Slim Summary 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)
Slim Summary Parameters and Internals
| LLM Name | Slim Summary |
| Repository 🤗 | https://huggingface.co/llmware/slim-summary |
| Model Size | 3b |
| Required VRAM | 5.6 GB |
| Updated | 2024-09-07 |
| Maintainer | llmware |
| Model Type | stablelm_epoch |
| Model Files | |
| Model Architecture | StableLMEpochForCausalLM |
| License | cc-by-sa-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.33.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
Best Alternatives to Slim Summary
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Stable Code 3B Mlx | 16K / 5.6 GB | 4 | 1 |
| Aura 3B | 4K / 5.6 GB | 6 | 2 |
| Slim Extract | 4K / 5.6 GB | 93 | 11 |
| Slim Boolean | 4K / 5.6 GB | 3 | 4 |
| Slim Sa Ner | 4K / 5.6 GB | 4 | 6 |
| Slim Tags 3B | 4K / 5.6 GB | 4 | 4 |
| Slim Xsum | 4K / 5.6 GB | 9 | 6 |
| Memphis CoT 3B | 4K / 5.6 GB | 10 | 29 |
| Tofu 3B | 4K / 5.6 GB | 7 | 2 |
| Fett Uccine Mini 3B | 4K / 5.6 GB | 7 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than llmware/slim-summary .
Rank the Slim Summary 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