license: gpl
datasets:
- nomic-ai/gpt4all-j-prompt-generations
language:
- en
inference: false
GPT4All-13B-snoozy-GGML
These files are GGML format model files of Nomic.AI's GPT4all-13B-snoozy.
GGML files are for CPU inference using llama.cpp.
Repositories available
- 4bit GPTQ models for GPU inference.
- 4bit and 5bit GGML models for GPU inference.
- Nomic.AI's original model in float32 HF for GPU inference.
Provided files
| Name | Quant method | Bits | Size | RAM required | Use case |
|---|---|---|---|---|---|
GPT4All-13B-snoozy.q4_0.bin |
q4_0 | 4bit | 8.14GB | 10GB | Maximum compatibility |
GPT4All-13B-snoozy.q4_2.bin |
q4_2 | 4bit | 8.14GB | 10GB | Best compromise between resources, speed and quality |
GPT4All-13B-snoozy.q5_0.bin |
q5_0 | 5bit | 8.95GB | 11GB | Brand new 5bit method. Potentially higher quality than 4bit, at cost of slightly higher resources. |
GPT4All-13B-snoozy.q5_1.bin |
q5_1 | 5bit | 9.76GB | 12GB | Brand new 5bit method. Slightly higher resource usage than q5_0. |
- The q4_0 file provides lower quality, but maximal compatibility. It will work with past and future versions of llama.cpp
- The q4_2 file offers the best combination of performance and quality. This format is still subject to change and there may be compatibility issues, see below.
- The q5_0 file is using brand new 5bit method released 26th April. This is the 5bit equivalent of q4_0.
- The q5_1 file is using brand new 5bit method released 26th April. This is the 5bit equivalent of q4_1.
q4_2 compatibility
q4_2 is a relatively new 4bit quantisation method offering improved quality. However they are still under development and their formats are subject to change.
In order to use these files you will need to use recent llama.cpp code. And it's possible that future updates to llama.cpp could require that these files are re-generated.
If and when the q4_2 file no longer works with recent versions of llama.cpp I will endeavour to update it.
If you want to ensure guaranteed compatibility with a wide range of llama.cpp versions, use the q4_0 file.
q5_0 and q5_1 compatibility
These new methods were released to llama.cpp on 26th April. You will need to pull the latest llama.cpp code and rebuild to be able to use them.
Don't expect any third-party UIs/tools to support them yet.
How to run in llama.cpp
I use the following command line; adjust for your tastes and needs:
./main -t 12 -m GPT4All-13B-snoozy.q4_2.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write a story about llamas
### Response:"
Change -t 12 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.
If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins
How to run in text-generation-webui
Further instructions here: text-generation-webui/docs/llama.cpp-models.md.
Note: at this time text-generation-webui will not support the new q5 quantisation methods.
Thireus has written a great guide on how to update it to the latest llama.cpp code so that these files can be used in the UI.
Repositories available
- 4bit GPTQ models for GPU inference.
- 4bit and 5bit GGML models for GPU inference.
- Nomic.AI's original model in float32 HF for GPU inference.
Original Model Card for GPT4All-13b-snoozy
An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
Model Details
Model Description
This model has been finetuned from LLama 13B
- Developed by: Nomic AI
- Model Type: A finetuned LLama 13B model on assistant style interaction data
- Language(s) (NLP): English
- License: Apache-2
- Finetuned from model [optional]: LLama 13B
This model was trained on nomic-ai/gpt4all-j-prompt-generations using revision=v1.3-groovy
Model Sources [optional]
- Repository: https://github.com/nomic-ai/gpt4all
- Base Model Repository: https://github.com/facebookresearch/llama
- Demo [optional]: https://gpt4all.io/
Results
Results on common sense reasoning benchmarks
Model BoolQ PIQA HellaSwag WinoGrande ARC-e ARC-c OBQA
----------------------- ---------- ---------- ----------- ------------ ---------- ---------- ----------
GPT4All-J 6B v1.0 73.4 74.8 63.4 64.7 54.9 36.0 40.2
GPT4All-J v1.1-breezy 74.0 75.1 63.2 63.6 55.4 34.9 38.4
GPT4All-J v1.2-jazzy 74.8 74.9 63.6 63.8 56.6 35.3 41.0
GPT4All-J v1.3-groovy 73.6 74.3 63.8 63.5 57.7 35.0 38.8
GPT4All-J Lora 6B 68.6 75.8 66.2 63.5 56.4 35.7 40.2
GPT4All LLaMa Lora 7B 73.1 77.6 72.1 67.8 51.1 40.4 40.2
GPT4All 13B snoozy *83.3* 79.2 75.0 *71.3* 60.9 44.2 43.4
Dolly 6B 68.8 77.3 67.6 63.9 62.9 38.7 41.2
Dolly 12B 56.7 75.4 71.0 62.2 *64.6* 38.5 40.4
Alpaca 7B 73.9 77.2 73.9 66.1 59.8 43.3 43.4
Alpaca Lora 7B 74.3 *79.3* 74.0 68.8 56.6 43.9 42.6
GPT-J 6B 65.4 76.2 66.2 64.1 62.2 36.6 38.2
LLama 7B 73.1 77.4 73.0 66.9 52.5 41.4 42.4
LLama 13B 68.5 79.1 *76.2* 70.1 60.0 *44.6* 42.2
Pythia 6.9B 63.5 76.3 64.0 61.1 61.3 35.2 37.2
Pythia 12B 67.7 76.6 67.3 63.8 63.9 34.8 38.0
Vicuña T5 81.5 64.6 46.3 61.8 49.3 33.3 39.4
Vicuña 13B 81.5 76.8 73.3 66.7 57.4 42.7 43.6
Stable Vicuña RLHF 82.3 78.6 74.1 70.9 61.0 43.5 *44.4*
StableLM Tuned 62.5 71.2 53.6 54.8 52.4 31.1 33.4
StableLM Base 60.1 67.4 41.2 50.1 44.9 27.0 32.0