metadata

license: apache-2.0
inference: true

NOTE: This GGML conversion is primarily for use with llama.cpp.

PR #896 was used for q4_0. Everything else is latest as of upload time.
A warning for q4_2 and q4_3: These are WIP. Do not expect any kind of backwards compatibility until they are finalized.
13B can be found here: https://huggingface.co/eachadea/ggml-vicuna-13b-1.1
Choosing the right model:
- ggml-vicuna-7b-1.1-q4_0 - Fast, lacks in accuracy.
- ggml-vicuna-7b-1.1-q4_1 - More accurate, lacks in speed.
- ggml-vicuna-7b-1.1-q4_2 - Pretty much a better q4_0. Similarly fast, but more accurate.
- ggml-vicuna-7b-1.1-q4_3 - Pretty much a better q4_1. More accurate, still slower.
- ggml-vicuna-7b-1.0-uncensored - Available in q4_2 and q4_3, is an uncensored/unfiltered variant of the model. It is based on the previous release and still uses the ### Human: syntax. Avoid unless you need it.

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. (48k for the uncensored variant. 22k worth of garbage removed – see https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered)

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 "</s>". 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.