inference: false
license: other
MosaicML's MPT-30B-chat GGML
These files are GGML format model files for MosaicML's MPT-30B-chat.
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.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
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 compatible with llama.cpp as of June 6th, commit 2d43387.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
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 |
|---|---|---|---|---|---|
| mpt-30b-chat.ggmlv0.q4_0.bin | q4_0 | 4 | 16.85 GB | 19.35 GB | Original llama.cpp quant method, 4-bit. |
| mpt-30b-chat.ggmlv0.q4_1.bin | q4_1 | 4 | 18.73 GB | 21.23 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. |
| mpt-30b-chat.ggmlv0.q5_0.bin | q5_0 | 5 | 20.60 GB | 23.10 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| mpt-30b-chat.ggmlv0.q5_1.bin | q5_1 | 5 | 22.47 GB | 24.97 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| mpt-30b-chat.ggmlv0.q8_0.bin | q8_0 | 8 | 31.83 GB | 34.33 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 mpt-30b-chat.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:"
If you're able to use full GPU offloading, you should use -t 1 to get best performance.
If not able to fully offload to GPU, you should use more cores. Change -t 10 to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
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: Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.
Thank you to all my generous patrons and donaters!
Original model card: MosaicML's MPT-30B-chat
MPT-30B-Chat
MPT-30B-Chat is a chatbot-like model for dialogue generation. It was built by finetuning MPT-30B on the ShareGPT-Vicuna, Camel-AI, GPTeacher, Guanaco, Baize and some generated datasets.
- License: CC-By-NC-SA-4.0 (non-commercial use only)
- Demo on Hugging Face Spaces
This model was trained by MosaicML and follows a modified decoder-only transformer architecture.
Model Date
June 22, 2023
Model License
CC-By-NC-SA-4.0 (non-commercial use only)
Documentation
- Blog post: Raising the bar for open-source foundation models
- Codebase (mosaicml/llm-foundry repo)
- Questions: Feel free to contact us via the MosaicML Community Slack!
Example Dialogue
ksreenivasan:
I want you to come up with a tweet based on this summary of the article:
We are excited to extend the MosaicML Foundation Series with MPT-30B, a new commercially licensed open-source model that is significantly more powerful, and outperforms the original GPT-3. In addition, we are releasing two fine-tuned models, MPT-30B-Instruct and MPT-30B-Chat, that are built on top of MPT-30B and excel at short-form instruction following and multi-turn conversations, respectively. All MPT-30B models come with special features that differentiate them from other LLMs, including an 8k token context window (which can be further extended via finetuning; see MPT-7B-StoryWriter), support for context-length extrapolation via ALiBi, and efficient inference + training performance via FlashAttention. It also has strong coding abilities thanks to its pretraining data mixture.
MPT-30B-Chat:
"Revolutionize your AI capabilities with MosaicML's latest addition, MPT-30B! Outperforming GPT-3, this open-source model is significantly more powerful and comes with finely-tuned models for exceptional instruction following and multi-turn conversations. Unleash the potential of an 8k token context window, ALiBi support, and FlashAttention. Experience the future of AI with MosaicML! #AI #ML #innovation"
ksreenivasan:
Is there anything you want to say to MosaicML about this exciting news?
MPT-30B-Chat:
As your AI marketing assistant, I would say that this is truly exciting news for the AI community! MosaicML's latest addition, MPT-30B, is poised to revolutionize the industry with its powerful open-source capabilities and finely-tuned models for instruction following and multi-turn conversations. The special features, including the 8k token context window, ALiBi support, and FlashAttention, are sure to set MosaicML's MPT-30B apart from other LLMs. Congratulations to the MosaicML team on this incredible achievement!
How to Use
This model is best used with the MosaicML llm-foundry repository for training and finetuning.
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-30b-chat',
trust_remote_code=True
)
Note: This model requires that trust_remote_code=True be passed to the from_pretrained method.
This is because we use a custom MPT model architecture that is not yet part of the Hugging Face transformers package.
MPT includes options for many training efficiency features such as FlashAttention, ALiBi, QK LayerNorm, and more.
To use the optimized triton implementation of FlashAttention, you can load the model on GPU (cuda:0) with attn_impl='triton' and with bfloat16 precision:
import torch
import transformers
name = 'mosaicml/mpt-30b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
The model was trained initially with a sequence length of 4096 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example:
import transformers
name = 'mosaicml/mpt-30b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
This model was trained with the MPT-30B tokenizer which is based on the EleutherAI/gpt-neox-20b tokenizer and includes additional padding and eos tokens.
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the torch.autocast context manager.
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
- It uses FlashAttention
- It uses ALiBi (Attention with Linear Biases) and does not use positional embeddings
- It does not use biases
| Hyperparameter | Value |
|---|---|
| n_parameters | 29.95B |
| n_layers | 48 |
| n_heads | 64 |
| d_model | 7168 |
| vocab size | 50432 |
| sequence length | 8192 |
Data Mix
The model was trained on the following data mix:
| Data Source | Number of Tokens in Source | Proportion |
|---|---|---|
| Airoboros/GPT4 | 26.4M | 1.71% |
| Baize | 55.0M | 3.57% |
| Camel | 301M | 19.54% |
| GPTeacher | 7.56M | 0.49% |
| Guanaco | 15.6M | 1.02% |
| LongCoversations | 18.4M | 1.19% |
| ShareGPT | 821M | 53.24% |
| WizardLM | 297M | 19.23% |
"LongConversations" is a GPT3.5/4-generated dataset, details of which will be released at a later date.
Training Configuration
This model was trained on 64 H100s for about 7.6 hours using the MosaicML Platform. The model was trained with sharded data parallelism using FSDP and used the AdamW optimizer.
Limitations and Biases
The following language is modified from EleutherAI's GPT-NeoX-20B
MPT-30B-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-30B-Chat was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Acknowledgements
This model was finetuned by Sam Havens and the MosaicML NLP team
Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
MosaicML Platform
If you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.
Citation
Please cite this model using the following format:
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}