RichardErkhov/AdaptLLM_-_finance-chat-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

finance-chat - GGUF

• Model creator: https://huggingface.co/AdaptLLM/
• Original model: https://huggingface.co/AdaptLLM/finance-chat/

Name	Quant method	Size
finance-chat.Q2_K.gguf	Q2_K	2.36GB
finance-chat.IQ3_XS.gguf	IQ3_XS	2.6GB
finance-chat.IQ3_S.gguf	IQ3_S	2.75GB
finance-chat.Q3_K_S.gguf	Q3_K_S	2.75GB
finance-chat.IQ3_M.gguf	IQ3_M	2.9GB
finance-chat.Q3_K.gguf	Q3_K	3.07GB
finance-chat.Q3_K_M.gguf	Q3_K_M	3.07GB
finance-chat.Q3_K_L.gguf	Q3_K_L	3.35GB
finance-chat.IQ4_XS.gguf	IQ4_XS	3.4GB
finance-chat.Q4_0.gguf	Q4_0	3.56GB
finance-chat.IQ4_NL.gguf	IQ4_NL	3.58GB
finance-chat.Q4_K_S.gguf	Q4_K_S	3.59GB
finance-chat.Q4_K.gguf	Q4_K	3.8GB
finance-chat.Q4_K_M.gguf	Q4_K_M	3.8GB
finance-chat.Q4_1.gguf	Q4_1	3.95GB
finance-chat.Q5_0.gguf	Q5_0	4.33GB
finance-chat.Q5_K_S.gguf	Q5_K_S	4.33GB
finance-chat.Q5_K.gguf	Q5_K	4.45GB
finance-chat.Q5_K_M.gguf	Q5_K_M	4.45GB
finance-chat.Q5_1.gguf	Q5_1	4.72GB
finance-chat.Q6_K.gguf	Q6_K	5.15GB
finance-chat.Q8_0.gguf	Q8_0	6.67GB

Original model description:

language: - en license: llama2 tags: - finance datasets: - Open-Orca/OpenOrca - GAIR/lima - WizardLM/WizardLM_evol_instruct_V2_196k metrics: - accuracy pipeline_tag: text-generation model-index: - name: finance-chat results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 53.75 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 76.6 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 50.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 44.54 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 75.69 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 18.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/finance-chat name: Open LLM Leaderboard

Adapting Large Language Models to Domains via Continual Pre-Training

This repo contains the domain-specific chat model developed from LLaMA-2-Chat-7B, using the method in our ICLR 2024 paper Adapting Large Language Models via Reading Comprehension.

We explore continued pre-training on domain-specific corpora for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to transform large-scale pre-training corpora into reading comprehension texts, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. Our 7B model competes with much larger domain-specific models like BloombergGPT-50B.

🤗 [2024/6/21] We release the 2nd version of AdaptLLM at Instruction-Pretrain, effective for both pre-training from scratch and continual pre-training 🤗

**************************** Updates ****************************

• 2024/6/22: Released the benchmarking code.
• 2024/6/21: 👏🏻 Released the 2nd version of AdaptLLM at Instruction-Pretrain 👏🏻
• 2024/1/16: 🎉 Our research paper has been accepted by ICLR 2024!!!🎉
• 2023/12/19: Released our 13B base models developed from LLaMA-1-13B.
• 2023/12/8: Released our chat models developed from LLaMA-2-Chat-7B.
• 2023/9/18: Released our paper, code, data, and base models developed from LLaMA-1-7B.

Domain-Specific LLaMA-1

LLaMA-1-7B

In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: Biomedicine-LLM, Finance-LLM and Law-LLM, the performances of our AdaptLLM compared to other domain-specific LLMs are:

LLaMA-1-13B

Moreover, we scale up our base model to LLaMA-1-13B to see if our method is similarly effective for larger-scale models, and the results are consistently positive too: Biomedicine-LLM-13B, Finance-LLM-13B and Law-LLM-13B.

Domain-Specific LLaMA-2-Chat

Our method is also effective for aligned models! LLaMA-2-Chat requires a specific data format, and our reading comprehension can perfectly fit the data format by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: Biomedicine-Chat, Finance-Chat and Law-Chat

For example, to chat with the finance-chat model:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat")
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat")

# Put your input here:
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange
MMM Chicago Stock Exchange, Inc.
1.500% Notes due 2026 MMM26 New York Stock Exchange
1.750% Notes due 2030 MMM30 New York Stock Exchange
1.500% Notes due 2031 MMM31 New York Stock Exchange

Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''

# Apply the prompt template and system prompt of LLaMA-2-Chat demo for chat models (NOTE: NO prompt template is required for base models!)
our_system_prompt = "\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n" # Please do NOT change this
prompt = f"<s>[INST] <<SYS>>{our_system_prompt}<</SYS>>\n\n{user_input} [/INST]"

# # NOTE:
# # If you want to apply your own system prompt, please integrate it into the instruction part following our system prompt like this:
# your_system_prompt = "Please, check if the answer can be inferred from the pieces of context provided."
# prompt = f"<s>[INST] <<SYS>>{our_system_prompt}<</SYS>>\n\n{your_system_prompt}\n{user_input} [/INST]"

inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
outputs = model.generate(input_ids=inputs, max_length=4096)[0]

answer_start = int(inputs.shape[-1])
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)

print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')

Domain-Specific Tasks

To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: biomedicine-tasks, finance-tasks, and law-tasks.

Note: those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.26
AI2 Reasoning Challenge (25-Shot)	53.75
HellaSwag (10-Shot)	76.60
MMLU (5-Shot)	50.16
TruthfulQA (0-shot)	44.54
Winogrande (5-shot)	75.69
GSM8k (5-shot)	18.80

Citation

If you find our work helpful, please cite us:

@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}