Model Card on HF 🤗: https://huggingface.co/lightblue/kurage-ru
Kurage Ru 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)
Kurage Ru Parameters and Internals
| LLM Name | Kurage Ru |
| Repository 🤗 | https://huggingface.co/lightblue/kurage-ru |
| Model Size | 7.6b |
| Required VRAM | 15.2 GB |
| Updated | 2024-12-27 |
| Maintainer | lightblue |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | ru |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151648 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Kurage Ru
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Exp 3 Q R | 128K / 15.2 GB | 42 | 0 |
| T36Model | 128K / 15.2 GB | 416 | 0 |
| T21Model | 128K / 15.2 GB | 327 | 0 |
| Exp 2 Q R | 128K / 15.2 GB | 25 | 0 |
| T35Model | 128K / 15.2 GB | 46 | 0 |
| Arcee Agent | 128K / 15.2 GB | 236 | 88 |
| Marco O1 | 32K / 15.2 GB | 15212 | 670 |
| Arcee Spark | 32K / 15.2 GB | 2859 | 86 |
| Oolel V0.1 | 32K / 30.5 GB | 407 | 13 |
| Kurage Multilingual | 32K / 15.2 GB | 36 | 28 |
Note: green Score (e.g. "73.2") means that the model is better than lightblue/kurage-ru .
Rank the Kurage Ru 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? 40303 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227