Trinity 2 Codestral 22B V0.2 by migtissera

 ยป  All LLMs  ยป  migtissera  ยป  Trinity 2 Codestral 22B V0.2   URL Share it on

Base model:finetune:mistralai/... Base model:mistralai/codestral...   Generated from trainer   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Trinity 2 Codestral 22B V0.2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Trinity 2 Codestral 22B V0.2 (migtissera/Trinity-2-Codestral-22B-v0.2)

Trinity 2 Codestral 22B V0.2 Parameters and Internals

Model Type 
coding specific LLM
Additional Notes 
Trinity is a coding specific Large Language Model series.
Input Output 
Input Format:
ChatML
LLM NameTrinity 2 Codestral 22B V0.2
Repository ๐Ÿค—https://huggingface.co/migtissera/Trinity-2-Codestral-22B-v0.2 
Base Model(s)  mistralai/Codestral-22B-v0.1   mistralai/Codestral-22B-v0.1
Model Size22b
Required VRAM44.7 GB
Updated2025-02-18
Maintainermigtissera
Model Typemistral
Model Files  4.9 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   4.9 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   4.9 GB: 7-of-9   5.0 GB: 8-of-9   5.0 GB: 9-of-9   0.0 GB
Model ArchitectureMistralForCausalLM
LicenseMNPL-0.1
Context Length32768
Model Max Length32768
Transformers Version4.43.4
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_text|>
Vocabulary Size32771
Torch Data Typebfloat16

Best Alternatives to Trinity 2 Codestral 22B V0.2

Best Alternatives
Context / RAM
Downloads
Likes
MS Schisandra 22B V0.2128K / 44.7 GB319
...ntheon RP Pure 1.6.2 22B Small128K / 44.7 GB4127
MS Meadowlark 22B128K / 44.7 GB13013
... V4x1.6.2RP Cydonia VXXX 22B 8128K / 44.7 GB3005
... V4x1.6.2RP Cydonia VXXX 22B 6128K / 44.7 GB2822
Beeper King 22B128K / 44.7 GB277
MS Moingooistral 2409 22B128K / 44.7 GB400
MS Dampf 2409 22B128K / 44.7 GB360
MS A Coolyte 2409 22B128K / 44.7 GB340
MS Fujin 2409 22B128K / 44.7 GB330
Note: green Score (e.g. "73.2") means that the model is better than migtissera/Trinity-2-Codestral-22B-v0.2.

Rank the Trinity 2 Codestral 22B V0.2 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? 43267 in total.

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