Edit model card

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Bagel 7B v0.1 - GGUF

Model creator: Jon Durbin
Original model: Bagel 7B v0.1

Description

This repo contains GGUF format model files for Jon Durbin's Bagel 7B v0.1.

These files were quantised using hardware kindly provided by Massed Compute.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

llama.cpp. The source project for GGUF. Offers a CLI and a server option.
text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

Repositories available

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

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

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
bagel-7b-v0.1.Q2_K.gguf	Q2_K	2	3.08 GB	5.58 GB	smallest, significant quality loss - not recommended for most purposes
bagel-7b-v0.1.Q3_K_S.gguf	Q3_K_S	3	3.16 GB	5.66 GB	very small, high quality loss
bagel-7b-v0.1.Q3_K_M.gguf	Q3_K_M	3	3.52 GB	6.02 GB	very small, high quality loss
bagel-7b-v0.1.Q3_K_L.gguf	Q3_K_L	3	3.82 GB	6.32 GB	small, substantial quality loss
bagel-7b-v0.1.Q4_0.gguf	Q4_0	4	4.11 GB	6.61 GB	legacy; small, very high quality loss - prefer using Q3_K_M
bagel-7b-v0.1.Q4_K_S.gguf	Q4_K_S	4	4.14 GB	6.64 GB	small, greater quality loss
bagel-7b-v0.1.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	6.87 GB	medium, balanced quality - recommended
bagel-7b-v0.1.Q5_0.gguf	Q5_0	5	5.00 GB	7.50 GB	legacy; medium, balanced quality - prefer using Q4_K_M
bagel-7b-v0.1.Q5_K_S.gguf	Q5_K_S	5	5.00 GB	7.50 GB	large, low quality loss - recommended
bagel-7b-v0.1.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	7.63 GB	large, very low quality loss - recommended
bagel-7b-v0.1.Q6_K.gguf	Q6_K	6	5.94 GB	8.44 GB	very large, extremely low quality loss
bagel-7b-v0.1.Q8_0.gguf	Q8_0	8	7.70 GB	10.20 GB	very large, extremely low quality loss - not recommended

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 download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

LM Studio
LoLLMS Web UI
Faraday.dev

In `text-generation-webui`

Under Download Model, you can enter the model repo: TheBloke/bagel-7B-v0.1-GGUF and below it, a specific filename to download, such as: bagel-7b-v0.1.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/bagel-7B-v0.1-GGUF bagel-7b-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage (click to read)

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/bagel-7B-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/bagel-7B-v0.1-GGUF bagel-7b-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Example `llama.cpp` command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 35 -m bagel-7b-v0.1.Q4_K_M.gguf --color -c 32768 --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.\n\n### Instruction:\n{prompt}\n\n### Response:"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 32768 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in `text-generation-webui`

Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.

How to load this model in Python code, using llama-cpp-python

For full documentation, please see: llama-cpp-python docs.

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python

Simple llama-cpp-python example code

from llama_cpp import Llama

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
  model_path="./bagel-7b-v0.1.Q4_K_M.gguf",  # Download the model file first
  n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
)

# Simple inference example
output = llm(
  "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # Prompt
  max_tokens=512,  # Generate up to 512 tokens
  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
  echo=True        # Whether to echo the prompt
)

# Chat Completion API

llm = Llama(model_path="./bagel-7b-v0.1.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are a story writing assistant."},
        {
            "role": "user",
            "content": "Write a story about llamas."
        }
    ]
)

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

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: Aemon Algiz.

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.

Original model card: Jon Durbin's Bagel 7B v0.1

A bagel, with everything (except DPO)

Overview

This is the pre-DPO version of the mistral-7b model fine-tuned with https://github.com/jondurbin/bagel

You probably want the higher performing model that underwent DPO: https://huggingface.co/jondurbin/bagel-dpo-7b-v0.1

