<!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end -->

Kaist AI's Selfee 13B fp16

These are fp16 pytorch format model files for Kaist AI's Selfee 13B merged with Kaio Ken's SuperHOT 8K.

Kaio Ken's SuperHOT 13b LoRA is merged on to the base model, and then 8K context can be achieved during inference by using trust_remote_code=True.

Note that config.json has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.

Repositories available

How to use this model from Python code

First make sure you have Einops installed:

pip3 install auto-gptq

Then run the following code. config.json has been default to a sequence length of 8192, but you can also configure this in your Python code.

The provided modelling code, activated with trust_remote_code=True will automatically set the scale parameter from the configured max_position_embeddings. Eg for 8192, scale is set to 4.

from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse

model_name_or_path = "TheBloke/Selfee-13B-SuperHOT-8K-fp16"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192

model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
        config=config,
        trust_remote_code=True,
        device_map='auto')

# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(pipe(prompt_template)[0]['generated_text'])

Using other UIs: monkey patch

Provided in the repo is llama_rope_scaled_monkey_patch.py, written by @kaiokendev.

It can be theoretically be added to any Python UI or custom code to enable the same result as trust_remote_code=True. I have not tested this, and it should be superseded by using trust_remote_code=True, but I include it for completeness and for interest.

<!-- footer start -->

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!

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.

Special thanks to: Luke from CarbonQuill, Aemon Algiz.

Patreon special mentions: RoA, Lone Striker, Gabriel Puliatti, Derek Yates, Randy H, Jonathan Leane, Eugene Pentland, Karl Bernard, Viktor Bowallius, senxiiz, Daniel P. Andersen, Pierre Kircher, Deep Realms, Cory Kujawski, Oscar Rangel, Fen Risland, Ajan Kanaga, LangChain4j, webtim, Nikolai Manek, Trenton Dambrowitz, Raven Klaugh, Kalila, Khalefa Al-Ahmad, Chris McCloskey, Luke @flexchar, Ai Maven, Dave, Asp the Wyvern, Sean Connelly, Imad Khwaja, Space Cruiser, Rainer Wilmers, subjectnull, Alps Aficionado, Willian Hasse, Fred von Graf, Artur Olbinski, Johann-Peter Hartmann, WelcomeToTheClub, Willem Michiel, Michael Levine, Iucharbius , Spiking Neurons AB, K, biorpg, John Villwock, Pyrater, Greatston Gnanesh, Mano Prime, Junyu Yang, Stephen Murray, John Detwiler, Luke Pendergrass, terasurfer , Pieter, zynix , Edmond Seymore, theTransient, Nathan LeClaire, vamX, Kevin Schuppel, Preetika Verma, ya boyyy, Alex , SuperWojo, Ghost , Joseph William Delisle, Matthew Berman, Talal Aujan, chris gileta, Illia Dulskyi.

Thank you to all my generous patrons and donaters!

<!-- footer end -->

Original model card: Kaio Ken's SuperHOT 8K

SuperHOT Prototype 2 w/ 8K Context

This is a second prototype of SuperHOT, a NSFW focused LoRA, this time 7B with 8K context and no RLHF, using the same technique described in the github blog.

Looking for Merged & Quantized Models?

Make some please :)

Using the monkey-patch?

You will NEED to apply the monkeypatch or, if you are already using the monkeypatch, change the scaling factor to 0.25 and the maximum sequence length to 8192

The monkeypatch is only necessary if you are using a front-end/back-end that does not already support scaling and said front-end/back-end is Python-based (i.e. Huggingface Transformers). To apply the patch, you will need to copy the llama_rope_scaled_monkey_patch.py into your working directory and call the exported function replace_llama_rope_with_scaled_rope at the very start of your Python program. It will modify the Transformers library's implementation of RoPE to properly apply the scaling factor.

Using Oobabooga with Exllama?

Switch your loader to exllama or exllama_hf Add the arguments max_seq_len 8192 and compress_pos_emb 4. While the model may work well with compress_pos_emb 2, it was trained on 4, so that is what I advocate for you to use

Example in the command-line:

In the UI, you will see the loader option in the Models tab. Once you select either exllama or exllama_hf, the max_seq_len and compress_pos_emb settings will appear.

Training Details

I trained the LoRA with the following configuration:

Original model card: Kaist AI's Selfee 13B

<!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end -->

Kaist AI's Selfee 13B GGML

This repo contains fp16 pytorch format model files for Kaist AI's Selfee 13B.

It is the result of merging the diff at the above repo with base Llama 13B, then converting fp32 to fp16.

