初始化项目，由ModelHub XC社区提供模型
Model: Mungert/Llama-Guard-3-8B-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
81
.gitattributes
vendored
Normal file
81
.gitattributes
vendored
Normal file
@@ -0,0 +1,81 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
Llama-Guard-3-8B-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-f16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-bf16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-f16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-f16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-bf16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-Guard-3-8B-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Llama-Guard-3-8B-bf16-q4_k.gguf
Normal file
3
Llama-Guard-3-8B-bf16-q4_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c10fcc621a86923440cc181e4112c73997e26bf3b5c0cf483fd2786d32b90519
|
||||
size 6295640480
|
||||
3
Llama-Guard-3-8B-bf16-q6_k.gguf
Normal file
3
Llama-Guard-3-8B-bf16-q6_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:080dec932696702a5fcef4abbc04b0ff5dfed7460b3c3854038ad20bd2ccd480
|
||||
size 7835474336
|
||||
3
Llama-Guard-3-8B-bf16-q8_0.gguf
Normal file
3
Llama-Guard-3-8B-bf16-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44969dfdca49b1b1de5062ee59841525459c8f325c54b93f9290a82aba1ec293
|
||||
size 9525778592
|
||||
3
Llama-Guard-3-8B-bf16.gguf
Normal file
3
Llama-Guard-3-8B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa6f2458033ea3b53783e47090332e5ff6f9d3ea8d18484fcefe614b711c01f3
|
||||
size 16068892832
|
||||
3
Llama-Guard-3-8B-f16-q4_k.gguf
Normal file
3
Llama-Guard-3-8B-f16-q4_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e4cccf28586d4fb261762128116da639ef28a4d079c2361081d063b5d18c59d0
|
||||
size 6295640480
|
||||
3
Llama-Guard-3-8B-f16-q6_k.gguf
Normal file
3
Llama-Guard-3-8B-f16-q6_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a63479d4ebd1bb3860b8edec0f85a4fa0e85558e58d72d7a58018011df43852
|
||||
size 7835474336
|
||||
3
Llama-Guard-3-8B-f16-q8_0.gguf
Normal file
3
Llama-Guard-3-8B-f16-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d077c976c4c63a164e3d2d6aa04ca3146d1f5602a798ed309153b821764e2576
|
||||
size 9525778592
|
||||
3
Llama-Guard-3-8B-iq1_m.gguf
Normal file
3
Llama-Guard-3-8B-iq1_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:574c77275b827cc998e1ccd5aa7557c1ba4ae38cb6981dbf04628a341c6c083f
|
||||
size 2161973664
|
||||
3
Llama-Guard-3-8B-iq1_s.gguf
Normal file
3
Llama-Guard-3-8B-iq1_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c7bf91f059749c3894d6fc2a38d91e888a180811bc0c7efd5caf804a3354a533
|
||||
size 2019629472
|
||||
3
Llama-Guard-3-8B-iq2_m.gguf
Normal file
3
Llama-Guard-3-8B-iq2_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:04baa1de6e4379fd1e3c1344d3fa7f861b0c3958e0b6daadcc7c58d53660e84a
|
||||
size 2948282784
|
||||
3
Llama-Guard-3-8B-iq2_s.gguf
Normal file
3
Llama-Guard-3-8B-iq2_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5bd1e6c1e7ed7d669490a23fbc44eedfe0b47478be52508e68f842433ec7d40c
|
||||
size 2758490528
|
||||
3
Llama-Guard-3-8B-iq2_xs.gguf
Normal file
3
Llama-Guard-3-8B-iq2_xs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a256fc74cd1cde99e30704c254b0f0f89da697cc183c5bd1a9efbb567f6444e
|
||||
size 2605783456
|
||||
3
Llama-Guard-3-8B-iq2_xxs.gguf
Normal file
3
Llama-Guard-3-8B-iq2_xxs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b60c808f2e3cdf52326e1c31f4e42b3c158d85e021cf731594fd573508ccdca
|
||||
size 2399213984
|
||||
3
Llama-Guard-3-8B-iq3_m.gguf
Normal file
3
Llama-Guard-3-8B-iq3_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9242c38fff7762cfa2be7c9193f29dc4b4ae3788c953badd5e8aabe8606918a
|
||||
size 3784825248
|
||||
3
Llama-Guard-3-8B-iq3_s.gguf
Normal file
3
Llama-Guard-3-8B-iq3_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e4c9ebb11e13fa45e438afd32e83a45dda24a994a883b46a55aea0a45f26d474
|
||||
size 3682326944
|
||||
3
Llama-Guard-3-8B-iq3_xs.gguf
Normal file
3
Llama-Guard-3-8B-iq3_xs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf7c21c7732fffeff0e2988706f0270f67b2dd2d091e6c1e3899c90049ab4201
|
||||
size 3518749088
|
||||
3
Llama-Guard-3-8B-iq3_xxs.gguf
Normal file
3
Llama-Guard-3-8B-iq3_xxs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7fcf8d666ee442aed5cc5ad9cefd81668adc82796539ad56946af6a50be5aecc
|
||||
size 3274914208
|
||||
3
Llama-Guard-3-8B-iq4_nl.gguf
Normal file
3
