Model Card on HF 🤗: https://huggingface.co/Trelis/TrelisLM-100M-layer-hidden-pruned
TrelisLM 100M Layer Hidden Pruned 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)
TrelisLM 100M Layer Hidden Pruned Parameters and Internals
| LLM Name | TrelisLM 100M Layer Hidden Pruned |
| Repository 🤗 | https://huggingface.co/Trelis/TrelisLM-100M-layer-hidden-pruned |
| Model Size | 100m |
| Required VRAM | 0.2 GB |
| Updated | 2024-09-18 |
| Maintainer | Trelis |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to TrelisLM 100M Layer Hidden Pruned
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmollerLM2 100M Instruct Sft | 8K / 0.3 GB | 25 | 0 |
| SmollerLM2 100M | 8K / 0.2 GB | 5 | 0 |
| Stockmark 2 100B Instruct Beta | 4K / 192.9 GB | 55 | 10 |
| Stockmark 100B | 4K / 191.9 GB | 1324 | 33 |
| Saily 100b | 4K / 235.5 GB | 183 | 7 |
| Plankton 100M | 4K / 0.4 GB | 17 | 0 |
| Reglu 100B | 2K / 2.6 GB | 29 | 1 |
| Llama 161M 100B | 1K / 0.3 GB | 16 | 23 |
| ...ephyr Smol Llama 100M DPO Full | 1K / 0.2 GB | 12 | 3 |
| ...ephyr Smol Llama 100M DPO Full | 1K / GB | 13 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Trelis/TrelisLM-100M-layer-hidden-pruned .
Rank the TrelisLM 100M Layer Hidden Pruned 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124