Repositories available

<!-- footer start -->

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!

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.

Special thanks to: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions: 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!

<!-- footer end -->

Original model card: Kaist AI's Selfee 13B

<p align="center" width="100%"> <a href="https://kaistai.github.io/SelFee/demo" target="_blank"><img src="https://raw.githubusercontent.com/kaistAI/SelFee/main/assets/llama_selfie.png" alt="KAIST-Selfee" style="width: 30%; min-width: 200px; display: block; margin: auto;"></a> </p>

SelFee: Iterative Self-Revising LLM Empowered by <br/> Self-Feedback Generation

Code License Data License Python 3.9+ Code style: black

News

[May 31, 2023] Initial release: We released the first version of SelFee! Check out the <a href="https://kaistai.github.io/SelFee/">blog post</a> for more details.

Overview

This is the repository for the KAIST SelFee project, which aims to build and share an instruction-following LLaMA model. This repo mainly has five contents:

This repository is based on the Stanford-Alpaca and Vicuna repository. Thanks to all the contributors for these awesome repositories!! 🙌

We highly recommend you read our blog post for more details about the model.

Data Release

For data collection, we collected datasets from five different fields. These are the Stanford Alpaca dataset, math collection, code collection, Flan collection, and ShareGPT. We provide code that we used to make a dataset for training. We also provide code how we preprocessed ShareGPT. For ShareGPT, we only use the first (question, answer) pair from human and GPT, respectively. We only use instances which are classified as english,and filter instance which is not a form of question. For other datsets, we do not need special data collection method.

Data Generation Process

To train our model with high-quality instructions and answer pairs, we utilized data augmentation using OpenAI API calls. The process involved three steps. <br> Firstly, we collected various instructions from multiple fields and fed them to ChatGPT to generate answers. <br> Secondly, we gathered feedback on the generated answer by querying ChatGPT again and asked it to determine if the initial answer required any revision. <br> Thirdly, if a revision was necessary, we passed the instruction, initial answer, and feedback pair to ChatGPT to generate a revised answer and its feedback pair. We repeated the process until we received feedback that required no further revision or hit the maximum iteration. However, due to the token limitation of the ChatGPT API, we had to truncate some instances that needed more than 4096 tokens while augmenting.<br> You can see the details with command here.<br> *We provide the whole dataset after collection and augmentation using huggingface(code), so you can either use the code or follow our data merging step to replicate the training dataset. Feel free to use any of them!

Training

We utilize <a href="https://github.com/lm-sys/FastChat">FastChat</a> to train the model. Given the instruction, we fine-tune the model to generate the answer and feedback chain (including the revisions).<br>

To reproduce the training procedure, here are the steps. <br>

pip install -r requirements.txt

torchrun --nproc_per_node=4 train/train_mem.py \
    --model_name_or_path llama-7b \
    --data_path outputs/feedback_gpt_3.5_turbo_merged_whole.json \
    --bf16 True \
    --output_dir ckpt/selfee-7b \
    --num_train_epochs 3 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 16 \
    --gradient_accumulation_steps 2 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 5000 \
    --save_total_limit 1 \
    --learning_rate 2e-5 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --fsdp "shard_grad_op auto_wrap" \
    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
    --tf32 True \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --training_objective full \

The hyperparameters are as follows, following Vicuna and Alpaca.

Hyperparameter Global Batch Size Learning rate Epochs Max length Weight decay
SelFee (7B, 13B) 128 2e-5 3 2048 0

Inference

<b>Restoring checkpoint using diff</b><br> We provide diff weight and code which can restore the same model with SelFee. To restore the original SelFee weight, you first need to convert the Meta's original LLAMA checkpoint into huggingface format into your local machine. Once you are done, you can restore the same checkpoint of our model by using the following command

python inference/apply_delta.py --path_raw {path_to_llama_7b} --path_tuned /ckpt/selfee-7b --path_diff kaist-ai/selfee-7b-delta

<b>Autonomous Inference Mode</b><br>

Because SelFee is trained to generate iterative feedback and revisions until the response is satisfying, it automatically generates iterative feedback and revisions on a single forward pass. The model autonomously decides when to stop generating revisions based on the feedback. If the feedback chain ends with sequences like Revision is not needed., the model autonomously terminates generation. <br>

For autonomous inference mode,

python inference/inference.py --model-path "ckpt/selfee-7b" --model-id "selfee" --question-file "evaluation/template/question.jsonl" --answer-file "evaluation/answer/selfee_7b_autonomous.jsonl"

<b>Revision Enforce Inference Mode</b><br> We observed that increasing the minimum number of required revisions corresponds to a corresponding increase in performance. To enforce revisions, we automatically replace sequences such as Revision is not needed. into Revision is needed. during self-feedback generation. Because SelFee is trained to generate Revision {index}: after the sequence of Revision is needed., the model would continually revise the answer.