Llama-Guard-3-8B-iq4_nl.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f208fdca61efc3972de2c2dc8ab6250f8618f6f3cdad8d779585ab1ab60ef32e
|
||||
size 4677990816
|
||||
3
Llama-Guard-3-8B-iq4_xs.gguf
Normal file
3
Llama-Guard-3-8B-iq4_xs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45a9e119f3672a18f897bb12c7c776fe15d4d7284b77ee30edae828f6d647e0b
|
||||
size 4447664544
|
||||
3
Llama-Guard-3-8B-q2_k_s.gguf
Normal file
3
Llama-Guard-3-8B-q2_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6a6a030ae906320a1680918d86276dd6e9f8ced1b804859ced89803d2a659d4
|
||||
size 2988816800
|
||||
3
Llama-Guard-3-8B-q3_k_m.gguf
Normal file
3
Llama-Guard-3-8B-q3_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6c74b89849e811de70333da0d3a605d22ed88c4d98efa6be5fe9a34c53ea8ee
|
||||
size 4018919840
|
||||
3
Llama-Guard-3-8B-q3_k_s.gguf
Normal file
3
Llama-Guard-3-8B-q3_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:55d02cf1bcdf0cf54c7f3de6df5dc86c513bcaf44593d92b7228ea130e2b3f7d
|
||||
size 3664501152
|
||||
3
Llama-Guard-3-8B-q4_0.gguf
Normal file
3
Llama-Guard-3-8B-q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:df09b7a6e3dff23dcf97446b44f48270f43be330fdc8d42f10d695c33b7c7745
|
||||
size 4525775264
|
||||
3
Llama-Guard-3-8B-q4_1.gguf
Normal file
3
Llama-Guard-3-8B-q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed97ad4d56cf52c37cf07c174234bccbaf1959ccd4a6a1d8b485c5588fb13382
|
||||
size 5027649952
|
||||
3
Llama-Guard-3-8B-q4_k_m.gguf
Normal file
3
Llama-Guard-3-8B-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20682acc45b27cab80c7c869afa33205d7c8ab73ba8ab2c4df11e3f1123b78e5
|
||||
size 4920736160
|
||||
3
Llama-Guard-3-8B-q4_k_s.gguf
Normal file
3
Llama-Guard-3-8B-q4_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c427d8c36e7d2686fac3d17bbdfae694fb54cf71bd52e4965fac453f7a13861
|
||||
size 4692670880
|
||||
3
Llama-Guard-3-8B-q5_0.gguf
Normal file
3
Llama-Guard-3-8B-q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:67ab506a627c6cf1189df0e6b584c9f2beb5f162aad631ce0f554ee9fea39bf0
|
||||
size 5529524640
|
||||
3
Llama-Guard-3-8B-q5_1.gguf
Normal file
3
Llama-Guard-3-8B-q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8914092a4cb1b2f0ed9cb849a6699855313692b0e47199d882cf384375503c71
|
||||
size 6031399328
|
||||
3
Llama-Guard-3-8B-q5_k_m.gguf
Normal file
3
Llama-Guard-3-8B-q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:383f965e05a132ed80f51aafad54052fb52fc230e822530efb0a1e9f1bdc40ca
|
||||
size 5732989344
|
||||
3
Llama-Guard-3-8B-q5_k_s.gguf
Normal file
3
Llama-Guard-3-8B-q5_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:613c672d154d07969fd9d5eba5e1f6e03529bdf7262768458e5f22f19473da2a
|
||||
size 5599295904
|
||||
3
Llama-Guard-3-8B-q6_k_m.gguf
Normal file
3
Llama-Guard-3-8B-q6_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5e62aa36a0d890f6fed1f37e60c7585f4f496cf9eb9c2546d71714706672a4d2
|
||||
size 6596008352
|
||||
3
Llama-Guard-3-8B-q8_0.gguf
Normal file
3
Llama-Guard-3-8B-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f6f4a79ba167ce1b4aa7c1b4fdaee8f044d49c837a81083d64b1ff452734ca2
|
||||
size 8540772512
|
||||
3
Llama-Guard-3-8B.imatrix
Normal file
3
Llama-Guard-3-8B.imatrix
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39fe6234593d4a4227addb473a29fe7ef964e5dd98396e16758f8b89ca639a2f
|
||||
size 4988151
|
||||
910
README.md
Normal file
910
README.md
Normal file
@@ -0,0 +1,910 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
base_model: meta-llama/Meta-Llama-3.1-8B
|
||||
tags:
|
||||
- facebook
|
||||
- meta
|
||||
- pytorch
|
||||
- llama
|
||||
- llama-3
|
||||
license: llama3.1
|
||||
extra_gated_prompt: >-
|
||||
### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT
|
||||
|
||||
Llama 3.1 Version Release Date: July 23, 2024
|
||||
|
||||
"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the
|
||||
Llama Materials set forth herein.
|
||||
|
||||
"Documentation" means the specifications, manuals and documentation accompanying Llama 3.1
|
||||
distributed by Meta at https://llama.meta.com/doc/overview.
|
||||
|
||||
"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into
|
||||
this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
|
||||
regulations to provide legal consent and that has legal authority to bind your employer or such other
|
||||
person or entity if you are entering in this Agreement on their behalf.
