Tinyllama 15M 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)
Tinyllama 15M Parameters and Internals
| LLM Name | Tinyllama 15M |
| Repository 🤗 | https://huggingface.co/nickypro/tinyllama-15M |
| Model Size | 15m |
| Required VRAM | 0 GB |
| Updated | 2024-09-07 |
| Maintainer | nickypro |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 256 |
| Model Max Length | 256 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
Best Alternatives to Tinyllama 15M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| L3 Aethora 15B V2 | 8K / 30.1 GB | 84 | 39 |
| OpenCrystal 15B L3 V3 | 8K / 30 GB | 50 | 5 |
| OpenCrystal L3 15B V2.1 | 8K / 30 GB | 22 | 5 |
| OpenCrystal 15B L3 V2 | 8K / 30 GB | 35 | 4 |
| L3 Aethora 15B | 8K / 30.1 GB | 85 | 30 |
| Meta Llama 3 15B Instruct | 8K / 23.9 GB | 3 | 1 |
| Llama 3 15B Instruct Ft V2 | 8K / 30.1 GB | 7 | 4 |
| Llama 3 15B Instruct Zeroed Ft | 8K / 30.1 GB | 5 | 2 |
| LLaMa 3 Stheno V3.2 15B | 8K / 30 GB | 12 | 5 |
| L3 NA Aethora 15B | 8K / 30.1 GB | 6 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than nickypro/tinyllama-15M .
Rank the Tinyllama 15M 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