Arxiv:1910.09700 4-bit 4bit Autotrain compatible Conversational Endpoints compatible Gemma Gptq Lora Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/ghemdd/gemma-EPFL-4bit
Gemma EPFL 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 EPFL 4bit Parameters and Internals
| LLM Name | Gemma EPFL 4bit |
| Repository 🤗 | https://huggingface.co/ghemdd/gemma-EPFL-4bit |
| Model Size | 790m |
| Required VRAM | 2.1 GB |
| Updated | 2025-02-22 |
| Maintainer | ghemdd |
| Model Type | gemma |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | GemmaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Gemma EPFL 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kto Sft Mcqa 4bit | 8K / 2.1 GB | 80 | 0 |
| Gemma Kto Only 4bit | 8K / 2.1 GB | 77 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ghemdd/gemma-EPFL-4bit .
Rank the Gemma EPFL 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227