ScikitLLM Model EXL2 by probabl-ai

 »  All LLMs  »  probabl-ai  »  ScikitLLM Model EXL2   URL Share it on

ScikitLLM Model EXL2 is an open-source language model by probabl-ai. Features: LLM, VRAM: 3GB, Context: 32K, Quantized, LLM Explorer Score: 0.12.

  3-bit   Conversational   Endpoints compatible   Exl2   Mistral   Quantized   Region:us   Safetensors

ScikitLLM Model EXL2 Benchmarks

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

ScikitLLM Model EXL2 Parameters and Internals

Model Type 
text generation
Additional Notes 
ScikitLLM is finetuned on writing references and code for Scikit-Learn documentation, supporting RAG (three chunks) and using a modified wiki syntax for sources and quotations.
Training Details 
Methodology:
Lower learning rate fine-tuning, based on Mistral-OpenHermes 7B finetune of Mistral 7B.
LLM NameScikitLLM Model EXL2
Repository 🤗https://huggingface.co/probabl-ai/ScikitLLM-Model-exl2 
Required VRAM3 GB
Updated2026-05-19
Maintainerprobabl-ai
Model Typemistral
Model Files  3.0 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<|im_end|>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to ScikitLLM Model EXL2

Best Alternatives
Context / RAM
Downloads
Likes
NemoMix Unleashed EXL2 4bpw1000K / 7.3 GB189
...al Small 2505 Unsloth Bnb 4bit128K / 15 GB275
...iminalComputingConfig Mlx 8Bit32K / 25 GB863
...0.88 07.02 RP DPO Merged 16bit32K / 14.4 GB60
...eZephir Sft Instruct Ead 16bit32K / 14.4 GB560
...cr To Json V1 HQQ 1bit Smashed32K / 1.6 GB50
...cr To Json V1 HQQ 4bit Smashed32K / 4.2 GB50
Chargen V2 8bpw EXL232K / 7.4 GB21
...tral PairRM DPO 8.0bpw H8 EXL232K / 7.4 GB122
HamSter 0.2 8.0bpw H8 EXL232K / 7.4 GB51
Note: green Score (e.g. "73.2") means that the model is better than probabl-ai/ScikitLLM-Model-exl2.

Rank the ScikitLLM Model EXL2 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? 53972 in total.

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