Hugging Face's logo

TheBloke
/
Phind-CodeLlama-34B-v2-GGUF

Transformers
GGUF
llama
code llama
Eval Results
text-generation-inference
Model card Files Community
3
Phind-CodeLlama-34B-v2-GGUF / README.md
TheBloke's picture
TheBloke
Upload README.md
ab837f8
preview code
|
raw
history blame
No virus
18.6 kB
metadata
inference: false
license: llama2
model-index:
  - name: Phind-CodeLlama-34B-v1
    results:
      - dataset:
          name: HumanEval
          type: openai_humaneval
        metrics:
          - name: pass@1
            type: pass@1
            value: 73.8%
            verified: false
        task:
          type: text-generation
model_creator: Phind
model_link: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
model_name: CodeLlama 34B v2
model_type: llama
quantized_by: TheBloke
tags:
  - code llama
TheBlokeAI

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

CodeLlama 34B v2 - GGUF

Description

This repo contains GGUF format model files for Phind's CodeLlama 34B v2.

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.

The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

Here are a list of clients and libraries that are known to support GGUF:

  • llama.cpp.
  • text-generation-webui, the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
  • KoboldCpp, now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
  • LM Studio, version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, should now work, choose the c_transformers backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
  • ctransformers, now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
  • candle, added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

Prompt template: Phind 

### System Prompt
{system_message}

### User Message
{prompt}

### Assistant

Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9

They are now also compatible with many third party UIs and libraries - please see the list at the top of the 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
phind-codellama-34b-v2.Q2_K.gguf Q2_K 2 14.21 GB 16.71 GB smallest, significant quality loss - not recommended for most purposes
phind-codellama-34b-v2.Q3_K_S.gguf Q3_K_S 3 14.61 GB 17.11 GB very small, high quality loss
phind-codellama-34b-v2.Q3_K_M.gguf Q3_K_M 3 16.28 GB 18.78 GB very small, high quality loss
phind-codellama-34b-v2.Q3_K_L.gguf Q3_K_L 3 17.77 GB 20.27 GB small, substantial quality loss
phind-codellama-34b-v2.Q4_0.gguf Q4_0 4 19.05 GB 21.55 GB legacy; small, very high quality loss - prefer using Q3_K_M
phind-codellama-34b-v2.Q4_K_S.gguf Q4_K_S 4 19.15 GB 21.65 GB small, greater quality loss
phind-codellama-34b-v2.Q4_K_M.gguf Q4_K_M 4 20.22 GB 22.72 GB medium, balanced quality - recommended
phind-codellama-34b-v2.Q5_0.gguf Q5_0 5 23.24 GB 25.74 GB legacy; medium, balanced quality - prefer using Q4_K_M
phind-codellama-34b-v2.Q5_K_S.gguf Q5_K_S 5 23.24 GB 25.74 GB large, low quality loss - recommended
phind-codellama-34b-v2.Q5_K_M.gguf Q5_K_M 5 23.84 GB 26.34 GB large, very low quality loss - recommended
phind-codellama-34b-v2.Q6_K.gguf Q6_K 6 27.68 GB 30.18 GB very large, extremely low quality loss
phind-codellama-34b-v2.Q8_0.gguf Q8_0 8 35.86 GB 38.36 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.

Example llama.cpp command

Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.

For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.

./main -t 10 -ngl 32 -m phind-codellama-34b-v2.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System Prompt\nYou are a story writing assistant.\n\n### User Message\nWrite a story about llamas\n\n### Assistant"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8. If offloading all layers to GPU, set -t 1.

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

Change -c 4096 to the desired sequence length for this model. 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 from Python using ctransformers

First install the package 

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models 

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("TheBloke/Phind-CodeLlama-34B-v2-GGUF", model_file="phind-codellama-34b-v2.q4_K_M.gguf", model_type="llama", gpu_layers=50)

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

How to use with LangChain

Here's guides on using llama-cpp-python or 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!

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: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Phind's CodeLlama 34B v2

Phind-CodeLlama-34B-v2

We've fine-tuned Phind-CodeLlama-34B-v1 on an additional 1.5B tokens high-quality programming-related data, achieving 73.8% pass@1 on HumanEval. It's the current state-of-the-art amongst open-source models.

Furthermore, this model is instruction-tuned on the Alpaca/Vicuna format to be steerable and easy-to-use.

More details can be found on our blog post.

Model Details

This model is fine-tuned from Phind-CodeLlama-34B-v1 and achieves 73.8% pass@1 on HumanEval.

Phind-CodeLlama-34B-v2 is multi-lingual and is proficient in Python, C/C++, TypeScript, Java, and more.

Dataset Details

We fined-tuned on a proprietary dataset of 1.5B tokens of high quality programming problems and solutions. This dataset consists of instruction-answer pairs instead of code completion examples, making it structurally different from HumanEval. LoRA was not used -- both models are a native finetune. We used DeepSpeed ZeRO 3 and Flash Attention 2 to train these models in 15 hours on 32 A100-80GB GPUs. We used a sequence length of 4096 tokens.

How to Get Started with the Model

Make sure to install Transformers from the main git branch:

pip install git+https://github.com/huggingface/transformers.git

How to Prompt the Model

This model accepts the Alpaca/Vicuna instruction format.

For example:

### System Prompt
You are an intelligent programming assistant.

### User Message
Implement a linked list in C++

### Assistant
...

How to reproduce HumanEval Results

To reproduce our results:


from transformers import AutoTokenizer, LlamaForCausalLM
from human_eval.data import write_jsonl, read_problems
from tqdm import tqdm

# initialize the model

model_path = "Phind/Phind-CodeLlama-34B-v2"
model = LlamaForCausalLM.from_pretrained(model_path, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)

# HumanEval helper

def generate_one_completion(prompt: str):
    tokenizer.pad_token = tokenizer.eos_token
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=4096)

    # Generate
    generate_ids = model.generate(inputs.input_ids.to("cuda"), max_new_tokens=384, do_sample=True, top_p=0.75, top_k=40, temperature=0.1)
    completion = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
    completion = completion.replace(prompt, "").split("\n\n\n")[0]

    return completion

# perform HumanEval
problems = read_problems()

num_samples_per_task = 1
samples = [
    dict(task_id=task_id, completion=generate_one_completion(problems[task_id]["prompt"]))
    for task_id in tqdm(problems)
    for _ in range(num_samples_per_task)
]
write_jsonl("samples.jsonl", samples)

# run `evaluate_functional_correctness samples.jsonl` in your HumanEval code sandbox

Bias, Risks, and Limitations

This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.

Training details

  • Hardware Type: 32x A100-80GB
  • Hours used: 480 GPU-hours
  • Cloud Provider: AWS
  • Compute Region: us-east-1