This repository contains executable weights (which we call
llamafiles) that run on
Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64.
llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023.
It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp
binaries that run on the stock installs of six OSes for both ARM64 and
AMD64.
In addition to being executables, llamafiles are also zip archives. Each
llamafile contains a GGUF file, which you can extract using the unzip
command. If you want to change or add files to your llamafiles, then the
zipalign command (distributed on the llamafile github) should be used
instead of the traditional zip command.
About Quantization Formats (General Advice)
Your choice of quantization format depends on three things:
Will it fit in RAM or VRAM?
Is your use case reading (e.g. summarization) or writing (e.g. chatbot)?
llamafiles bigger than 4.30 GB are hard to run on Windows (see gotchas)
Good quants for writing (eval speed) are Q5_K_M, and Q4_0. Text
generation is bounded by memory speed, so smaller quants help, but they
also cause the LLM to hallucinate more.
Good quants for reading (prompt eval speed) are BF16, F16, Q4_0, and
Q8_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
computation speed (flops) so simpler quants help.
Files which exceed the HF 50GB upload limit have a .cat𝑋 extension. You
need to use the cat command locally to turn them back into a single
file, using the same order.
Note: BF16 is currently only supported on CPU.
Hardware Choices (LLaMA3 70B Specific)
Don't bother if you're using a Macbook M1 with 32GB of RAM. The Q2_K
weights might work slowly if you run in CPU mode (pass -ngl 0) but
you're not going to have a good experience.
Mac Studio is recommended. An Apple M2 Ultra w/ 24-core CPU, 60-core
GPU, 128GB RAM (costs $8000 with the monitor) runs
Meta-Llama-3-70B-Instruct.Q4_0.llamafile at 14 tok/sec (prompt eval is
82 tok/sec) thanks to the Metal GPU.
Just want to try it? You can go on vast.ai and rent a system with 4x RTX
4090's for a few bucks an hour. That'll run these 70b llamafiles. Be
sure to pass the -ngl 9999 flag. Or you could build your own, but the
graphics cards alone will cost $10k+.
AMD Threadripper Pro 7995WX ($10k) does a good job too at 5.9 tok/sec
eval with Q4_0 (49 tok/sec prompt). With F16 weights the prompt eval
goes 65 tok/sec.
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-3-70B-Instruct, for use with transformers and with the original llama3 codebase.
Use with transformers
See the snippet below for usage with Transformers:
python
1import transformers
2import torch
34model_id ="meta-llama/Meta-Llama-3-70B-Instruct"56pipeline = transformers.pipeline(7"text-generation",8 model=model_id,9 model_kwargs={"torch_dtype": torch.bfloat16},10 device="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):])
Use with llama3
Please, follow the instructions in the repository.
To download Original checkpoints, see the example command below leveraging huggingface-cli:
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.
