Arxiv:1910.09700 4-bit 4bit Autotrain compatible Conversational Endpoints compatible Gemma Gptq Instruct Quantized Region:us Safetensors Sharded Tensorflow
Gemma 7B Instruct GPTQ 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 7B Instruct GPTQ 4bit Parameters and Internals
| LLM Name | Gemma 7B Instruct GPTQ 4bit |
| Repository 🤗 | https://huggingface.co/stan-hua/Gemma-7B-Instruct-GPTQ-4bit |
| Model Size | 7b |
| Required VRAM | 5.6 GB |
| Updated | 2024-09-06 |
| Maintainer | stan-hua |
| Model Type | gemma |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | GemmaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Gemma 7B Instruct GPTQ 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ruct Malayalam Model Vllm 4bit | 16K / 5.6 GB | 22 | 0 |
| Gemma Ko 7B Instruct V0.71 | 8K / 17 GB | 3140 | 1 |
| Gemma Ko 7B Instruct V0.62 | 8K / 17 GB | 6971 | 2 |
| ... 7B Finetuned Sft Navarasa 2.0 | 8K / 34 GB | 405 | 16 |
| Gemma Ko 7B Instruct V0.52 | 8K / 17 GB | 1757 | 0 |
| Gemma Ko 7B Instruct V0.50 | 8K / 17 GB | 1761 | 0 |
| X Instruction 7B Ta | 8K / 17.1 GB | 6 | 0 |
| X Instruction 7B Id | 8K / 17.1 GB | 5 | 0 |
| RoGemma 7B Instruct | 8K / 17.1 GB | 43 | 1 |
| X Instruction 7B 10langs | 8K / 17.1 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than stan-hua/Gemma-7B-Instruct-GPTQ-4bit .
Rank the Gemma 7B Instruct GPTQ 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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110