Karasu Instruct11 by aipib

 ยป  All LLMs  ยป  aipib  ยป  Karasu Instruct11   URL Share it on

  Merged Model   Aipib/karasu-moe2   Aipib/tinyllama-moe4   Autotrain compatible   Base model:aipib/karasu-moe2 Base model:aipib/tinyllama-moe...   Conversational   Endpoints compatible   Gguf   Mixtral   Q4   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/aipib/karasu-instruct11 

Karasu Instruct11 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Karasu Instruct11 (aipib/karasu-instruct11)

Karasu Instruct11 Parameters and Internals

Additional Notes 
Merged using LazyMergekit.
LLM NameKarasu Instruct11
Repository ๐Ÿค—https://huggingface.co/aipib/karasu-instruct11 
Base Model(s)  Tinyllama Moe4   Karasu Moe2   aipib/Tinyllama-moe4   aipib/karasu-moe2
Merged ModelYes
Model Size1.9b
Required VRAM3.7 GB
Updated2025-02-22
Maintaineraipib
Model Typemixtral
Model Files  1.1 GB   1.5 GB   1.0 GB: 1-of-4   1.0 GB: 2-of-4   1.0 GB: 3-of-4   0.7 GB: 4-of-4
GGUF QuantizationYes
Quantization Typeq4|gguf|q4_k
Model ArchitectureMixtralForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Karasu Instruct11

Best Alternatives
Context / RAM
Downloads
Likes
TinyJ.O.S.I.E. 2x1.1B 32K Base32K / 7.5 GB201
TinyJ.O.S.I.E. 2x1.1B 32K Base32K / 7.5 GB81
HelpingAI Lite 2x1B2K / 7.5 GB1562
Karasu Moexdareties2K / 3.7 GB920
TinyLlamaHerd 2x1.1B2K / 3.7 GB821
Tiny Llamix 2x1B2K / 7.5 GB950
NeuvilletteBot2K / 3.7 GB1570
Note: green Score (e.g. "73.2") means that the model is better than aipib/karasu-instruct11.

Rank the Karasu Instruct11 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? 43470 in total.

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