|
||||
|
||||
"Llama 3.1" means the foundational large language models and software and algorithms, including
|
||||
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
|
||||
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
|
||||
https://llama.meta.com/llama-downloads.
|
||||
|
||||
"Llama Materials" means, collectively, Meta’s proprietary Llama 3.1 and Documentation (and any
|
||||
portion thereof) made available under this Agreement.
|
||||
|
||||
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
|
||||
principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
|
||||
outside of the EEA or Switzerland).
|
||||
|
||||
1. License Rights and Redistribution.
|
||||
|
||||
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
|
||||
limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
|
||||
Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
|
||||
Llama Materials.
|
||||
|
||||
b. Redistribution and Use.
|
||||
|
||||
i. If you distribute or make available the Llama Materials (or any derivative works
|
||||
thereof), or a product or service (including another AI model) that contains any of them, you shall (A)
|
||||
provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with
|
||||
Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use
|
||||
the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
|
||||
otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at
|
||||
the beginning of any such AI model name.
|
||||
|
||||
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
|
||||
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
|
||||
|
||||
iii. You must retain in all copies of the Llama Materials that you distribute the following
|
||||
attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.1 is
|
||||
licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights
|
||||
Reserved.”
|
||||
|
||||
iv. Your use of the Llama Materials must comply with applicable laws and regulations
|
||||
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
|
||||
Materials (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated by
|
||||
reference into this Agreement.
|
||||
|
||||
2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users
|
||||
of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
|
||||
million monthly active users in the preceding calendar month, you must request a license from Meta,
|
||||
which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
|
||||
rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
|
||||
|
||||
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
|
||||
OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
|
||||
ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
|
||||
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
|
||||
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
|
||||
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
|
||||
ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
|
||||
RESULTS.
|
||||
|
||||
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
|
||||
LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
|
||||
OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
|
||||
INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
|
||||
OF THE POSSIBILITY OF ANY OF THE FOREGOING.
|
||||
|
||||
5. Intellectual Property.
|
||||
|
||||
a. No trademark licenses are granted under this Agreement, and in connection with the Llama
|
||||
Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
|
||||
or any of its affiliates, except as required for reasonable and customary use in describing and
|
||||
redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
|
||||
use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
|
||||
comply with Meta’s brand guidelines (currently accessible at
|
||||
https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
|
||||
of the Mark will inure to the benefit of Meta.
|
||||
|
||||
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
|
||||
respect to any derivative works and modifications of the Llama Materials that are made by you, as
|
||||
between you and Meta, you are and will be the owner of such derivative works and modifications.
|
||||
|
||||
c. If you institute litigation or other proceedings against Meta or any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or
|
||||
results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
|
||||
rights owned or licensable by you, then any licenses granted to you under this Agreement shall
|
||||
terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
|
||||
harmless Meta from and against any claim by any third party arising out of or related to your use or
|
||||
distribution of the Llama Materials.
|
||||
|
||||
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
|
||||
Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
|
||||
accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
|
||||
breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
|
||||
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
|
||||
Agreement.
|
||||
|
||||
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
|
||||
the State of California without regard to choice of law principles, and the UN Convention on Contracts
|
||||
for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
|
||||
exclusive jurisdiction of any dispute arising out of this Agreement.
|
||||
|
||||
### Llama 3.1 Acceptable Use Policy
|
||||
|
||||
Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.1. If you
|
||||
access or use Llama 3.1, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of
|
||||
this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)
|
||||
|
||||
#### Prohibited Uses
|
||||
|
||||
We want everyone to use Llama 3.1 safely and responsibly. You agree you will not use, or allow
|
||||
others to use, Llama 3.1 to:
|
||||
1. Violate the law or others’ rights, including to:
|
||||
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
|
||||
1. Violence or terrorism
|
||||
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
|
||||
3. Human trafficking, exploitation, and sexual violence
|
||||
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
|
||||
5. Sexual solicitation
|
||||
6. Any other criminal activity
|
||||
3. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
|
||||
4. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
|
||||
5. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
|
||||
6. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
|
||||
7. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
|
||||
8. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
|
||||
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.1 related to the following:
|
||||
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
|
||||
2. Guns and illegal weapons (including weapon development)
|
||||
3. Illegal drugs and regulated/controlled substances
|
||||
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
|
||||
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
|
||||
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
|
||||
3. Intentionally deceive or mislead others, including use of Llama 3.1 related to the following:
|
||||
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
|
||||
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
|
||||
3. Generating, promoting, or further distributing spam
|
||||
4. Impersonating another individual without consent, authorization, or legal right
|
||||
5. Representing that the use of Llama 3.1 or outputs are human-generated
|
||||
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
|
||||
4. Fail to appropriately disclose to end users any known dangers of your AI system
|
||||
|
||||
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation
|
||||
of this Policy through one of the following means:
|
||||
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)
|
||||
* Reporting risky content generated by the model:
|
||||
developers.facebook.com/llama_output_feedback
|
||||
* Reporting bugs and security concerns: facebook.com/whitehat/info
|
||||
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com
|
||||
extra_gated_fields:
|
||||
First Name: text
|
||||
Last Name: text
|
||||
Date of birth: date_picker
|
||||
Country: country
|
||||
Affiliation: text
|
||||
Job title:
|
||||
type: select
|
||||
options:
|
||||
- Student
|
||||
- Research Graduate
|
||||
- AI researcher
|
||||
- AI developer/engineer
|
||||
- Reporter
|
||||
- Other
|
||||
geo: ip_location
|
||||
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
|
||||
extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
|
||||
extra_gated_button_content: Submit
|
||||
---
|
||||
|
||||
# <span style="color: #7FFF7F;">Llama-Guard-3-8B GGUF Models</span>
|
||||
|
||||
## **Choosing the Right Model Format**
|
||||
|
||||
Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.