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

ai2_arc
- Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent.
airoboros
- Variety of categories of synthetic instructions generated by gpt-4.
apps
- Python coding dataset with 10k problems.
belebele
- Multi-lingual reading comprehension dataset.
boolq
- Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)
cinematika (instruction and plain text)
- RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.
drop
- More reading comprehension.
gutenberg (plain text)
- Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize
lmsys_chat_1m (only gpt-4 items, also used for DPO)
- Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.
mathinstruct
- Composite dataset with a variety of math-related tasks and problem/question formats.
mmlu
- Massive Multitask Language Understanding - a wide variety of questions about various subject matters.
natural_instructions
- Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)
openbookqa
- Question answering dataset.
piqa
- Phyiscal interaction question answering.
python_alpaca
- Python instruction response pairs, validated as functional.
rosetta_code
- Code problems and solutions in a variety of programming languages taken from rosettacode.org.
slimorca
- Collection of ~500k gpt-4 verified chats from OpenOrca.
spider
- SQL-targeted dataset.
squad_v2
- Contextual question answering (RAG).
synthia
- GPT-4 generated data using advanced prompting from Migel Tissera.
winogrande
- Fill in the blank style prompts.

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:

{bos}<|im_start|>{role}
{text}
<|im_end|>{eos}

I just changed it to:

{bos}{role}
{text}
{eos}

In practice, this would mean tokenization code like such:

tokenizer = AutoTokenizer.from_pretrained('mistralai/mistral-7b-v0.1')

input_str = f"""system
You are a goat.
{tokenizer.eos_token}
{tokenizer.bos_token}user
Tell me how to fry an egg.
{tokenizer.eos_token}
{tokenizer.bos_token}assistant
"""

inputs = tokenizer(input_str, return_tensors="pt")

Llama-2 chat

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Fine-tune

Note: I actually used my fork of qlora's train.py for this, but I'm porting it to a minified version here, not tested yet!

More notes: I stopped the fine-tune around 50% because of budget constraints - it's a lot of data...

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Deepspeed configuration:

{
  "gradient_accumulation_steps": "auto",
  "gradient_clipping": "auto",
  "train_batch_size": "auto",
  "train_micro_batch_size_per_gpu": "auto",
  "bf16": {
    "enabled": true
  },
  "zero_optimization": {
    "stage": 2,
    "contiguous_gradients": true,
    "overlap_comm": true,
    "reduce_scatter": true,
    "reduce_bucket_size": 5e8,
    "allgather_bucket_size": 5e8
  }
}

Downloads last month: 305

GGUF

Model size

7.24B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API

Inference API (serverless) has been turned off for this model.

Model tree for TheBloke/bagel-7B-v0.1-GGUF

Base model

jondurbin/bagel-7b-v0.1

Quantized

(3)

this model

TheBloke
/

bagel-7B-v0.1-GGUF

Bagel 7B v0.1 - GGUF

Description

About GGUF

Repositories available

Prompt template: Alpaca

Compatibility

Explanation of quantisation methods

Provided files

How to download GGUF files

In `text-generation-webui`

On the command line, including multiple files at once

Example `llama.cpp` command

How to run in `text-generation-webui`

How to run from Python code

How to load this model in Python code, using llama-cpp-python

First install the package

Simple llama-cpp-python example code

How to use with LangChain

Discord

Thanks, and how to contribute

Original model card: Jon Durbin's Bagel 7B v0.1

A bagel, with everything (except DPO)

Overview

Data selection.

SFT data sources

Prompt formatting

Alpaca (sort of)

Vicuna

ChatML (sort of)

Llama-2 chat

Fine-tune

Model tree for TheBloke/bagel-7B-v0.1-GGUF

Datasets used to train TheBloke/bagel-7B-v0.1-GGUF

Bagel 7B v0.1 - GGUF

Description

About GGUF

Repositories available

Prompt template: Alpaca

Compatibility

Explanation of quantisation methods

Provided files

How to download GGUF files

In text-generation-webui

On the command line, including multiple files at once

Example llama.cpp command

How to run in text-generation-webui

How to run from Python code

How to load this model in Python code, using llama-cpp-python

First install the package

Simple llama-cpp-python example code

How to use with LangChain

Discord

Thanks, and how to contribute

Original model card: Jon Durbin's Bagel 7B v0.1

A bagel, with everything (except DPO)

Overview

Data selection.

SFT data sources

Prompt formatting

Alpaca (sort of)

Vicuna

ChatML (sort of)

Llama-2 chat

Fine-tune

Model tree for TheBloke/bagel-7B-v0.1-GGUF

Datasets used to train TheBloke/bagel-7B-v0.1-GGUF

In `text-generation-webui`

Example `llama.cpp` command

How to run in `text-generation-webui`