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

Anima 7B 100K by lyogavin

 »  All LLMs  »  lyogavin  »  Anima 7B 100K   URL Share it on

  1040   

Anima 7B 100K is an open-source language model by lyogavin. Features: 7b LLM, VRAM: 13.5GB, Context: 32K, License: apache-2.0, HF Score: 43, LLM Explorer Score: 0.14, Arc: 46.6, HellaSwag: 72.3, MMLU: 33.4, TruthfulQA: 37.8, WinoGrande: 67.1, GSM8K: 0.7.

  100k   7b   Custom code   En   Endpoints compatible   Llama   Llama2   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/lyogavin/Anima-7B-100K 

Anima 7B 100K Benchmarks

ARC: 46.59 vs 96.7 (so35)-51.8%
HellaSwag: 72.28 vs 95.3 (gpt4)-24.2%
MMLU: 33.4 vs 88.3 (so35)-62.2%
TruthfulQA: 37.84 vs 59 (gpt4)-35.9%
WinoGrande: 67.09 vs 87.5 (gpt4)-23.3%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
LLME Score: 0.14267
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Anima 7B 100K (lyogavin/Anima-7B-100K)
🌟 Advertise your project 🚀

Anima 7B 100K Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Long context input processing, QA systems for large token inputs
Primary Use Cases:
Handling long input tokens efficiently due to memory optimizations
Limitations:
Limited information on performance benchmarks for 100k tokens
Additional Notes 
The model uniquely supports a 100k token input length, allowing for extensive input handling, contrasting typical language models.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
Long QA datasets
Data Volume:
30k to 100k token length datasets
Methodology:
Training on curated long QA datasets, and making memory optimizations for 100k tokens
Context Length:
100000
Model Architecture:
Extension and optimization based on Llama2 7B
Input Output 
Input Format:
Long-form prompt inputs with potentially 100K token length
Accepted Modalities:
text
Output Format:
Textual generated responses
Performance Tips:
Avoid using high memory accelerators if OOM is encountered, adjust cache usage settings
LLM NameAnima 7B 100K
Repository 🤗https://huggingface.co/lyogavin/Anima-7B-100K 
Model Size7b
Required VRAM13.5 GB
Updated2025-12-07
Maintainerlyogavin
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Anima 7B 100K

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
1621024K / 16.1 GB600
1571024K / 16.1 GB1010
1181024K / 16.1 GB150
A5.41024K / 16.1 GB120
A6 L1024K / 16.1 GB2010
A3.41024K / 16.1 GB130
A2.41024K / 16.1 GB120
M1024K / 16.1 GB1270
2 Very Sci Fi1024K / 16.1 GB3170
Note: green Score (e.g. "73.2") means that the model is better than lyogavin/Anima-7B-100K.

Rank the Anima 7B 100K 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? 52509 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer