---
inference: true
---

Better maintained files can be found here:
https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/

---

### NOTE:
The PR [#1405](https://github.com/ggerganov/llama.cpp/pull/1405) brought breaking changes - none of the old models work with the latest build of llama.cpp.

Pre-PR #1405 files have been marked as old but remain accessible for those who need them (oobabooga, gpt4all-chat haven't been updated to support the new format as of May 14).

Additionally, `q4_3` and `q4_2` have been completely axed in favor of their 5-bit counterparts (q5_1 and q5_0, respectively).

New files inference up to 10% faster without any quality reduction.


### Links
- [7B version of this model](https://huggingface.co/eachadea/ggml-vicuna-7b-1.1)
- [Set up with gpt4all-chat (one-click setup, available in in-app download menu)](https://gpt4all.io/index.html)
- [Set up with llama.cpp](https://github.com/ggerganov/llama.cpp)
- [Set up with oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md)

### Info
- Main files are based on v1.1 release
  - See changelog below
  - Use prompt template: ```HUMAN: <prompt> ASSISTANT: <response>```
- Uncensored files are based on a modified v0 release
  - Use prompt template: ```### User: <prompt> ### Assistant: <response>```

### Quantization
Several quantization methods are supported. They differ in the resulting model disk size and inference speed.

Model | F16 | Q4_0 | Q4_1 | Q4_2 | Q4_3 | Q5_0 | Q5_1 | Q8_0
-- | -- | -- | -- | -- | -- | -- | -- | --
7B (ppl) | 5.9565 | 6.2103 | 6.1286 | 6.1698 | 6.0617 | 6.0139 | 5.9934 | 5.9571
7B (size) | 13.0G | 4.0G | 4.8G | 4.0G | 4.8G | 4.4G | 4.8G | 7.1G
7B (ms/tok @ 4th) | 128 | 56 | 61 | 84 | 91 | 91 | 95 | 75
7B (ms/tok @ 8th) | 128 | 47 | 55 | 48 | 53 | 53 | 59 | 75
7B (bpw) | 16.0 | 5.0 | 6.0 | 5.0 | 6.0 | 5.5 | 6.0 | 9.0
-- | -- | -- | -- | -- | -- | -- | -- | --
13B (ppl) | 5.2455 | 5.3748 | 5.3471 | 5.3433 | 5.3234 | 5.2768 | 5.2582 | 5.2458
13B (size) | 25.0G | 7.6G | 9.1G | 7.6G | 9.1G | 8.4G | 9.1G | 14G
13B (ms/tok @ 4th) | 239 | 104 | 113 | 160 | 175 | 176 | 185 | 141
13B (ms/tok @ 8th) | 240 | 85 | 99 | 97 | 114 | 108 | 117 | 147
13B (bpw) | 16.0 | 5.0 | 6.0 | 5.0 | 6.0 | 5.5 | 6.0 | 9.0

q5_1 or 5_0 are the latest and most performant implementations. The former is slightly more accurate at the cost of a bit of performance. Most users should use one of the two.
If you encounter any kind of compatibility issues, you might want to try the older q4_x

---

# 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.