Autotrain compatible Conversational Dataset:ilyagusev/saiga prefer... Dataset:ilyagusev/saiga scored Endpoints compatible Gemma2 Region:us Ru Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/IlyaGusev/saiga_gemma2_9b
Saiga Gemma2 9b 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)
Saiga Gemma2 9B Parameters and Internals
| LLM Name | Saiga Gemma2 9b |
| Repository 🤗 | https://huggingface.co/IlyaGusev/saiga_gemma2_9b |
| Model Size | 9b |
| Required VRAM | 18.6 GB |
| Updated | 2025-02-22 |
| Maintainer | IlyaGusev |
| Model Type | gemma2 |
| Model Files | |
| Supported Languages | ru |
| Model Architecture | Gemma2ForCausalLM |
| License | gemma |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.42.4 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Saiga Gemma2 9B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| G2 GSHT 32K | 32K / 20.4 GB | 10 | 0 |
| SystemGemma2 9B It | 32K / 18.6 GB | 69 | 1 |
| Gemma 2 9B It SimPO | 8K / 18.6 GB | 26919 | 152 |
| Gemma 2 9B It | 8K / 18.6 GB | 540306 | 670 |
| Gemma 2 9B | 8K / 37.1 GB | 107376 | 648 |
| ...2 9B Cpt Sahabatai V1 Instruct | 8K / 18.6 GB | 2552 | 34 |
| SILMA 9B Instruct V1.0 | 8K / 18.6 GB | 17679 | 68 |
| MT Merge4 Gemma 2 9B | 8K / 20.4 GB | 139 | 1 |
| MT3 Gen4 Gemma 2 9B | 8K / 20.4 GB | 108 | 4 |
| Darkest Muse V1 | 8K / 20.4 GB | 206 | 58 |
Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/saiga_gemma2_9b .
Rank the Saiga Gemma2 9B 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