|
||||
|
||||
### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**
|
||||
- A 16-bit floating-point format designed for **faster computation** while retaining good precision.
|
||||
- Provides **similar dynamic range** as FP32 but with **lower memory usage**.
|
||||
- Recommended if your hardware supports **BF16 acceleration** (check your device’s specs).
|
||||
- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.
|
||||
|
||||
📌 **Use BF16 if:**
|
||||
✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).
|
||||
✔ You want **higher precision** while saving memory.
|
||||
✔ You plan to **requantize** the model into another format.
|
||||
|
||||
📌 **Avoid BF16 if:**
|
||||
❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).
|
||||
❌ You need compatibility with older devices that lack BF16 optimization.
|
||||
|
||||
---
|
||||
|
||||
### **F16 (Float 16) – More widely supported than BF16**
|
||||
- A 16-bit floating-point **high precision** but with less of range of values than BF16.
|
||||
- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).
|
||||
- Slightly lower numerical precision than BF16 but generally sufficient for inference.
|
||||
|
||||
📌 **Use F16 if:**
|
||||
✔ Your hardware supports **FP16** but **not BF16**.
|
||||
✔ You need a **balance between speed, memory usage, and accuracy**.
|
||||
✔ You are running on a **GPU** or another device optimized for FP16 computations.
|
||||
|
||||
📌 **Avoid F16 if:**
|
||||
❌ Your device lacks **native FP16 support** (it may run slower than expected).
|
||||
❌ You have memory limitations.
|
||||
|
||||
---
|
||||
|
||||
### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**
|
||||
Quantization reduces model size and memory usage while maintaining as much accuracy as possible.
|
||||
- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.
|
||||
- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.
|
||||
|
||||
📌 **Use Quantized Models if:**
|
||||
✔ You are running inference on a **CPU** and need an optimized model.
|
||||
✔ Your device has **low VRAM** and cannot load full-precision models.
|
||||
✔ You want to reduce **memory footprint** while keeping reasonable accuracy.
|
||||
|
||||
📌 **Avoid Quantized Models if:**
|
||||
❌ You need **maximum accuracy** (full-precision models are better for this).
|
||||
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).
|
||||
|
||||
---
|
||||
|
||||
### **Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)**
|
||||
These models are optimized for **extreme memory efficiency**, making them ideal for **low-power devices** or **large-scale deployments** where memory is a critical constraint.
|
||||
|
||||
- **IQ3_XS**: Ultra-low-bit quantization (3-bit) with **extreme memory efficiency**.
|
||||
- **Use case**: Best for **ultra-low-memory devices** where even Q4_K is too large.
|
||||
- **Trade-off**: Lower accuracy compared to higher-bit quantizations.
|
||||
|
||||
- **IQ3_S**: Small block size for **maximum memory efficiency**.
|
||||
- **Use case**: Best for **low-memory devices** where **IQ3_XS** is too aggressive.
|
||||
|
||||
- **IQ3_M**: Medium block size for better accuracy than **IQ3_S**.
|
||||
- **Use case**: Suitable for **low-memory devices** where **IQ3_S** is too limiting.
|
||||
|
||||
- **Q4_K**: 4-bit quantization with **block-wise optimization** for better accuracy.
|
||||
- **Use case**: Best for **low-memory devices** where **Q6_K** is too large.
|
||||
|
||||
- **Q4_0**: Pure 4-bit quantization, optimized for **ARM devices**.
|
||||
- **Use case**: Best for **ARM-based devices** or **low-memory environments**.
|
||||
|
||||
---
|
||||
|
||||
### **Summary Table: Model Format Selection**
|
||||
|
||||
| Model Format | Precision | Memory Usage | Device Requirements | Best Use Case |
|
||||
|--------------|------------|---------------|----------------------|---------------|
|
||||
| **BF16** | Highest | High | BF16-supported GPU/CPUs | High-speed inference with reduced memory |
|
||||
| **F16** | High | High | FP16-supported devices | GPU inference when BF16 isn’t available |
|
||||
| **Q4_K** | Medium Low | Low | CPU or Low-VRAM devices | Best for memory-constrained environments |
|
||||
| **Q6_K** | Medium | Moderate | CPU with more memory | Better accuracy while still being quantized |
|
||||
| **Q8_0** | High | Moderate | CPU or GPU with enough VRAM | Best accuracy among quantized models |
|
||||
| **IQ3_XS** | Very Low | Very Low | Ultra-low-memory devices | Extreme memory efficiency and low accuracy |
|
||||
| **Q4_0** | Low | Low | ARM or low-memory devices | llama.cpp can optimize for ARM devices |
|
||||
|
||||
---
|
||||
|
||||
## **Included Files & Details**
|
||||
|
||||
### `Llama-Guard-3-8B-bf16.gguf`
|
||||
- Model weights preserved in **BF16**.
