Model Card on HF 🤗: https://huggingface.co/d-llm/test_sft
Test 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)
Test Sft Parameters and Internals
| LLM Name | Test Sft |
| Repository 🤗 | https://huggingface.co/d-llm/test_sft |
| Model Size | 1.8b |
| Required VRAM | 3.7 GB |
| Updated | 2025-02-22 |
| Maintainer | d-llm |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 151646 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Test Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dhanishtha | 128K / 3.5 GB | 82 | 2 |
| Qwen1.5 1.8B | 32K / 3.7 GB | 130186 | 47 |
| Qwen1.5 1.8B Chat | 32K / 3.7 GB | 12159 | 49 |
| MiniPLM Qwen 200M | 32K / 0.8 GB | 277 | 2 |
| MiniPLM Qwen 500M | 32K / 1.9 GB | 221 | 5 |
| Qwen1.5 1.8B Seed Sft | 32K / 3.7 GB | 156 | 0 |
| Orca 2.0 Tau 1.8B | 32K / 3.7 GB | 406 | 9 |
| Neural Chat Mini V2.2 1.8B | 32K / 3.7 GB | 66 | 6 |
| Qwen1.5 Wukong 1.8B | 32K / 3.7 GB | 72 | 4 |
| Coder1.8 ORPO TEST | 32K / 3.7 GB | 141 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than d-llm/test_sft .
Rank the Test 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227