Autotrain compatible Conversational Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/shuttleai/shuttle-2.5-mini
Shuttle 2.5 Mini Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Shuttle 2.5 Mini Parameters and Internals
| LLM Name | Shuttle 2.5 Mini |
| Repository 🤗 | https://huggingface.co/shuttleai/shuttle-2.5-mini |
| Model Size | 12.2b |
| Required VRAM | 24.5 GB |
| Updated | 2025-02-22 |
| Maintainer | shuttleai |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131074 |
| Torch Data Type | bfloat16 |
Best Alternatives to Shuttle 2.5 Mini
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...aptain Eris Violet GRPO V0.420 | 1000K / 24.5 GB | 177 | 11 |
| Violet Twilight V0.2 | 1000K / 24.5 GB | 536387 | 29 |
| ...ish Mistral Nemo Instruct 2407 | 1000K / 24.5 GB | 77 | 2 |
| Mistral Nemo Kurdish | 1000K / 24.5 GB | 102 | 3 |
| Educa Ai Nemo Sft | 1000K / 49.3 GB | 543 | 4 |
| Slush ChatWaifu Chronos | 1000K / 24.5 GB | 30 | 3 |
| Educa Ai Nemo DPO | 1000K / 49.3 GB | 66 | 3 |
| Mergekit Slerp Xeugntu | 1000K / 24.5 GB | 16 | 0 |
| Slush Lyra Gutenberg Bophades | 1000K / 24.5 GB | 26 | 2 |
| Mergekit Slerp Xqcetfe | 1000K / 24.5 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than shuttleai/shuttle-2.5-mini .
Rank the Shuttle 2.5 Mini 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! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227