--- license: other --- # Vicuna 13B 1.1 HF This is an HF version of the [Vicuna 13B 1.1 model](https://huggingface.co/lmsys/vicuna-13b-delta-v1.1). It was created by merging the deltas provided in the above repo with the original Llama 13B model, [using the code provided on their Github page](https://github.com/lm-sys/FastChat#vicuna-weights). ## My Vicuna 1.1 model repositories I have the following Vicuna 1.1 repositories available: **13B models:** * [Unquantized 13B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-13B-1.1-HF) * [GPTQ quantized 4bit 13B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g) * [GPTQ quantized 4bit 13B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g-GGML) **7B models:** * [Unquantized 7B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-7B-1.1-HF) * [GPTQ quantized 4bit 7B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g) * [GPTQ quantized 4bit 7B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g-GGML) # Vicuna Model Card ## Model details **Model type:** Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. It is an auto-regressive language model, based on the transformer architecture. **Model date:** Vicuna was trained between March 2023 and April 2023. **Organizations developing the model:** The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego. **Paper or resources for more information:** https://vicuna.lmsys.org/ **License:** Apache License 2.0 **Where to send questions or comments about the model:** https://github.com/lm-sys/FastChat/issues ## Intended use **Primary intended uses:** The primary use of Vicuna is research on large language models and chatbots. **Primary intended users:** The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## Training dataset 70K conversations collected from ShareGPT.com. ## Evaluation dataset A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details. ## Major updates of weights v1.1 - Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `""`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries. - Fix the supervised fine-tuning loss computation for better model quality.