Model Card on HF 🤗: https://huggingface.co/amphora/small-instruct
Small Instruct 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)
Small Instruct Parameters and Internals
| LLM Name | Small Instruct |
| Repository 🤗 | https://huggingface.co/amphora/small-instruct |
| Required VRAM | 2.9 GB |
| Updated | 2025-09-23 |
| Maintainer | amphora |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | GPT2TokenizerFast |
| Padding Token | <||pad||> |
| Vocabulary Size | 50304 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Small Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Reverse Instruct | 32K / 27 GB | 6 | 3 |
| Etri Ones Solar | 4K / 42.9 GB | 10 | 0 |
| Phi 3 Orpo V8.16 | 4K / 7.6 GB | 5 | 0 |
| Tinyllama Python | 4K / 2.2 GB | 0 | 2 |
| Taiwan LLaMa V1.0 | 4K / 26 GB | 19 | 77 |
| Taiwan LLaMa V0.0 | 4K / 26 GB | 15 | 1 |
| Taiwan LLaMa V0.9 | 4K / 26 GB | 11 | 0 |
| Llama2 Ja Small Instruct | 2K / 1.7 GB | 5 | 1 |
| Kolong Llama V0.1 | 2K / 13.7 GB | 8 | 0 |
| ...ama Miniguanaco Instruct 121v2 | 2K / 2.2 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than amphora/small-instruct .
Rank the Small 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? 51549 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124