Sft is an open-source language model by gyubinc. Features: 2.1b LLM, VRAM: 4.2GB, Context: 32K, LLM Explorer Score: 0.28.
Model Card on HF 🤗: https://huggingface.co/gyubinc/sft
Sft 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)
Sft Parameters and Internals
| LLM Name | Sft |
| Repository 🤗 | https://huggingface.co/gyubinc/sft |
| Model Size | 2.1b |
| Required VRAM | 4.2 GB |
| Updated | 2026-05-20 |
| Maintainer | gyubinc |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.57.6 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
Best Alternatives to Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kanana 1.5 2.1B Instruct 2505 | 32K / 4.6 GB | 2491 | 37 |
| Fc Reasoning 2.1B | 32K / 4.2 GB | 6 | 0 |
| Kanana 1.5 2.1B Base | 32K / 4.2 GB | 481 | 13 |
| Kanana Safeguard Prompt 2.1B | 8K / 4.2 GB | 2864 | 18 |
| Kanana Nano 2.1B Base | 8K / 4.2 GB | 1497 | 39 |
| Kanana Nano 2.1B Instruct | 8K / 4.2 GB | 411 | 75 |
| DAMI Base Merge 0408 | 8K / 4.6 GB | 7 | 0 |
| EcomGen 0.0.2v | 8K / 8.4 GB | 6 | 0 |
| CT LLM Base | 4K / 4.3 GB | 20 | 11 |
| CT LLM SFT DPO | 4K / 0 GB | 23 | 5 |
Rank the Sft 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? 53834 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a