Model Card on HF 🤗: https://huggingface.co/llm-jp/llm-jp-3-3.7b
Llm Jp 3 3.7B 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)
Llm Jp 3 3.7B Parameters and Internals
| LLM Name | Llm Jp 3 3.7B |
| Repository 🤗 | https://huggingface.co/llm-jp/llm-jp-3-3.7b |
| Model Size | 3.7b |
| Required VRAM | 7.6 GB |
| Updated | 2025-09-23 |
| Maintainer | llm-jp |
| Model Type | llama |
| Model Files | |
| Supported Languages | en ja |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <PAD|LLM-jp> |
| Vocabulary Size | 99584 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llm Jp 3 3.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SJT 3.7B | 4K / 8.2 GB | 5 | 0 |
| ....0 Computer Crime Act Instruct | 4K / 13.7 GB | 9 | 0 |
| Llm Jp 3 3.7B Instruct | 4K / 7.6 GB | 1252 | 11 |
| ...3 3.7B Instruct EZO Humanities | 4K / 7.6 GB | 9 | 6 |
| Llm Jp 3 3.7B Instruct | 4K / 7.6 GB | 10 | 0 |
| Cpt St Vicuna V1.3 3.7B Ppl | 2K / 7.4 GB | 3 | 4 |
| ...sianMind V1.0 Bnb 4bit Smashed | 2K / 4.3 GB | 6 | 0 |
| Tenebra PreAlpha 128g 3BIT | 2K / 13.5 GB | 16 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than llm-jp/llm-jp-3-3.7b .
Rank the Llm Jp 3 3.7B 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124