Keyframer2 by bralynn

 ยป  All LLMs  ยป  bralynn  ยป  Keyframer2   URL Share it on

  Autotrain compatible   Base model:bralynn/omnim3 Base model:finetune:bralynn/om...   Conversational   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF ๐Ÿค—: https://huggingface.co/bralynn/keyframer2 

Keyframer2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Keyframer2 (bralynn/keyframer2)
๐ŸŒŸ Advertise your project ๐Ÿš€

Keyframer2 Parameters and Internals

LLM NameKeyframer2
Repository ๐Ÿค—https://huggingface.co/bralynn/keyframer2 
Base Model(s)  bralynn/omnim3   bralynn/omnim3
Model Size3.6b
Required VRAM7.2 GB
Updated2025-07-25
Maintainerbralynn
Model Typellama
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.53.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Keyframer2

Best Alternatives
Context / RAM
Downloads
Likes
ColdBrew Aphid128K / 7.2 GB81
Testing Semifinal128K / 7.3 GB960
...kpoint 1314 DPO Checkpoint 7472K / 7.3 GB120
...ckpoint 564 DPO Checkpoint 2492K / 7.3 GB270
Numfalm Chat Full2K / 7.3 GB80
... ChatMusician Bnb 4bit Smashed2K / 4.2 GB200

Rank the Keyframer2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 50068 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124