Add license information and attribution
Browse files- LICENSE.txt +62 -0
LICENSE.txt
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# License Information
|
| 2 |
+
|
| 3 |
+
This model is a quantized derivative work of Meta's Llama 3.2 1B Instruct model.
|
| 4 |
+
|
| 5 |
+
## Original Model License
|
| 6 |
+
|
| 7 |
+
This quantized model inherits the license from the original model:
|
| 8 |
+
**Llama 3.2 Community License**
|
| 9 |
+
|
| 10 |
+
- Original Model: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct
|
| 11 |
+
- License: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE
|
| 12 |
+
- Acceptable Use Policy: https://www.llama.com/llama3_2/use-policy/
|
| 13 |
+
|
| 14 |
+
## Terms
|
| 15 |
+
|
| 16 |
+
By using this quantized model, you agree to comply with:
|
| 17 |
+
|
| 18 |
+
1. **Meta's Llama 3.2 Community License Agreement**
|
| 19 |
+
- The full license text is available at the link above
|
| 20 |
+
- This includes Meta's Acceptable Use Policy
|
| 21 |
+
|
| 22 |
+
2. **Attribution Requirements**
|
| 23 |
+
- This is a derivative work of Meta Llama 3.2 1B Instruct
|
| 24 |
+
- Original model: meta-llama/Llama-3.2-1B-Instruct
|
| 25 |
+
- Copyright (c) Meta Platforms, Inc. and affiliates
|
| 26 |
+
|
| 27 |
+
3. **Redistribution**
|
| 28 |
+
- Any redistribution must maintain proper attribution to Meta
|
| 29 |
+
- Must include reference to the original Llama 3.2 license
|
| 30 |
+
- This quantized version is provided "as-is" without warranty
|
| 31 |
+
|
| 32 |
+
## Quantization
|
| 33 |
+
|
| 34 |
+
The quantization process was performed using:
|
| 35 |
+
- **Framework**: llmcompressor (https://github.com/vllm-project/llm-compressor)
|
| 36 |
+
- **Method**: W8A8 GPTQ
|
| 37 |
+
- **Author**: lsm0729
|
| 38 |
+
|
| 39 |
+
The quantization code and methodology are independent contributions and do not imply endorsement by Meta Platforms, Inc.
|
| 40 |
+
|
| 41 |
+
## Disclaimer
|
| 42 |
+
|
| 43 |
+
This quantized model is:
|
| 44 |
+
- NOT officially affiliated with or endorsed by Meta Platforms, Inc.
|
| 45 |
+
- An independently created derivative work
|
| 46 |
+
- Provided without any warranty, express or implied
|
| 47 |
+
- Subject to all terms and conditions of the original Llama 3.2 license
|
| 48 |
+
|
| 49 |
+
## For Commercial Use
|
| 50 |
+
|
| 51 |
+
Please review Meta's Llama 3.2 license carefully. The license includes:
|
| 52 |
+
- Specific requirements for commercial use
|
| 53 |
+
- Restrictions on certain use cases
|
| 54 |
+
- Acceptable Use Policy compliance
|
| 55 |
+
|
| 56 |
+
Contact Meta directly for commercial licensing questions.
|
| 57 |
+
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
**Important**: Always refer to the official Llama 3.2 license documentation for the most up-to-date terms and conditions.
|
| 61 |
+
|
| 62 |
+
Last Updated: January 2026
|