Arxiv:2306.05685 Arxiv:2307.09288 4-bit Autotrain compatible Base model:lmsys/vicuna-7b-v1.... Base model:quantized:lmsys/vic... Gptq Llama Quantized Region:us Safetensors
Vicuna 7B V1.5 GPTQ 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)
Vicuna 7B V1.5 GPTQ Parameters and Internals
| LLM Name | Vicuna 7B V1.5 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/vicuna-7B-v1.5-GPTQ |
| Model Name | Vicuna 7B v1.5 |
| Model Creator | lmsys |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 3.9 GB |
| Updated | 2024-09-07 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| 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 Vicuna 7B V1.5 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yarn Llama 2 7B 128K GPTQ | 128K / 3.9 GB | 15 | 7 |
| Yarn Llama 2 7B 64K GPTQ | 64K / 3.9 GB | 14 | 1 |
| ... 7B 32K Instructions V4 Marlin | 32K / 4.1 GB | 19 | 0 |
| Aixcoder 7B GPTQ | 32K / 4.5 GB | 3 | 1 |
| ...Calm2 7B Chat GPTQ Calib Ja 1K | 32K / 4.4 GB | 90 | 5 |
| Calm2 7B Chat GPTQ | 32K / 4.4 GB | 14 | 6 |
| Llama 2 7B 32K Instruct GPTQ | 32K / 3.9 GB | 19 | 27 |
| CodeLlama 7B Instruct GPTQ | 16K / 3.9 GB | 144636 | 43 |
| Codebear 7B 4bit | 16K / 3.9 GB | 4 | 1 |
| ...a 7B Instruct GPTQ Calib Ja 1K | 16K / 3.9 GB | 47 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/vicuna-7B-v1.5-GPTQ .
Rank the Vicuna 7B V1.5 GPTQ 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