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. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications
KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
Faraday.dev, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
localGPT An open-source initiative enabling private conversations with documents.
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.
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 folder.
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: LiteLLMs/Llama-3-8B-Instruct-Gradient-1048k-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.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:
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 8192 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
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
Run one of the following commands, according to your system:
shell
1# Base ctransformers with no GPU acceleration2pip install llama-cpp-python
3# With NVidia CUDA acceleration4CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
5# Or with OpenBLAS acceleration6CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
7# Or with CLBLast acceleration8CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
9# Or with AMD ROCm GPU acceleration (Linux only)10CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
11# Or with Metal GPU acceleration for macOS systems only12CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
13# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:14$env:CMAKE_ARGS ="-DLLAMA_OPENBLAS=on"15pip install llama-cpp-python
Simple llama-cpp-python example code
python
1from llama_cpp import Llama
2# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.3llm = Llama(4 model_path="./Q4_0/Q4_0-00001-of-00009.gguf",# Download the model file first5 n_ctx=32768,# The max sequence length to use - note that longer sequence lengths require much more resources6 n_threads=8,# The number of CPU threads to use, tailor to your system and the resulting performance7 n_gpu_layers=35# The number of layers to offload to GPU, if you have GPU acceleration available8)9# Simple inference example10output = llm(11"<PROMPT>",# Prompt12 max_tokens=512,# Generate up to 512 tokens13 stop=["</s>"],# Example stop token - not necessarily correct for this specific model! Please check before using.14 echo=True# Whether to echo the prompt15)16# Chat Completion API17llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2")# Set chat_format according to the model you are using18llm.create_chat_completion(19 messages =[20{"role":"system","content":"You are a story writing assistant."},21{22"role":"user",23"content":"Write a story about llamas."24}25]26)
How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
Gradient incorporates your data to deploy autonomous assistants that power critical operations across your business. If you're looking to build custom AI models or agents, email us a message contact@gradient.ai.
This model extends LLama-3 8B's context length from 8k to > 1040K, developed by Gradient, sponsored by compute from Crusoe Energy. It demonstrates that SOTA LLMs can learn to operate on long context with minimal training by appropriately adjusting RoPE theta. We trained on 830M tokens for this stage, and 1.4B tokens total for all stages, which is < 0.01% of Llama-3's original pre-training data.
Update (5/3): We further fine-tuned our model to strengthen its assistant-like chat ability as well. The NIAH result is updated.
NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by empirical RoPE theta optimization
Progressive training on increasing context lengths, similar to Large World Model [2] (See details below)
Infra:
We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 1048k tokens on Crusoe Energy high performance L40S cluster.
Notably, we layered parallelism on top of Ring Attention with a custom network topology to better leverage large GPU clusters in the face of network bottlenecks from passing many KV blocks between devices. This gave us a 33x speedup in model training (compare 524k and 1048k to 65k and 262k in the table below).
Data:
For training data, we generate long contexts by augmenting SlimPajama. We also fine-tune on a chat dataset based on UltraChat [4], following a similar recipe for data augmentation to [2].
Progressive Training Details:
| | 65K | 262K | 524k | 1048k |
| -- | -- | -
Base Model
Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Training Data
Params
Context length
GQA
Token count
Knowledge cutoff
Llama 3
A new mix of publicly available online data.
8B
8k
Yes
15T+
March, 2023
70B
8k
Yes
December, 2023
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original llama3 codebase.
Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the generate() function. Let's see examples of both.
Transformers pipeline
python
1import transformers
2import torch
34model_id ="meta-llama/Meta-Llama-3-8B-Instruct"56pipeline = transformers.pipeline(7"text-generation",8 model=model_id,9 model_kwargs={"torch_dtype": torch.bfloat16},10 device_map="auto",11)1213messages =[14{"role":"system","content":"You are a pirate chatbot who always responds in pirate speak!"},15{"role":"user","content":"Who are you?"},16]1718prompt = pipeline.tokenizer.apply_chat_template(19 messages,20 tokenize=False,21 add_generation_prompt=True22)2324terminators =[25 pipeline.tokenizer.eos_token_id,26 pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")27]2829outputs = pipeline(30 prompt,31 max_new_tokens=256,32 eos_token_id=terminators,33 do_sample=True,34 temperature=0.6,35 top_p=0.9,36)37print(outputs[0]["generated_text"][len(prompt):])
Transformers AutoModelForCausalLM
python
1from transformers import AutoTokenizer, AutoModelForCausalLM
2import torch
34model_id ="meta-llama/Meta-Llama-3-8B-Instruct"56tokenizer = AutoTokenizer.from_pretrained(model_id)7model = AutoModelForCausalLM.from_pretrained(8 model_id,9 torch_dtype=torch.bfloat16,10 device_map="auto",11)1213messages =[14{"role":"system","content":"You are a pirate chatbot who always responds in pirate speak!"},15{"role":"user","content":"Who are you?"},16]1718input_ids = tokenizer.apply_chat_template(19 messages,20 add_generation_prompt=True,21 return_tensors="pt"22).to(model.device)2324terminators =[25 tokenizer.eos_token_id,26 tokenizer.convert_tokens_to_ids("<|eot_id|>")27]2829outputs = model.generate(30 input_ids,31 max_new_tokens=256,32 eos_token_id=terminators,33 do_sample=True,34 temperature=0.6,35 top_p=0.9,36)37response = outputs[0][input_ids.shape[-1]:]38print(tokenizer.decode(response, skip_special_tokens=True))
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
Time (GPU hours)
Power Consumption (W)
Carbon Emitted(tCO2eq)
Llama 3 8B
1.3M
700
390
Llama 3 70B
6.4M
700
1900
Total
7.7M
2290
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
Base pretrained models
Category
Benchmark
Llama 3 8B
Llama2 7B
Llama2 13B
Llama 3 70B
Llama2 70B
General
MMLU (5-shot)
66.6
45.7
53.8
79.5
69.7
AGIEval English (3-5 shot)
45.9
28.8
38.7
63.0
54.8
CommonSenseQA (7-shot)
72.6
57.6
67.6
83.8
78.7
Winogrande (5-shot)
76.1
73.3
75.4
83.1
81.8
BIG-Bench Hard (3-shot, CoT)
61.1
38.1
47.0
81.3
65.7
ARC-Challenge (25-shot)
78.6
53.7
67.6
93.0
85.3
Knowledge reasoning
TriviaQA-Wiki (5-shot)
78.5
72.1
79.6
89.7
87.5
Reading comprehension
SQuAD (1-shot)
76.4
72.2
72.1
85.6
82.6
QuAC (1-shot, F1)
44.4
39.6
44.9
51.1
49.4
BoolQ (0-shot)
75.7
65.5
66.9
79.0
73.1
DROP (3-shot, F1)
58.4
37.9
49.8
79.7
70.2
Instruction tuned models
Benchmark
Llama 3 8B
Llama 2 7B
Llama 2 13B
Llama 3 70B
Llama 2 70B
MMLU (5-shot)
68.4
34.1
47.8
82.0
52.9
GPQA (0-shot)
34.2
21.7
22.3
39.5
21.0
HumanEval (0-shot)
62.2
7.9
14.0
81.7
25.6
GSM-8K (8-shot, CoT)
79.6
25.7
77.4
93.0
57.5
MATH (4-shot, CoT)
30.0
3.8
6.7
50.4
11.6
Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at https://llama.meta.com/llama3/use-policy/.
Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its 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, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
