TheBloke/speechless-codellama-34b-v2.0-GPTQ

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

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

---

Speechless Codellama 34B v2.0 - GPTQ

• Model creator: Jiangwen Su
• Original model: Speechless Codellama 34B v2.0

Description

This repo contains GPTQ model files for Jiangwen Su's Speechless Codellama 34B v2.0.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

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
• Jiangwen Su's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: None

{prompt}

Provided files, and GPTQ parameters

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.

Explanation of GPTQ parameters

• Bits: The bit size of the quantised model.
• GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
• Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
• Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
• GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
• Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
• ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.

Branch	Bits	GS	Act Order	Damp %	GPTQ Dataset	Seq Len	Size	ExLlama	Desc
main	4	None	Yes	0.1	Evol Instruct Code	16384	17.69 GB	Yes	4-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-4bit-128g-actorder_True	4	128	Yes	0.1	Evol Instruct Code	16384	18.33 GB	Yes	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-4bit-32g-actorder_True	4	32	Yes	0.1	Evol Instruct Code	16384	20.28 GB	Yes	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-3bit-128g-actorder_True	3	128	Yes	0.1	Evol Instruct Code	16384	14.14 GB	No	3-bit, with group size 128g and act-order. Higher quality than 128g-False.
gptq-8bit--1g-actorder_True	8	None	Yes	0.1	Evol Instruct Code	16384	34.30 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_True	8	128	Yes	0.1	Evol Instruct Code	16384	35.07 GB	No	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy.

How to download, including from branches

In text-generation-webui

To download from the main branch, enter TheBloke/speechless-codellama-34b-v2.0-GPTQ in the "Download model" box.

To download from another branch, add :branchname to the end of the download name, eg TheBloke/speechless-codellama-34b-v2.0-GPTQ:gptq-4bit-128g-actorder_True

From the command line

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

To download the main branch to a folder called speechless-codellama-34b-v2.0-GPTQ:

mkdir speechless-codellama-34b-v2.0-GPTQ
huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --local-dir speechless-codellama-34b-v2.0-GPTQ --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir speechless-codellama-34b-v2.0-GPTQ
huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir speechless-codellama-34b-v2.0-GPTQ --local-dir-use-symlinks False

More advanced huggingface-cli download usage

If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.

The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.

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:

mkdir speechless-codellama-34b-v2.0-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --local-dir speechless-codellama-34b-v2.0-GPTQ --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.

With git (not recommended)

To clone a specific branch with git, use a command like this:

git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ

Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)

How to easily download and use this model in text-generation-webui.

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/speechless-codellama-34b-v2.0-GPTQ.

• To download from a specific branch, enter for example TheBloke/speechless-codellama-34b-v2.0-GPTQ:gptq-4bit-128g-actorder_True
• see Provided Files above for the list of branches for each option.

3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: speechless-codellama-34b-v2.0-GPTQ
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.

• Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file quantize_config.json.

9. Once you're ready, click the Text Generation tab and enter a prompt to get started!

Serving this model from Text Generation Inference (TGI)

It's recommended to use TGI version 1.1.0 or later. The official Docker container is: ghcr.io/huggingface/text-generation-inference:1.1.0

Example Docker parameters:

--model-id TheBloke/speechless-codellama-34b-v2.0-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096

Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):

pip3 install huggingface-hub

from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: {response}")

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .

You can then use the following code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/speechless-codellama-34b-v2.0-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")

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

prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''

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

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, 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,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

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

Compatibility

The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.

ExLlama is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.

Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.

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!

Thanks to Clay from gpus.llm-utils.org!

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.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Jiangwen Su's Speechless Codellama 34B v2.0

speechless-codellama-34b-v2.0

• 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

Use the following datasets to fine-tune codellama/CodeLlama-34B in order to improve the model's inference and planning capabilities.

Total 153,013 samples.

• jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
• Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
• garage-bAInd/Open-Platypus: 100%, 24,926 samples.
• WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples

HumanEval

human-eval	pass@1
humaneval-python	75.61

Big Code Models Leaderboard

Models	pass@1
Phind-CodeLlama-34B-v2	71.95
WizardCoder-Python-34B-V1.0	70.73
Phind-CodeLlama-34B-Python-v1	70.22
Phind-CodeLlama-34B-v1	65.85
WizardCoder-Python-13B-V1.0	62.19
WizardCoder-15B-V1.0	58.12
CodeLlama-34B-Python	53.29
CodeLlama-34B-Instruct	50.79
CodeLlama-13B-Instruct	50.6
CodeLlama-34B	45.11
CodeLlama-13B-Python	42.89
CodeLlama-13B	35.07

NL2SQL

SQL-EVAL: 125/175 (71.43%)

Average rate of exact match: 67.43%

Average correct rate: 71.43%

• GPT4: 130/175 (74.29%)
• GPT3-Turbo-0613: 105/174 (60.00%)

lm-evaluation-harness

Open LLM Leaderboard

Metric	Value
ARC	54.35
HellaSwag	75.65
MMLU	54.67
TruthfulQA	45.21
Average	57.47

H800-80G x 2

transformers=4.33.0

flash-attn=2.1.0

bitsandbytes=0.41.1

peft=0.5.0

Training Arguments

lr	2e-4
lr_scheduler_type	cosine
weight_decay	0.0
optim	paged_adamw_8bit
flash_attention	True
rerope	False
max_new_tokens	8192
num_train_epochs	3
bits	4
lora_r	64
lora_alpha	16
lora_dropout	0.05
double_quant	True
quant_type	nf4
dataset_format	airoboros
mini_batch_size	4
grandient_accumulation_steps	16
bf16	True

epoch	3.0
etrain_loss	0.4261
etrain_runtime	1 day, 14:42:57.87
etrain_samples_per_second	3.227
etrain_steps_per_second	0.025
eeval_loss	0.4537
eeval_runtime	0:00:36.19
eeval_samples_per_second	5.525
eeval_steps_per_second	2.763

Code Llama

Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.

	Base Model	Python	Instruct
7B	codellama/CodeLlama-7b-hf	codellama/CodeLlama-7b-Python-hf	codellama/CodeLlama-7b-Instruct-hf
13B	codellama/CodeLlama-13b-hf	codellama/CodeLlama-13b-Python-hf	codellama/CodeLlama-13b-Instruct-hf
34B	codellama/CodeLlama-34b-hf	codellama/CodeLlama-34b-Python-hf	codellama/CodeLlama-34b-Instruct-hf

Model Use

To use this model, please make sure to install transformers from main until the next version is released:

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

Model capabilities:

• Code completion.
• Infilling.
• Instructions / chat.
• Python specialist.

from transformers import AutoTokenizer
import transformers
import torch

model = "codellama/CodeLlama-13b-hf"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

sequences = pipeline(
    'import socket\n\ndef ping_exponential_backoff(host: str):',
    do_sample=True,
    top_k=10,
    temperature=0.1,
    top_p=0.95,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=200,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Model Details

*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).

Model Developers Meta

Variations Code Llama comes in three model sizes, and three variants:

• Code Llama: base models designed for general code synthesis and understanding
• Code Llama - Python: designed specifically for Python
• Code Llama - Instruct: for instruction following and safer deployment

All variants are available in sizes of 7B, 13B and 34B parameters.

This repository contains the base version of the 13B parameters model.

Input Models input text only.

Output Models generate text only.

Model Architecture Code Llama is an auto-regressive language model that uses an optimized transformer architecture.

Model Dates Code Llama and its variants have been trained between January 2023 and July 2023.

Status This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.

License A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/

Research Paper More information can be found in the paper "Code Llama: Open Foundation Models for Code" or its arXiv page.

Intended Use

Intended Use Cases Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.

Out-of-Scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.

Hardware and Software

Training Factors We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.

Carbon Footprint In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.

Training Data

All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the research paper for details).

Evaluation Results

See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.

Ethical Considerations and Limitations

Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see the Responsible Use Guide available available at https://ai.meta.com/llama/responsible-user-guide.