bling phi 2 v0 - GGUF

• Model creator: llmware
• Original model: bling phi 2 v0

Description

This repo contains GGUF format model files for llmware's bling phi 2 v0.

These files were quantised using hardware kindly provided by Google Colab(Free CPU Machine).

You can also check it out easily in my GitHub repo.

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 incomplate 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.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• 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.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• 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.
• Nitro, a fast, lightweight 3mb inference server to supercharge apps with local AI, and OpenAI-compatible API server.

Repositories available

• 2, 3, 4, 5, 6, 8, 16 and 32-bit GGUF models for CPU+GPU inference
• llmware's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: BLING

System: A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
Human: {prompt}
Assistant:

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

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: mzwing/bling-phi-2-v0-GGUF, and below it, a specific filename to download, such as: bling-phi-2-v0.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 mzwing/bling-phi-2-v0-GGUF bling-phi-2-v0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

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

huggingface-cli download mzwing/bling-phi-2-v0-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 mzwing/bling-phi-2-v0-GGUF bling-phi-2-v0.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 32 -m bling-phi-2-v0.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "System: A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nHuman: {prompt}\nAssistant:"

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.

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 here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

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

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# 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 = AutoModelForCausalLM.from_pretrained("mzwing/bling-phi-2-v0-GGUF", model_file="bling-phi-2-v0.Q4_K_M.gguf", model_type="phi", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

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

• LangChain + llama-cpp-python
• LangChain + ctransformers

Thanks, and how to contribute

Thanks to Google Colab! All the quantised models in this repo are done on the awesome platform. Thanks a lot!

Thanks to llama.cpp! It inspired me to explore the inspiring AI field, thanks!

Thanks to TheBloke! Everything in this repo is a reference to him.

You are welcome to create a PullRequest! Especially for the RAM Usage!

Original model card: llmware's bling phi 2 v0

Model Card for Model ID

bling-phi-2-v0 is part of the BLING ("Best Little Instruct No GPU Required ...") model series, RAG-instruct trained on top of a Microsoft Phi-2B base model.

BLING models are fine-tuned with high-quality custom instruct datasets, designed for rapid prototyping in RAG scenarios.

For models with comparable size and performance in RAG deployments, please see:

bling-stable-lm-3b-4e1t-v0
bling-sheared-llama-2.7b-0.1
bling-red-pajamas-3b-0.1

Benchmark Tests

Evaluated against the benchmark test: RAG-Instruct-Benchmark-Tester
Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.

--Accuracy Score: 93.0 correct out of 100
--Not Found Classification: 95.0%
--Boolean: 85.0%
--Math/Logic: 82.5%
--Complex Questions (1-5): 3 (Above Average - multiple-choice, causal)
--Summarization Quality (1-5): 3 (Above Average)
--Hallucinations: No hallucinations observed in test runs.

For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).

Model Description

• Developed by: llmware
• Model type: Phi-2B
• Language(s) (NLP): English
• License: Apache 2.0
• Finetuned from model: Microsoft Phi-2B-Base

Uses

The intended use of BLING models is two-fold:

1. Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.

2. BLING models are fine-tuned on top of leading base foundation models, generally in the 1-3B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.

Direct Use

BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services, legal and regulatory industries with complex information sources.

BLING models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.

Bias, Risks, and Limitations

Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.

How to Get Started with the Model

The fastest way to get started with BLING is through direct import in transformers:

from transformers import AutoTokenizer, AutoModelForCausalLM  
tokenizer = AutoTokenizer.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
model = AutoModelForCausalLM.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  

Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The generation_test_llmware_script.py includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.

The dRAGon model was fine-tuned with a simple "<human> and <bot> wrapper", so to get the best results, wrap inference entries as:

full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"

The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:

1. Text Passage Context, and
2. Specific question or instruction based on the text passage

To get the best results, package "my_prompt" as follows:

my_prompt = {{text_passage}} + "\n" + {{question/instruction}}

If you are using a HuggingFace generation script:

# prepare prompt packaging used in fine-tuning process
new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"

inputs = tokenizer(new_prompt, return_tensors="pt")  
start_of_output = len(inputs.input_ids[0])

#   temperature: set at 0.3 for consistency of output
#   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries

outputs = model.generate(
        inputs.input_ids.to(device),
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.eos_token_id,
        do_sample=True,
        temperature=0.3,
        max_new_tokens=100,
        )

output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)  

Model Card Contact

Darren Oberst & llmware team