Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by Massed Compute.
This may not be a complete list; if you know of others, please let me know!
Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
Explanation of GPTQ parameters
Bits: The bit size of the quantised model.
GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.
Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
pip3 install huggingface-hub
python
1from huggingface_hub import InferenceClient
23endpoint_url ="https://your-endpoint-url-here"45prompt ="Tell me about AI"6prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
78### Instruction:
9{prompt}1011### Response:
12'''1314client = InferenceClient(endpoint_url)15response = client.text_generation(prompt,16 max_new_tokens=128,17 do_sample=True,18 temperature=0.7,19 top_p=0.95,20 top_k=40,21 repetition_penalty=1.1)2223print(f"Model output: {response}")
Python code example: inference from this GPTQ model
Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
shell
1pip3 install --upgrade transformers optimum
2# If using PyTorch 2.1 + CUDA 12.x:3pip3 install --upgrade auto-gptq
4# or, if using PyTorch 2.1 + CUDA 11.x:5pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
1from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
23model_name_or_path ="TheBloke/bagel-7B-v0.1-GPTQ"4# To use a different branch, change revision5# For example: revision="gptq-4bit-32g-actorder_True"6model = AutoModelForCausalLM.from_pretrained(model_name_or_path,7 device_map="auto",8 trust_remote_code=False,9 revision="main")1011tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)1213prompt ="Tell me about AI"14prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
1516### Instruction:
17{prompt}1819### Response:
20'''2122print("\n\n*** Generate:")2324input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()25output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)26print(tokenizer.decode(output[0]))2728# Inference can also be done using transformers' pipeline2930print("*** Pipeline:")31pipe = pipeline(32"text-generation",33 model=model,34 tokenizer=tokenizer,35 max_new_tokens=512,36 do_sample=True,37 temperature=0.7,38 top_p=0.95,39 top_k=40,40 repetition_penalty=1.141)4243print(pipe(prompt_template)[0]['generated_text'])
Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
ExLlama is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
Discord
For further support, and discussions on these models and AI in general, join us at:
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 special mentions: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
The only benefit to this model is that it is less "truthful", for roleplaying and other types of scenarios that may benefit more from the SFT-only tune.
Data selection.
The first step in the process is creating a dataset.
In this case, we're actually creating a composite dataset, consisting of both supervised fine-tuning data (SFT) and direct preference optimization (DPO) data.
All instruction data, that is, data that is not plain text (like project Gutenberg and items from Cinematika) or DPO, is converted into ShareGPT format so it's easier to work with.
See the corresponding code in bagel/data_sources/*.py in the repo linked above for full implementation for each data source.
Deduplication is done by creating a uuid v5 of the instruction/text, then only adding items not previously seen (where datasets are loaded in order of the confidence score I assign them).
This means that if an instruction is in data source "Foo" with confidence 4 as well as in data source "Bar" with confidence score 2, only the entry from "Foo" will be taken.
SFT data sources
Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check
Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss).
Prompt formatting
In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta).
I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format.
This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate.
Alpaca (sort of)
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt, if provided}
{instruction}
### Response:
The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an ### Input: block, so the inputs are just in the instruction section.
Vicuna
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
ChatML (sort of)
I don't really understand the point of having special tokens for <|im_start|> and <|im_end|>, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong).
So, instead of:
text
1{bos}<|im_start|>{role}
2{text}
3<|im_end|>{eos}
I just changed it to:
text
1{bos}{role}
2{text}
3{eos}
In practice, this would mean tokenization code like such:
python
1tokenizer = AutoTokenizer.from_pretrained('mistralai/mistral-7b-v0.1')23input_str =f"""system
4You are a goat.
5{tokenizer.eos_token}6{tokenizer.bos_token}user
7Tell me how to fry an egg.
8{tokenizer.eos_token}9{tokenizer.bos_token}assistant
10"""1112inputs = tokenizer(input_str, return_tensors="pt")
If you really want to use <|im_start|> and <|im_end|>, just update your tokenizer_config.json to use <|im_start|> instead of <s> and <|im_end|> instead of </s> and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune.
