Model Card on HF 🤗: https://huggingface.co/princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-top_k
Lm 1.3B Select 30B Tokens By Writing Style Top K 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)
Lm 1.3B Select 30B Tokens By Writing Style Top K Parameters and Internals
| LLM Name | Lm 1.3B Select 30B Tokens By Writing Style Top K |
| Repository 🤗 | https://huggingface.co/princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-top_k |
| Model Size | 30b |
| Required VRAM | 5.4 GB |
| Updated | 2025-03-14 |
| Maintainer | princeton-nlp |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Lm 1.3B Select 30B Tokens By Writing Style Top K
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Flash Llama 30M 20001 | 32K / 0.1 GB | 432 | 0 |
| Smaug Slerp 30B V0.1 | 32K / 60.4 GB | 12 | 0 |
| Tenebra 30B Alpha01 | 16K / 65 GB | 36 | 12 |
| Llama33b 16K | 16K / 65.2 GB | 7 | 1 |
| Yayi2 30B Llama | 4K / 121.2 GB | 430 | 22 |
| ... Tokens By Perplexity Bottom K | 4K / 5.4 GB | 7 | 0 |
| ...lue Sample With Temperature2.0 | 4K / 5.4 GB | 118 | 0 |
| ...via Sample With Temperature2.0 | 4K / 5.4 GB | 6 | 0 |
| Yayi2 30B Guanaco | 4K / 60.6 GB | 2 | 2 |
| Llama 30B Instruct 2048 | 2K / 65.2 GB | 2710 | 102 |
Note: green Score (e.g. "73.2") means that the model is better than princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-top_k .
Rank the Lm 1.3B Select 30B Tokens By Writing Style Top K 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? 46635 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227