Autotrain compatible Base model:finetune:locutusque... Base model:locutusque/tinymist... Dataset:epfl-llm/guidelines Dataset:jeankaddour/minipile En Endpoints compatible Generated from trainer Mistral Pytorch Region:us
TinyMistral V2.5 MiniPile Guidelines E1 Benchmarks
ARC: 26.45-72.5%
HellaSwag: 25.68-73.1%
MMLU: 23.53-72.8%
TruthfulQA: 49.85-15.5%
WinoGrande: 49.41-43.5%
nn.n% — How the model compares to the GPT-4.
TinyMistral V2.5 MiniPile Guidelines E1 Parameters and Internals
| LLM Name | TinyMistral V2.5 MiniPile Guidelines E1 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 248m |
| Required VRAM | 0.6 GB |
| Updated | 2024-07-27 |
| Maintainer | Dans-DiscountModels |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32005 |
| Torch Data Type | bfloat16 |
Best Alternatives to TinyMistral V2.5 MiniPile Guidelines E1
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| TinyMistral 248M V2.5 | 0.3 | 32K / 1 GB | 986 | 25 |
| TinyMistral 248M V2 | 0.3 | 32K / 1 GB | 1855 | 15 |
| TinyMistral 248M 8bits | 0.2 | 32K / 0.3 GB | 22 | 0 |
| Tinymistv1 | 0.2 | 32K / 0.5 GB | 20 | 0 |
| TinyMistral V2 Test1 | 0.2 | 32K / 1 GB | 6 | 1 |
| TinyMistral 248M Instruct | 0.2 | 32K / 1 GB | 133 | 11 |
| TinyMistral Haiku | 0.2 | 32K / 1 GB | 23 | 0 |
| ...istral 248M V2.5 Instruct Orpo | 0.2 | 32K / 0.5 GB | 6 | 0 |
| SpydazWebAI MiniAI 248m | 0.2 | 32K / 0.5 GB | 9 | 1 |
| TinyMistral 248M | 0.2 | 32K / 1 GB | 2647 | 38 |
Note: green Score (e.g. "73.2") means that the model is better than Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 .
Rank the TinyMistral V2.5 MiniPile Guidelines E1 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501