Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Gemma2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/skarnam/SFT_peft
SFT Peft 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 Peft Parameters and Internals
| LLM Name | SFT Peft |
| Repository 🤗 | https://huggingface.co/skarnam/SFT_peft |
| Model Size | 2.6b |
| Required VRAM | 5.2 GB |
| Updated | 2025-08-17 |
| Maintainer | skarnam |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.51.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <eos> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to SFT Peft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Test | 8K / 5.2 GB | 6 | 0 |
| SFT Fft | 8K / 5.2 GB | 5 | 0 |
| Gemma 2 Full Dare Peft | 8K / 10.5 GB | 7 | 0 |
| FFT Model Gemma | 8K / 5.2 GB | 5 | 0 |
| Vera V1.1 Instruct | 8K / 5.2 GB | 5 | 0 |
| SAFETY PEFT VECTOR | 8K / 10.5 GB | 6 | 0 |
| SAFETY FULL FT VECTOR | 8K / 10.5 GB | 6 | 0 |
| RESTA Sft Dare Full Ft | 8K / 10.5 GB | 5 | 0 |
| Base Tilde Sft Peft Gemma2 | 8K / 5.2 GB | 6 | 0 |
| Gemma2 Sft Peft | 8K / 5.2 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than skarnam/SFT_peft .
Rank the SFT Peft 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? 50728 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124