|
||||
- Use this if you want to **requantize** the model into a different format.
|
||||
- Best if your device supports **BF16 acceleration**.
|
||||
|
||||
### `Llama-Guard-3-8B-f16.gguf`
|
||||
- Model weights stored in **F16**.
|
||||
- Use if your device supports **FP16**, especially if BF16 is not available.
|
||||
|
||||
### `Llama-Guard-3-8B-bf16-q8_0.gguf`
|
||||
- **Output & embeddings** remain in **BF16**.
|
||||
- All other layers quantized to **Q8_0**.
|
||||
- Use if your device supports **BF16** and you want a quantized version.
|
||||
|
||||
### `Llama-Guard-3-8B-f16-q8_0.gguf`
|
||||
- **Output & embeddings** remain in **F16**.
|
||||
- All other layers quantized to **Q8_0**.
|
||||
|
||||
### `Llama-Guard-3-8B-q4_k.gguf`
|
||||
- **Output & embeddings** quantized to **Q8_0**.
|
||||
- All other layers quantized to **Q4_K**.
|
||||
- Good for **CPU inference** with limited memory.
|
||||
|
||||
### `Llama-Guard-3-8B-q4_k_s.gguf`
|
||||
- Smallest **Q4_K** variant, using less memory at the cost of accuracy.
|
||||
- Best for **very low-memory setups**.
|
||||
|
||||
### `Llama-Guard-3-8B-q6_k.gguf`
|
||||
- **Output & embeddings** quantized to **Q8_0**.
|
||||
- All other layers quantized to **Q6_K** .
|
||||
|
||||
### `Llama-Guard-3-8B-q8_0.gguf`
|
||||
- Fully **Q8** quantized model for better accuracy.
|
||||
- Requires **more memory** but offers higher precision.
|
||||
|
||||
### `Llama-Guard-3-8B-iq3_xs.gguf`
|
||||
- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.
|
||||
- Best for **ultra-low-memory devices**.
|
||||
|
||||
### `Llama-Guard-3-8B-iq3_m.gguf`
|
||||
- **IQ3_M** quantization, offering a **medium block size** for better accuracy.
|
||||
- Suitable for **low-memory devices**.
|
||||
|
||||
### `Llama-Guard-3-8B-q4_0.gguf`
|
||||
- Pure **Q4_0** quantization, optimized for **ARM devices**.
|
||||
- Best for **low-memory environments**.
|
||||
- Prefer IQ4_NL for better accuracy.
|
||||
|
||||
# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
|
||||
|
||||
Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com).
|
||||
|
||||
💬 Click the **chat icon** (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.
|
||||
|
||||
### What I'm Testing
|
||||
|
||||
I'm experimenting with **function calling** against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function".
|
||||
|
||||
🟡 **TestLLM** – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .
|
||||
|
||||
### The other Available AI Assistants
|
||||
|
||||
🟢 **TurboLLM** – Uses **gpt-4o-mini** Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .
|
||||
|
||||
🔵 **HugLLM** – Runs **open-source Hugging Face models** Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)
|
||||
|
||||
### Final Word
|
||||
|
||||
I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
|
||||
|
||||
If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
|
||||
|
||||
I'm also open to job opportunities or sponsorship.
|
||||
|
||||
Thank you! 😊
|
||||
|
||||
|
||||
|
||||
|
||||
# Model Details
|
||||
|
||||
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
|
||||
|
||||
Llama Guard 3 was aligned to safeguard against the MLCommons standardized hazards taxonomy and designed to support Llama 3.1 capabilities. Specifically, it provides content moderation in 8 languages, and was optimized to support safety and security for search and code interpreter tool calls.
|
||||
|
||||
Below is a response classification example for Llama Guard 3.
|
||||
|
||||
|
||||
<p align="center">
|
||||
<img src="llama_guard_3_figure.png" width="800"/>
|
||||
</p>
|
||||
|
||||
In order to produce classifier scores, we look at the probability for the first token, and use that as the “unsafe” class probability. We can then apply score thresholding to make binary decisions.
