Nomic.AI's GPT4All-13B-snoozy GGML
These files are GGML format model files for Nomic.AI's GPT4All-13B-snoozy.
GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:
Repositories available
- 4-bit GPTQ models for GPU inference
- 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
- Unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Compatibility
Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.
They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.
New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K
These new quantisation methods are only compatible with llama.cpp as of June 6th, commit 2d43387.
They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.
Explanation of the new k-quant methods
The new methods available are:
- GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
- GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
- GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
- GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
- GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
- GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| GPT4All-13B-snoozy.ggmlv3.q2_K.bin | q2_K | 2 | 5.43 GB | 7.93 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| GPT4All-13B-snoozy.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.87 GB | 9.37 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| GPT4All-13B-snoozy.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.25 GB | 8.75 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| GPT4All-13B-snoozy.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.59 GB | 8.09 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| GPT4All-13B-snoozy.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| GPT4All-13B-snoozy.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.82 GB | 10.32 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| GPT4All-13B-snoozy.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.32 GB | 9.82 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| GPT4All-13B-snoozy.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| GPT4All-13B-snoozy.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.21 GB | 11.71 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| GPT4All-13B-snoozy.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.95 GB | 11.45 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
How to run in llama.cpp
I use the following command line; adjust for your tastes and needs:
./main -t 10 -ngl 32 -m GPT4All-13B-snoozy.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
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.
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute.
Thanks to the chirper.ai team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
- Patreon: https://patreon.com/TheBlokeAI
- Ko-Fi: https://ko-fi.com/TheBlokeAI
Special thanks to: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
Patreon special mentions: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.
Thank you to all my generous patrons and donaters!
Original model card: Nomic.AI's GPT4All-13B-snoozy
Model Card for GPT4All-13b-snoozy
A GPL 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: GPL
- 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 | Avg. |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
| GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 |
| GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 |
| GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 |
| GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 |
| GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 |
| GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | **65.3** |
| Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 |
| Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 |
| Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 |
| Alpaca Lora 7B | 74.3 | **79.3** | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 |
| GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 |
| LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 |
| LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 |
| Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 |
| Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 |
| Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 |
| Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 |
| Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 |
| StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 |
| StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 |
| StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 |
| Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
| Mosaic mpt-7B | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |