Arxiv:2307.09288 Arxiv:2309.15088 Autotrain compatible En Fp16 Information retrieval Llama Pytorch Quantized Region:us Reranker Sharded
Rank Vicuna 7b V1 Fp16 Benchmarks
nn.n% — How the model compares to the GPT-4.
Rank Vicuna 7B V1 Fp16 Parameters and Internals
| LLM Name | Rank Vicuna 7b V1 Fp16 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2024-07-26 |
| Maintainer | castorini |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | fp16 |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Rank Vicuna 7B V1 Fp16
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Smaugv0.1 6.0bpw H6 EXL2 | 0.2 | 195K / 26.4 GB | 4 | 4 |
| Smaugv0.1 5.0bpw H6 EXL2 | 0.2 | 195K / 22.3 GB | 6 | 3 |
| Smaugv0.1 4.0bpw H6 EXL2 | 0.2 | 195K / 18 GB | 11 | 1 |
| Smaugv0.1 3.0bpw H6 EXL2 | 0.2 | 195K / 13.9 GB | 6 | 1 |
| Smaugv0.1 8.0bpw H8 EXL2 | 0.2 | 195K / 34.9 GB | 6 | 1 |
| Smaugv0.1 4.65bpw H6 EXL2 | 0.2 | 195K / 20.8 GB | 5 | 1 |
| Mistral 7B Openplatypus 1K | 0.2 | 32K / 29 GB | 944 | 0 |
| Mistral 7B OpenOrca 1K | 0.2 | 32K / 29 GB | 940 | 3 |
| Mistral 7B A U0.5 B2 Ver0.4 | 0.2 | 32K / 14.4 GB | 1700 | 0 |
| Mistral 7B OP U1k Ver0.6 | 0.2 | 32K / 14.4 GB | 1700 | 0 |
Rank the Rank Vicuna 7B V1 Fp16 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