Llava 7B V0 4bit 128g 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)
Llava 7B V0 4bit 128g Parameters and Internals
| LLM Name | Llava 7B V0 4bit 128g |
| Repository 🤗 | https://huggingface.co/wojtab/llava-7b-v0-4bit-128g |
| Model Size | 7b |
| Required VRAM | 4 GB |
| Updated | 2024-09-07 |
| Maintainer | wojtab |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32004 |
| Torch Data Type | float16 |
Best Alternatives to Llava 7B V0 4bit 128g
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Smaugv0.1 6.0bpw H6 EXL2 | 195K / 26.4 GB | 18 | 4 |
| Smaugv0.1 5.0bpw H6 EXL2 | 195K / 22.3 GB | 20 | 3 |
| Smaugv0.1 4.0bpw H6 EXL2 | 195K / 18 GB | 19 | 1 |
| Smaugv0.1 3.0bpw H6 EXL2 | 195K / 13.9 GB | 18 | 1 |
| Smaugv0.1 4.65bpw H6 EXL2 | 195K / 20.8 GB | 18 | 1 |
| Smaugv0.1 8.0bpw H8 EXL2 | 195K / 34.9 GB | 17 | 1 |
| Mistral 7B A U0.5 B2 Ver0.4 | 32K / 14.4 GB | 2870 | 0 |
| Mistral 7B OP U1k Ver0.6 | 32K / 14.4 GB | 2900 | 0 |
| Mistral 7B Openplatypus 1K | 32K / 29 GB | 688 | 0 |
| Mistral 7B OpenOrca 1K | 32K / 29 GB | 684 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than wojtab/llava-7b-v0-4bit-128g .
Rank the Llava 7B V0 4bit 128g 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803