Model Overview
Model Features
Model Capabilities
Use Cases
đ Finance LLM - GGUF
This repository provides GGUF format model files for AdaptLLM's Finance LLM, offering various quantization options for different use cases.
đ Quick Start
Downloading the Model
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/finance-LLM-GGUF and below it, a specific filename to download, such as: finance-llm.Q4_K_M.gguf. Then click Download.
On the command line
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/finance-LLM-GGUF finance-llm.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
Running the Model
Example llama.cpp
command
Make sure you are using llama.cpp
from commit d0cee0d or later.
./main -ngl 35 -m finance-llm.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\n{system_message}\n<</SYS>>\n{prompt} [/INST]"
Change -ngl 32
to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 2048
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 â 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
⨠Features
- Multiple Quantization Options: Offers a variety of quantization methods (Q2_K, Q3_K_S, Q3_K_M, etc.) to balance between model size and quality.
- Wide Compatibility: Compatible with llama.cpp from August 27th onwards and many third - party UIs and libraries.
- Automated RoPE Scaling: For extended sequence models, the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
đĻ Installation
Installing Dependencies
To download models on the command line, you need to install the huggingface-hub
Python library:
pip3 install huggingface-hub
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer
:
pip3 install hf_transfer
đģ Usage Examples
Basic Usage
huggingface-cli download TheBloke/finance-LLM-GGUF finance-llm.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
Advanced Usage
Download multiple files at once with a pattern:
huggingface-cli download TheBloke/finance-LLM-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
đ Documentation
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
- AWQ model(s) for GPU inference.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- AdaptLLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Llama-2-Chat
[INST] <<SYS>>
{system_message}
<</SYS>>
{prompt} [/INST]
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 bpwRefer 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 |
---|---|---|---|---|---|
finance-llm.Q2_K.gguf | Q2_K | 2 | 2.83 GB | 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
finance-llm.Q3_K_S.gguf | Q3_K_S | 3 | 2.95 GB | 5.45 GB | very small, high quality loss |
finance-llm.Q3_K_M.gguf | Q3_K_M | 3 | 3.30 GB | 5.80 GB | very small, high quality loss |
finance-llm.Q3_K_L.gguf | Q3_K_L | 3 | 3.60 GB | 6.10 GB | small, substantial quality loss |
finance-llm.Q4_0.gguf | Q4_0 | 4 | 3.83 GB | 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
finance-llm.Q4_K_S.gguf | Q4_K_S | 4 | 3.86 GB | 6.36 GB | small, greater quality loss |
finance-llm.Q4_K_M.gguf | Q4_K_M | 4 | 4.08 GB | 6.58 GB | medium, balanced quality - recommended |
finance-llm.Q5_0.gguf | Q5_0 | 5 | 4.65 GB | 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
finance-llm.Q5_K_S.gguf | Q5_K_S | 5 | 4.65 GB | 7.15 GB | large, low quality loss - recommended |
finance-llm.Q5_K_M.gguf | Q5_K_M | 5 | 4.78 GB | 7.28 GB | large, very low quality loss - recommended |
finance-llm.Q6_K.gguf | Q6_K | 6 | 5.53 GB | 8.03 GB | very large, extremely low quality loss |
finance-llm.Q8_0.gguf | Q8_0 | 8 | 7.16 GB | 9.66 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.
In text-generation-webui
Under Download Model, you can enter the model repo: TheBloke/finance-LLM-GGUF and below it, a specific filename to download, such as: finance-llm.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/finance-LLM-GGUF finance-llm.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: ```shell huggingface-cli download TheBloke/finance-LLM-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](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/finance-LLM-GGUF finance-llm.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.How to run in text-generation-webui
Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 â 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
đ§ Technical Details
Model Information
Property | Details |
---|---|
Model Type | llama |
Base Model | AdaptLLM/finance-LLM |
Datasets | Open-Orca/OpenOrca, GAIR/lima, WizardLM/WizardLM_evol_instruct_V2_196k |
Metrics | accuracy |
Model Creator | AdaptLLM |
Quantized By | TheBloke |
Tags | finance |
License | other |
Quantization Details
The GGUF files in this repository use different quantization methods to balance between model size and quality. The new quantization methods (GGML_TYPE_Q2_K, GGML_TYPE_Q3_K, etc.) have specific bit - per - weight (bpw) values and block structures, as described in the "Explanation of quantisation methods" section.
đ License
This project is released under the [other] license.
â ī¸ Important Note
The above RAM figures in the "Provided files" section assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
đĄ Usage Tip
When using
text-generation-webui
, you can enter the model repo and a specific filename to download a single model file. When downloading on the command line, use thehuggingface-hub
Python library for high - speed downloads.

