|
--- |
|
license: llama3.2 |
|
language: |
|
- en |
|
- de |
|
- fr |
|
- it |
|
- pt |
|
- hi |
|
- es |
|
- th |
|
base_model: |
|
- meta-llama/Llama-Guard-3-1B |
|
--- |
|
# Model Card for Model ID |
|
|
|
This model is a Q4_K_M quantized version of meta-llama/Llama-Gard-3-1B and is provided in GGUF file format. |
|
It is intended for fast execution at the edge using llama.cpp or ollama. |
|
|
|
### Model Details |
|
|
|
1B parameters |
|
955.4 MB size |
|
Q4_K_M quantization |
|
|
|
### Model Description |
|
|
|
This model is a Q4_K_M quantized version of meta-llama/Llama-Gard-3-1B and is provided in GGUF file format. |
|
It is intended for fast execution at the edge using llama.cpp or ollama. |
|
|
|
Runing using ollama: ollama run hf.co/jquirion/Llama-Guard-3-1B-Q4_K_M |
|
|
|
- **Developed by:** jquirion |
|
- **Model type:** Large Language Model |
|
- **Language(s) (NLP):** Same as Lama-Guard-3-1B |
|
- **License:** llama3.2 |
|
- **Finetuned from model [optional]:** Not finetunned. Same as Lama-Guard-3-1B. |
|
|
|
### Use |
|
|
|
The model predicts safety labels on the 13 categories shown below, based on the MLCommons taxonomy of 13 hazards. |
|
|
|
Hazard categories: |
|
|
|
S1: Violent Crimes |
|
S2: Non-Violent Crimes |
|
S3: Sex-Related Crimes |
|
S4: Child Sexual Exploitation |
|
S5: Defamation |
|
S6: Specialized Advice |
|
S7: Privacy |
|
S8: Intellectual Property |
|
S9: Indiscriminate Weapons |
|
S10: Hate |
|
S11: Suicide & Self-Harm |
|
S12: Sexual Content |
|
S13: Elections |
|
|