For revision enforce inference mode, use the max-num-revision argument.

python inference/inference.py --model-path "ckpt/selfee-7b" --model-id "selfee" --question-file "evaluation/template/question.jsonl" --answer-file "evaluation/answer/selfee_7b_enforce_3_revision.jsonl" --max-num-revision 3

Evaluation

Following evaluation setting of Vicuna, we evaluate on 80 diverse queries and utilize GPT-4 language model as the evaluator, scoring a model's response relative to ChatGPT's response. One of the difference with Vicuna evaluation is that due to positional bias of GPT-4, we employ a bidirectional evaluation setting. This means that each evaluation instance is inferred twice, depending on its position.<br>

We release the inference result of SelFee in the folder of evaluation/answer and also the scores generated by GPT-4 in the folder of evaluation/review. <br>

GPT-4 Automatic Evaluation

First, you need to get your API key to get access to the GPT-4 API.

export OPENAI_API_KEYS={personal_key}

To compare the performance of a generation result (for example, located on evaluation/answer/file_A.jsonl) with another generation result (located on evaluation/anwer/file_B.jsonl),

python evaluation/gpt4_automatic_evaluation.py -q evaluation/template/question.jsonl -a evaluation/answer/file_A.jsonl evaluation/answer/file_B.jsonl -p evaluation/template/prompt.jsonl -r evaluation/template/reviewer.jsonl -o evaluation/review/A_vs_B.jsonl

To mitigate the positional bias of GPT-4 model, we apply a bidirectional evaluation setting. Therefore, automatic evaluation with opposite position is also needed.

python evaluation/gpt4_automatic_evaluation.py -q evaluation/template/question.jsonl -a evaluation/answer/file_B.jsonl evaluation/answer/file_A.jsonl -p evaluation/template/prompt.jsonl -r evaluation/template/reviewer.jsonl -o evaluation/review/B_vs_A.jsonl

Limitations

Similar to other LLaMA-finetuned models, SelFee also make some mistakes especially for math, reasoning, factuality, and coding tasks. Although our performance outperforms ChatGPT on Vicuna setting, the evaluation setting contains some limitations in terms of comprehension (limited to 80 queries), inconsistency, and unreliability. Therefore, further research for a better evaluation setting is needed. Please take these claims with a grain of salt.

Online demo

Check out the <a href="https://kaistai.github.io/SelFee/demo">demo</a>!

How to launch the demo yourself

To serve the web demo yourself, run the following commands:

  1. Run the controller
python3 -m serve.controller
  1. Run the model worker
python3 -m serve.model_worker --model-path $MODEL_PATH --port 21002 --worker-address=http://localhost:21002 --model-name=SelFee-13b
  1. Run the web server
python3 -m serve.gradio_web_server --share

You can find the serving code here.

Team members

<a href="https://seonghyeonye.github.io/)">Seonghyeon Ye*</a>, <a href="https://github.com/dreamgonfly">Yongrae Jo*</a>, <a href="https://github.com/doeyoungkim">Doyoung Kim*</a>, <a href="https://scholar.google.com/citations?user=xKrSnDoAAAAJ&hl">Sungdong Kim</a>, <a href="https://github.com/hbin0701">Hyeonbin Hwang</a>, and <a href="https://seominjoon.github.io/">Minjoon Seo</a>. <br/> (* denotes equal contribution)

Release

We have released the SelFee-7B and SelFee-13B model diff weights, which can be found with instructions here. Moreover, the training instances used to train SelFee is released on huggingface.

License

The research preview online demo is only for non-commercial use and is subject to various licenses and terms of use, including the LLaMA model <a href="https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md">License</a>, OpenAI's <a href="https://openai.com/policies/terms-of-use">Terms of Use</a> for the generated data, and ShareGPT's <a href="https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb">Privacy Practices</a>. If you suspect any violations, please reach out to us.

Citation

Please cite if you use the data or code in this repo.

@misc{selfee2023,
	author = {Ye, Seonghyeon and Jo, Yongrae and Kim, Doyoung and Kim, Sungdong and Hwang, Hyeonbin and Seo, Minjoon},
	title = {SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation},
	url = {https://kaistai.github.io/SelFee/},
	month = {May},
	year = {2023},
	howpublished = {Blog post}
}