Model92 by C10X

 ยป  All LLMs  ยป  C10X  ยป  Model92   URL Share it on

  4bit   Autotrain compatible   En   Endpoints compatible   Pytorch   Quantized   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF ๐Ÿค—: https://huggingface.co/C10X/model92 

Model92 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Model92 (C10X/model92)

Model92 Parameters and Internals

LLM NameModel92
Repository ๐Ÿค—https://huggingface.co/C10X/model92 
Base Model(s)  unsloth/qwen2.5-3b-bnb-4bit   unsloth/qwen2.5-3b-bnb-4bit
Model Size3b
Required VRAM6.8 GB
Updated2024-12-11
MaintainerC10X
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   1.8 GB: 2-of-2   5.0 GB: 1-of-2   1.8 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Model92

Best Alternatives
Context / RAM
Downloads
Likes
QwQ LCoT 3B Instruct32K / 6.2 GB1276
Qwen2.5 3B Instruct Bnb 4bit32K / 2 GB84625
Thinik Orpo V2.032K / 6.2 GB110
Saba1.5 Pro 3B128K / 5.8 GB561
Qwen2.5 3B Instruct32K / 6.2 GB210716116
Qwen2.5 3B32K / 6.2 GB10147243
Calme 3.3 Instruct 3B32K / 11 GB88282
Qwen2.5 Coder 3B Instruct32K / 6.2 GB6776422
Calme 3.2 Instruct 3B32K / 11 GB28880
Calme 3.1 Baguette 3B32K / 6.2 GB28241
Note: green Score (e.g. "73.2") means that the model is better than C10X/model92.

Rank the Model92 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217