---
base_model: uukuguy/speechless-codellama-34b-v2.0
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
inference: false
language:
- en
library_name: transformers
license: llama2
model-index:
- name: SpeechlessCoder
results:
- dataset:
name: HumanEval
type: openai_humaneval
metrics:
- name: pass@1
type: pass@1
value: 75.61
verified: false
task:
type: text-generation
model_creator: Jiangwen Su
model_name: Speechless Codellama 34B v2.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- llama-2
- code
---
# Speechless Codellama 34B v2.0 - AWQ
- Model creator: [Jiangwen Su](https://huggingface.co/uukuguy)
- Original model: [Speechless Codellama 34B v2.0](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
## Description
This repo contains AWQ model files for [Jiangwen Su's Speechless Codellama 34B v2.0](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.
It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).
Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF)
* [Jiangwen Su's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
## Prompt template: None
```
{prompt}
```
## Provided files, and AWQ parameters
For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ/tree/main) | 4 | 128 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 18.31 GB
## Serving this model from vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
Note: at the time of writing, vLLM has not yet done a new release with AWQ support.
If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
```shell
python3 python -m vllm.entrypoints.api_server --model TheBloke/speechless-codellama-34b-v2.0-AWQ --quantization awq --dtype half
```
When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/speechless-codellama-34b-v2.0-AWQ", quantization="awq", dtype="half")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
## Serving this model from Text Generation Inference (TGI)
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:
```shell
--model-id TheBloke/speechless-codellama-34b-v2.0-AWQ --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):
```shell
pip3 install huggingface-hub
```
```python
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 AWQ model from Python code
### Install the necessary packages
Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later
```shell
pip3 install autoawq
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### You can then try the following example code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_name_or_path = "TheBloke/speechless-codellama-34b-v2.0-AWQ"
# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
tokens,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
max_new_tokens=512
)
print("Output: ", tokenizer.decode(generation_output[0]))
"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import 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:
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
- [vLLM](https://github.com/vllm-project/vllm)
- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054). Use the `:latest` Docker container until the next TGI release is made.
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
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.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF)
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](https://huggingface.co/spaces/bigcode/bigcode-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](https://huggingface.co/spaces/HuggingFaceH4/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](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/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:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [x] Infilling.
- [ ] Instructions / chat.
- [ ] Python specialist.
```python
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/](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](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## 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](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) 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](https://ai.meta.com/llama/responsible-user-guide).
