4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Gemma2 Quantized Region:us Safetensors
Gemma 2 2B 4bit 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)
Gemma 2 2B 4bit Parameters and Internals
| LLM Name | Gemma 2 2B 4bit |
| Repository 🤗 | https://huggingface.co/Arthur-LAGACHERIE/Gemma-2-2b-4bit |
| Model Size | 2b |
| Required VRAM | 2.2 GB |
| Updated | 2024-10-04 |
| Maintainer | Arthur-LAGACHERIE |
| Model Type | gemma2 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.42.3 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Gemma 2 2B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 2 2B It Bnb 4bit | 8K / 2.2 GB | 14633 | 12 |
| Gemma 2 2B Bnb 4bit | 8K / 2.2 GB | 11528 | 6 |
| Gemma 2 2B It 4bit | 8K / 1.5 GB | 584 | 2 |
| Athena Gemma 2 2B It Philos | 8K / 5.2 GB | 33 | 0 |
| Vi Gemma 2 2B Function Calling | 8K / 5.2 GB | 96 | 5 |
| Gemma 2 2B It 8bit | 8K / 2.8 GB | 59 | 2 |
| Gemma 2 2B 4bit | 8K / 1.5 GB | 27 | 3 |
| Gemma2 2B It Codealpaca | 8K / 5.2 GB | 12 | 0 |
| Gemma 2 2B It | 8K / 5.2 GB | 357787 | 580 |
| Gemma 2 2B | 8K / 10.5 GB | 3534825 | 354 |
Note: green Score (e.g. "73.2") means that the model is better than Arthur-LAGACHERIE/Gemma-2-2b-4bit .
Rank the Gemma 2 2B 4bit 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? 36542 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803