Merged Model Autotrain compatible Code Computer science Dataset:open-phi/programming b... Dataset:open-phi/textbooks En Endpoints compatible Mistral Model-index Region:us Safetensors
TinyMistral 248M V2.5 Benchmarks
ARC: 24.57 vs 96.7 (so35)-74.6%
HellaSwag: 27.49 vs 95.3 (gpt4)-71.2%
MMLU: 23.15 vs 88.3 (so35)-73.8%
TruthfulQA: 46.72 vs 59 (gpt4)-20.8%
WinoGrande: 47.83 vs 87.5 (gpt4)-45.3%
LLME Score: 0.24987
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)
TinyMistral 248M V2.5 Parameters and Internals
| LLM Name | TinyMistral 248M V2.5 |
| Repository 🤗 | https://huggingface.co/Locutusque/TinyMistral-248M-v2.5 |
| Merged Model | Yes |
| Model Size | 248m |
| Required VRAM | 1 GB |
| Updated | 2024-09-07 |
| Maintainer | Locutusque |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en code |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32005 |
| Torch Data Type | float16 |
Best Alternatives to TinyMistral 248M V2.5
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TinyMistral 248M V2 | 32K / 1 GB | 1343 | 15 |
| TinyMistral 248M V2.5 Instruct | 32K / 1 GB | 12 | 10 |
| ...al V2.5 MiniPile Guidelines E1 | 32K / 0.6 GB | 5 | 2 |
| TinyMistral V2 Test1 | 32K / 1 GB | 4 | 1 |
| TinyMistral 248M 8bits | 32K / 0.3 GB | 21 | 1 |
| Tinymistv1 | 32K / 0.5 GB | 17 | 0 |
| TinyMistral 248M Instruct | 32K / 1 GB | 59 | 11 |
| TinyMistral Haiku | 32K / 1 GB | 6 | 0 |
| TinyMistral 248M | 32K / 1 GB | 6475 | 39 |
| ...istral 248M V2.5 Instruct Orpo | 32K / 0.5 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Locutusque/TinyMistral-248M-v2.5 .
Rank the TinyMistral 248M V2.5 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803