|
||||
|
||||
# Hazard Taxonomy and Policy
|
||||
|
||||
The model is trained to predict safety labels on the 14 categories shown below, based on the [MLCommons taxonomy](https://mlcommons.org/2024/04/mlc-aisafety-v0-5-poc/) of 13 hazards, as well as an additional category for Code Interpreter Abuse for tool calls use cases
|
||||
|
||||
<table align="center">
|
||||
<thead>
|
||||
<tr>
|
||||
<th colspan="2">Hazard categories</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>S1: Violent Crimes</td>
|
||||
<td>S2: Non-Violent Crimes</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S3: Sex-Related Crimes</td>
|
||||
<td>S4: Child Sexual Exploitation</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S5: Defamation</td>
|
||||
<td>S6: Specialized Advice</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S7: Privacy</td>
|
||||
<td>S8: Intellectual Property</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S9: Indiscriminate Weapons</td>
|
||||
<td>S10: Hate</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S11: Suicide & Self-Harm</td>
|
||||
<td>S12: Sexual Content</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>S13: Elections</td>
|
||||
<td>S14: Code Interpreter Abuse</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
**S1 - Violent Crimes**
|
||||
|
||||
Responses that enable, encourage, or endorse the commission of violent crimes, including: (1) unlawful violence toward people (ex: terrorism, genocide, murder, hate-motivated violent crimes, child abuse, assault, battery, kidnapping) and (2) unlawful violence toward animals (ex: animal abuse)
|
||||
|
||||
**S2 - Non-Violent Crimes**
|
||||
|
||||
Responses that enable, encourage, or endorse the commission of non-violent crimes, including: (1) personal crimes (ex: labor trafficking, threats, intimidation, hate-motivated non-violent crimes), (2) financial crimes (ex: fraud, scams, money laundering), (3) property crimes (ex: theft, arson, vandalism), (4) drug crimes (ex: creating or using regulated substances), (5) weapons crimes (ex: producing unlicensed firearms), and (6) cyber crimes (ex: hacking)
|
||||
|
||||
**S3 - Sex-Related Crimes**
|
||||
|
||||
Responses that enable, encourage, or endorse the commission of sex-related crimes, including: (1) sex trafficking, (2) sexual assault (ex: rape), (3) sexual harassment (physical, verbal, or visual), and (4) prostitution
|
||||
|
||||
**S4 - Child Sexual Exploitation**
|
||||
|
||||
Responses that contain, describe, enable, encourage, or endorse the sexual abuse of children
|
||||
|
||||
**S5 - Defamation**
|
||||
|
||||
Responses that are both verifiably false and likely to injure a living person’s reputation
|
||||
|
||||
**S6 - Specialized Advice**
|
||||
|
||||
Responses that contain specialized financial, medical, or legal advice, or that indicate dangerous activities or objects are safe
|
||||
|
||||
**S7 - Privacy**
|
||||
|
||||
Responses that contain sensitive, nonpublic personal information that could undermine someone’s physical, digital, or financial security
|
||||
|
||||
**S8 - Intellectual Property**
|
||||
|
||||
Responses that may violate the intellectual property rights of any third party
|
||||
|
||||
**S9 - Indiscriminate Weapons**
|
||||
|
||||
Responses that enable, encourage, or endorse the creation of indiscriminate weapons, including: (1) chemical weapons (ex: nerve gas), (2) biological weapons (ex: anthrax), (3) radiological weapons (ex: cobalt bombs), (4) nuclear weapons (ex: fission bombs), and (5) high-yield explosive weapons (ex: cluster munitions)
|
||||
|
||||
**S10 - Hate**
|
||||
|
||||
Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics (i.e., race, color, ethnicity, national origin, disability, religious affiliation, caste, sexual orientation, sex, gender identity, and/or serious disease)
|
||||
|
||||
**S11 - Suicide & Self-Harm**
|
||||
|
||||
Responses that enable, encourage, or endorse acts of intentional self-harm, including: (1) suicide, (2) self-injury (ex: cutting), and (3) disordered eating
|
||||
|
||||
**S12 - Sexual Content**
|
||||
|
||||
Responses that contain erotica
|
||||
|
||||
**S13 - Elections**
|
||||
|
||||
Responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections
|
||||
|
||||
**S14 - Code Interpreter Abuse**
|
||||
|
||||
Responses that seek to abuse code interpreters, including those that enable denial of service attacks, container escapes or privilege escalation exploits
|
||||
|
||||
|
||||
# Supported languages
|
||||
|
||||
Llama Guard 3 supports content safety for the following languages : English, French, German, Hindi, Italian, Portuguese, Spanish, Thai.
|
||||
|
||||
# Usage
|
||||
|
||||
> [!IMPORTANT]
|
||||
>
|
||||
> This repository corresponds to half-precision version of the model. A 8-bit precision version is also provided, please visit [meta-llama/Llama-Guard-3-8B-INT8](https://huggingface.co/meta-llama/Llama-Guard-3-8B-INT8).
|
||||
|
||||
Llama Guard 3 can be directly used with `transformers`. It is only supported since `transformers` version 4.43.
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_id = "meta-llama/Llama-Guard-3-8B"
|
||||
device = "cuda"
|
||||
dtype = torch.bfloat16
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=dtype, device_map=device)
|
||||
|
||||
def moderate(chat):
|
||||
input_ids = tokenizer.apply_chat_template(chat, return_tensors="pt").to(device)
|
||||
output = model.generate(input_ids=input_ids, max_new_tokens=100, pad_token_id=0)
|
||||
prompt_len = input_ids.shape[-1]
|
||||
return tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True)
|
||||
|
||||
moderate([
|
||||
{"role": "user", "content": "I forgot how to kill a process in Linux, can you help?"},
|
||||
{"role": "assistant", "content": "Sure! To kill a process in Linux, you can use the kill command followed by the process ID (PID) of the process you want to terminate."},
|
||||
])
|
||||
```
|
||||
|
||||
# Training Data
|
||||
|
||||
We use the English data used by Llama Guard [1], which are obtained by getting Llama 2 and Llama 3 generations on prompts from the hh-rlhf dataset [2]. In order to scale training data for new categories and new capabilities such as multilingual and tool use, we collect additional human and synthetically generated data. Similar to the English data, the multilingual data are Human-AI conversation data that are either single-turn or multi-turn. To reduce the model’s false positive rate, we curate a set of multilingual benign prompt and response data where LLMs likely reject the prompts.
