpl-3.0
Context Length8192
Model Max Length8192
Transformers Version4.45.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Odin 9B

Best Alternatives
Context / RAM
Downloads
Likes
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB427634
SILMA 9B Instruct V1.08K / 18.6 GB1881363
Magnum V4 9B8K / 18.6 GB498317
Gemma Evo 10B8K / 20.4 GB224
Gigantes V2 Gemma2 9B It8K / 18.6 GB70
Gigantes V1 Gemma2 9B It8K / 18.6 GB81
Gigantes V3 Gemma2 9B It8K / 18.6 GB50
...B IT Simpo Infinity Preference8K / 18.6 GB506117
...ma2 9B Cpt Sea Lionv3 Instruct8K / 18.6 GB30697
FuseChat Gemma 2 9B Instruct8K / 18.6 GB1225
Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Odin-9B.

Rank the Odin 9B 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? 42577 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 v20241227
  Support LLM Explorer