Autotrain compatible Base model:finetune:locutusque... Base model:locutusque/tinymist... Biology Chemistry Code Dataset:locutusque/hercules-v1... Dataset:open-orca/slimorca-ded... En Endpoints compatible Instruct Merge Mistral Not-for-all-audiences Region:us Safetensors
TinyMistral 248M V2.5 Instruct Benchmarks
ARC: 22.27 vs 96.7 (so35)-77%
HellaSwag: 27.6 vs 95.3 (gpt4)-71%
MMLU: 23.9 vs 88.3 (so35)-72.9%
TruthfulQA: 44.21 vs 59 (gpt4)-25.1%
WinoGrande: 48.22 vs 87.5 (gpt4)-44.9%
LLME Score: 0.24003
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 Instruct Parameters and Internals
| LLM Name | TinyMistral 248M V2.5 Instruct |
| Repository 🤗 | https://huggingface.co/Locutusque/TinyMistral-248M-v2.5-Instruct |
| Base Model(s) | |
| Model Size | 248m |
| Required VRAM | 1 GB |
| Updated | 2024-09-16 |
| Maintainer | Locutusque |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| 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 | float32 |
Quantized Models of the TinyMistral 248M V2.5 Instruct
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| ...istral 248M V2.5 Instruct GGUF | 2 | 100 | 0 GB |
Best Alternatives to TinyMistral 248M V2.5 Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Tinymistv1 | 32K / 0.5 GB | 17 | 0 |
| TinyMistral 248M Instruct | 32K / 1 GB | 59 | 11 |
| ...istral 248M V2.5 Instruct Orpo | 32K / 0.5 GB | 5 | 0 |
| TinyMistral 248M V2 Instruct | 32K / 0.5 GB | 11 | 7 |
| ...stral V2 Pycoder Instruct 248M | 32K / 1 GB | 16 | 2 |
| ...mistral 248M Hypnosis Instruct | 32K / 0.5 GB | 7 | 1 |
| ...al V2 Pycoder Instruct 248M V1 | 32K / 0.5 GB | 5 | 1 |
| ...istral Magicoder Instruct 248M | 32K / 0.5 GB | 6 | 2 |
| Tinymistv1 | 32K / 0.5 GB | 0 | 0 |
| TinyMistral 248M Chat V2 | 2K / 1 GB | 260 | 26 |
Rank the TinyMistral 248M V2.5 Instruct 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? 35926 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803