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

Magot V1 Gemma2 8K 9B by grimjim

 »  All LLMs  »  grimjim  »  Magot V1 Gemma2 8K 9B   URL Share it on

  2   
  Merged Model   Autotrain compatible Base model:anthracite-org/magn... Base model:grimjim/kitsunebi-v...   Conversational   Endpoints compatible   Ext 8k   Gemma2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/grimjim/Magot-v1-Gemma2-8k-9B 

Magot V1 Gemma2 8K 9B Benchmarks

MMLU Pro: 37.08
GPQA: 12.86
MUSR: 14.91
BBH: 42.82
IFEval: 29.97 vs 88 (so35)-65.9%
MATH Lvl 5: 4.61
LLME Score: 0.28325
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magot V1 Gemma2 8K 9B (grimjim/Magot-v1-Gemma2-8k-9B)

Magot V1 Gemma2 8K 9B Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is an experiment in using merger as a method of making an Instruct-heavy model less constrained in its text generation. The low weight (0.2) infusion of the Magnum model provided needed variety to text generation. Inherent model safety is still strong due to Instruct base, but narratives are less bounded by positivity. Metadata linkbacks to this model are appreciated when used.
LLM NameMagot V1 Gemma2 8K 9B
Repository 🤗https://huggingface.co/grimjim/Magot-v1-Gemma2-8k-9B 
Base Model(s)  Kitsunebi V1 Gemma2 8K 9B   Magnum V3 9B Customgemma2   grimjim/Kitsunebi-v1-Gemma2-8k-9B   anthracite-org/magnum-v3-9b-customgemma2
Merged ModelYes
Model Size9b
Required VRAM18.6 GB
Updated2025-02-05
Maintainergrimjim
Model Typegemma2
Model Files  1.9 GB: 1-of-10   2.0 GB: 2-of-10   2.0 GB: 3-of-10   2.0 GB: 4-of-10   2.0 GB: 5-of-10   2.0 GB: 6-of-10   2.0 GB: 7-of-10   2.0 GB: 8-of-10   2.0 GB: 9-of-10   0.7 GB: 10-of-10
Context Length8k
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.44.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Magot V1 Gemma2 8K 9B

Best Alternatives
Context / RAM
Downloads
Likes
G2 GSHT 32K32K / 20.4 GB110
Gemma 2 9B It SimPO8K / 18.6 GB29255142
Gemma 2 9B It8K / 18.6 GB388793642
Gemma 2 9B8K / 37.1 GB78866635
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB427634
MT4 Gen5 Gemma 2 9B8K / 20.4 GB1552
SILMA 9B Instruct V1.08K / 18.6 GB1881363
Recoilme Gemma 2 9B V0.38K / 20.4 GB51703
...erge 02012025163610 Gemma 2 9B8K / 20.4 GB461
...erge 02012025163610 Gemma 2 9B8K / 20.4 GB541
Note: green Score (e.g. "73.2") means that the model is better than grimjim/Magot-v1-Gemma2-8k-9B.

Rank the Magot V1 Gemma2 8K 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? 42565 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