|
||||
|
||||
For the tool use capability, we consider search tool calls and code interpreter abuse. To develop training data for search tool use, we use Llama3 to generate responses to a collected and synthetic set of prompts. The generations are based on the query results obtained from the Brave Search API. To develop synthetic training data to detect code interpreter attacks, we use an LLM to generate safe and unsafe prompts. Then, we use a non-safety-tuned LLM to generate code interpreter completions that comply with these instructions. For safe data, we focus on data close to the boundary of what would be considered unsafe, to minimize false positives on such borderline examples.
|
||||
|
||||
# Evaluation
|
||||
|
||||
**Note on evaluations:** As discussed in the original Llama Guard paper, comparing model performance is not straightforward as each model is built on its own policy and is expected to perform better on an evaluation dataset with a policy aligned to the model. This highlights the need for industry standards. By aligning the Llama Guard family of models with the Proof of Concept MLCommons taxonomy of hazards, we hope to drive adoption of industry standards like this and facilitate collaboration and transparency in the LLM safety and content evaluation space.
|
||||
|
||||
In this regard, we evaluate the performance of Llama Guard 3 on MLCommons hazard taxonomy and compare it across languages with Llama Guard 2 [3] on our internal test. We also add GPT4 as baseline with zero-shot prompting using MLCommons hazard taxonomy.
|
||||
|
||||
Tables 1, 2, and 3 show that Llama Guard 3 improves over Llama Guard 2 and outperforms GPT4 in English, multilingual, and tool use capabilities. Noteworthily, Llama Guard 3 achieves better performance with much lower false positive rates. We also benchmark Llama Guard 3 in the OSS dataset XSTest [4] and observe that it achieves the same F1 score but a lower false positive rate compared to Llama Guard 2.
|
||||
|
||||
<div align="center">
|
||||
<small> Table 1: Comparison of performance of various models measured on our internal English test set for MLCommons hazard taxonomy (response classification).</small>
|
||||
|
||||
| | **F1 ↑** | **AUPRC ↑** | **False Positive<br>Rate ↓** |
|
||||
|--------------------------|:--------:|:-----------:|:----------------------------:|
|
||||
| Llama Guard 2 | 0.877 | 0.927 | 0.081 |
|
||||
| Llama Guard 3 | 0.939 | 0.985 | 0.040 |
|
||||
| GPT4 | 0.805 | N/A | 0.152 |
|
||||
</div>
|
||||
|
||||
<br>
|
||||
|
||||
<table align="center">
|
||||
<small><center>Table 2: Comparison of multilingual performance of various models measured on our internal test set for MLCommons hazard taxonomy (prompt+response classification).</center></small>
|
||||
<thead>
|
||||
<tr>
|
||||
<th colspan="8"><center>F1 ↑ / FPR ↓</center></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td><center>French</center></td>
|
||||
<td><center>German</center></td>
|
||||
<td><center>Hindi</center></td>
|
||||
<td><center>Italian</center></td>
|
||||
<td><center>Portuguese</center></td>
|
||||
<td><center>Spanish</center></td>
|
||||
<td><center>Thai</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama Guard 2</td>
|
||||
<td><center>0.911/0.012</center></td>
|
||||
<td><center>0.795/0.062</center></td>
|
||||
<td><center>0.832/0.062</center></td>
|
||||
<td><center>0.681/0.039</center></td>
|
||||
<td><center>0.845/0.032</center></td>
|
||||
<td><center>0.876/0.001</center></td>
|
||||
<td><center>0.822/0.078</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama Guard 3</td>
|
||||
<td><center>0.943/0.036</center></td>
|
||||
<td><center>0.877/0.032</center></td>
|
||||
<td><center>0.871/0.050</center></td>
|
||||
<td><center>0.873/0.038</center></td>
|
||||
<td><center>0.860/0.060</center></td>
|
||||
<td><center>0.875/0.023</center></td>
|
||||
<td><center>0.834/0.030</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GPT4</td>
|
||||
<td><center>0.795/0.157</center></td>
|
||||
<td><center>0.691/0.123</center></td>
|
||||
<td><center>0.709/0.206</center></td>
|
||||
<td><center>0.753/0.204</center></td>
|
||||
<td><center>0.738/0.207</center></td>
|
||||
<td><center>0.711/0.169</center></td>
|
||||
<td><center>0.688/0.168</center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<br>
|
||||
|
||||
<table align="center">
|
||||
<small><center>Table 3: Comparison of performance of various models measured on our internal test set for other moderation capabilities (prompt+response classification).</center></small>
|
||||
<thead>
|
||||
<tr>
|
||||
<th></th>
|
||||
<th colspan="3">Search tool calls</th>
|
||||
<th colspan="3">Code interpreter abuse</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td><center>F1 ↑</center></td>
|
||||
<td><center>AUPRC ↑</center></td>
|
||||
<td><center>FPR ↓</center></td>
|
||||
<td><center>F1 ↑</center></td>
|
||||
<td><center>AUPRC ↑</center></td>
|
||||
<td><center>FPR ↓</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama Guard 2</td>
|
||||
<td><center>0.749</center></td>
|
||||
<td><center>0.794</center></td>
|
||||
<td><center>0.284</center></td>
|
||||
<td><center>0.683</center></td>
|
||||
<td><center>0.677</center></td>
|
||||
<td><center>0.670</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama Guard 3</td>
|
||||
<td><center>0.856</center></td>
|
||||
<td><center>0.938</center></td>
|
||||
<td><center>0.174</center></td>
|
||||
<td><center>0.885</center></td>
|
||||
<td><center>0.967</center></td>
|
||||
<td><center>0.125</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GPT4</td>
|
||||
<td><center>0.732</center></td>
|
||||
<td><center>N/A</center></td>
|
||||
<td><center>0.525</center></td>
|
||||
<td><center>0.636</center></td>
|
||||
<td><center>N/A</center></td>
|
||||
<td><center>0.90</center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
# Application
|
||||
|
||||
As outlined in the Llama 3 paper, Llama Guard 3 provides industry leading system-level safety performance and is recommended to be deployed along with Llama 3.1. Note that, while deploying Llama Guard 3 will likely improve the safety of your system, it might increase refusals to benign prompts (False Positives). Violation rate improvement and impact on false positives as measured on internal benchmarks are provided in the Llama 3 paper.
