LLM Name | Llama 7B 4bit Act |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 3.8 GB |
Updated | 2024-07-27 |
Maintainer | wcde |
Model Type | llama |
Model Files | |
Quantization Type | 4bit |
Model Architecture | LLaMAForCausalLM |
Transformers Version | 4.27.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Llama 7B Onnx Merged Fp16 | 0.1 | 2K / GB | 14 | 7 |
Alpaca 7B Native 4bit | 0.1 | 0K / 4.5 GB | 52 | 4 |
Alpaca Native 4bit | 0.1 | 0K / 4.5 GB | 20 | 57 |
Llama 7B 4bit Gr128 | 0.1 | 0K / 4 GB | 11 | 4 |
Swallow 7B GPTQ | 0.2 | 4K / 4.1 GB | 5 | 1 |
Honest Llama2 Chat 7B | 0.1 | 2K / 13.5 GB | 19 | 9 |
Llama 7B Onnx Merged Fp32 | 0.1 | 2K / GB | 9 | 2 |
...xplore LM Ext 7B Brainstorming | 0.2 | 0K / 27 GB | 6 | 2 |
Explore LM Ext 7B Rewriting | 0.2 | 0K / 27 GB | 8 | 1 |
Explore LM 7B Math | 0.2 | 0K / 27 GB | 6 | 1 |
๐ 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! ๐