Model Card on HF 🤗: https://huggingface.co/StarRing2022/RWKV-4-Raven-3B-v11-zh
RWKV 4 Raven 3B V11 Zh 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)
RWKV 4 Raven 3B V11 Zh Parameters and Internals
| Model Type |
| |||||||||
| Supported Languages |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | RWKV 4 Raven 3B V11 Zh |
| Repository 🤗 | https://huggingface.co/StarRing2022/RWKV-4-Raven-3B-v11-zh |
| Model Size | 3b |
| Required VRAM | 6 GB |
| Updated | 2025-02-22 |
| Maintainer | StarRing2022 |
| Model Type | rwkv |
| Model Files | |
| Model Architecture | AutoModel |
| Transformers Version | 4.29.0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50277 |
Best Alternatives to RWKV 4 Raven 3B V11 Zh
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Falcon 3 3B Rp Lora Model | 0K / 0.1 GB | 0 | 2 |
| Phi 4 Sky Lora | 0K / 0.3 GB | 0 | 2 |
| Qwen 2.5 3B Lora Model | 0K / 0.1 GB | 0 | 1 |
| Rocket 3B Llamafile | 0K / GB | 5068 | 7 |
| Madlad400 3B Mt Ct2 Int8 | 0K / 3 GB | 16 | 0 |
| ...230520 3147 520Gtokens Ctx4096 | 0K / 6 GB | 105 | 0 |
| Fastchat T5 3B V1.0 Ct2 Int8 | 0K / 2.9 GB | 2 | 2 |
| ...edPajama INCITE Instruct 3B V1 | 0K / 5.5 GB | 9 | 3 |
| ...st RedPajama INCITE Chat 3B V1 | 0K / 5.5 GB | 4 | 4 |
| Ct2fast Dolly V2 3B | 0K / 2.8 GB | 9 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than StarRing2022/RWKV-4-Raven-3B-v11-zh .
Rank the RWKV 4 Raven 3B V11 Zh 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