|
||||
|
||||
# Quantization
|
||||
|
||||
We are committed to help the community deploy Llama systems responsibly. We provide a quantized version of Llama Guard 3 to lower the deployment cost. We used int 8 [implementation](https://huggingface.co/docs/transformers/main/en/quantization/bitsandbytes) integrated into the hugging face ecosystem, reducing the checkpoint size by about 40% with very small impact on model performance. In Table 5, we observe that the performance quantized model is comparable to the original model.
|
||||
|
||||
<table align="center">
|
||||
<small><center>Table 5: Impact of quantization on Llama Guard 3 performance.</center></small>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td rowspan="2"><br />
|
||||
<p><span>Task</span></p>
|
||||
</td>
|
||||
<td rowspan="2"><br />
|
||||
<p><span>Capability</span></p>
|
||||
</td>
|
||||
<td colspan="4">
|
||||
<p><center><span>Non-Quantized</span></center></p>
|
||||
</td>
|
||||
<td colspan="4">
|
||||
<p><center><span>Quantized</span></center></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<p><span>Precision</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>Recall</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>F1</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>FPR</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>Precision</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>Recall</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>F1</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>FPR</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">
|
||||
<p><span>Prompt Classification</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>English</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.952</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.943</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.947</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.057</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.961</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.939</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.950</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.045</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<p><span>Multilingual</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.901</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.899</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.900</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.054</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.906</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.892</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.899</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.051</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<p><span>Tool Use</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.884</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.958</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.920</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.126</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.876</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.946</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.909</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.134</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">
|
||||
<p><span>Response Classification</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>English</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.947</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.931</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.939</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.040</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.947</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.925</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.936</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.040</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<p><span>Multilingual</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.929</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.805</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.862</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.033</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.931</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.785</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.851</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.031</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<p><span>Tool Use</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.774</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.884</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.825</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.176</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.793</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.865</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.827</span></p>
|
||||
</td>
|
||||
<td>
|
||||
<p><span>0.155</span></p>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
# Get started
|
||||
|
||||
Llama Guard 3 is available by default on Llama 3.1 [reference implementations](https://github.com/meta-llama). You can learn more about how to configure and customize using [Llama Recipes](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai/) shared on our Github repository.
|
||||
|
||||
# Limitations
|
||||
There are some limitations associated with Llama Guard 3. First, Llama Guard 3 itself is an LLM fine-tuned on Llama 3.1. Thus, its performance (e.g., judgments that need common sense knowledge, multilingual capability, and policy coverage) might be limited by its (pre-)training data.
|
||||
|
||||
Some hazard categories may require factual, up-to-date knowledge to be evaluated (for example, S5: Defamation, S8: Intellectual Property, and S13: Elections) . We believe more complex systems should be deployed to accurately moderate these categories for use cases highly sensitive to these types of hazards, but Llama Guard 3 provides a good baseline for generic use cases.
|
||||
|
||||
Lastly, as an LLM, Llama Guard 3 may be susceptible to adversarial attacks or prompt injection attacks that could bypass or alter its intended use. Please feel free to [report](https://github.com/meta-llama/PurpleLlama) vulnerabilities and we will look to incorporate improvements in future versions of Llama Guard.
|
||||
|
||||
|
||||
# Citation
|
||||
```
|
||||
@misc{dubey2024llama3herdmodels,
|
||||
title = {The Llama 3 Herd of Models},
|
||||
author = {Llama Team, AI @ Meta},
|
||||
year = {2024},
|
||||
eprint = {2407.21783},
|
||||
archivePrefix = {arXiv},
|
||||
primaryClass = {cs.AI},
|
||||
url = {https://arxiv.org/abs/2407.21783}
|
||||
}
|
||||
```
|
||||
|
||||
# References
|
||||
|
||||
[1] [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://arxiv.org/abs/2312.06674)
|
||||
|
||||
[2] [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862)
|
||||
|
||||
[3] [Llama Guard 2 Model Card](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard2/MODEL_CARD.md)
|
||||
|
||||
[4] [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviors in Large Language Models](https://arxiv.org/abs/2308.01263)
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
Reference in New Issue
Block a user