Kolibri Mistral 0427 2.gguf by kaleinaNyan

 ยป  All LLMs  ยป  kaleinaNyan  ยป  Kolibri Mistral 0427 2.gguf   URL Share it on

  Conversational   En   Endpoints compatible   Gguf   Mistral   Quantized   Region:us   Ru

Kolibri Mistral 0427 2.gguf Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kolibri Mistral 0427 2.gguf (kaleinaNyan/kolibri-mistral-0427-2.gguf)

Kolibri Mistral 0427 2.gguf Parameters and Internals

Model Type 
instruction following
Additional Notes 
I recommend using the model with LMStudio.
Supported Languages 
en (primary), ru (optimized)
Training Details 
Data Sources:
multitude of instruction datasets
Methodology:
optimized for Russian using kolibrify
Input Output 
Input Format:
ChatML template
Performance Tips:
Adding a system prompt will likely improve performance.
Release Notes 
Version:
pre-alpha
Notes:
Initial release optimized for Russian; more details on training procedure and data mix to come in future releases.
LLM NameKolibri Mistral 0427 2.gguf
Repository ๐Ÿค—https://huggingface.co/kaleinaNyan/kolibri-mistral-0427-2.gguf 
Required VRAM4.4 GB
Updated2025-02-22
MaintainerkaleinaNyan
Model Typemistral
Model Files  4.4 GB   7.7 GB
Supported Languagesen ru
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Kolibri Mistral 0427 2.gguf

Best Alternatives
Context / RAM
Downloads
Likes
ComicBot V.2 Gguf32K / 5 GB1520
Phi 2 GGUF0K / 1.2 GB3703103197
Marco O1 GGUF0K / 3 GB75312
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB31035611
Mixtral 8x7B V0.1 GGUF0K / 15.6 GB6904424
Futfut By Zephyr7b Gguf0K / 5.1 GB8312
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB8203301
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB10762138
GOAT Llama3.1 V0.10K / 0.2 GB163
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB96116
Note: green Score (e.g. "73.2") means that the model is better than kaleinaNyan/kolibri-mistral-0427-2.gguf.

Rank the Kolibri Mistral 0427 2.gguf 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