4-bit 4bit Autotrain compatible Base model:quantized:unsloth/g... Base model:unsloth/gemma-2b-bn... Bitsandbytes En Endpoints compatible Gemma Quantized Region:us Safetensors Sft Trl Unsloth
Test Model Parameters and Internals
| LLM Name | Test Model |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 2.1 GB |
| Updated | 2024-07-26 |
| Maintainer | taradepan |
| Model Type | gemma |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | GemmaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Test Model
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Vi Gemma 2B RAG | 0.3 | 8K / 5.1 GB | 370 | 7 |
| Gemma 1.1 2B It Bnb 4bit | 0.3 | 8K / 2.1 GB | 2854 | 4 |
| Gemma 2B Bnb 4bit | 0.3 | 8K / 2.1 GB | 8106 | 14 |
| Gemma 2B It Bnb 4bit | 0.3 | 8K / 2.1 GB | 5660 | 15 |
| My AwesomeFinance Model | 0.2 | 8K / 2.1 GB | 23 | 0 |
| ... 2.8 Gemma 2B HQQ 1bit Smashed | 0.2 | 8K / 1.3 GB | 22 | 0 |
| ... 2.8 Gemma 2B HQQ 2bit Smashed | 0.2 | 8K / 1.6 GB | 21 | 0 |
| ... 2.8 Gemma 2B Bnb 4bit Smashed | 0.2 | 8K / 2.2 GB | 27 | 0 |
| ... 2.8 Gemma 2B HQQ 4bit Smashed | 0.2 | 8K / 2.1 GB | 15 | 0 |
| Emo AI 3B | 0.2 | 8K / 5.1 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than taradepan/test-model .
Rank the Test Model 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501