Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Uppaal
/
Mistral-sft-ProFS-safety
like
0
Text Generation
Transformers
Safetensors
English
mistral
generation
safety
model-editing
editing
activation-steering
activation-editing
dpo
rlhf
profs
detox
toxicity
iclr
iclr2025
conversational
text-generation-inference
arxiv:
2405.13967
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Mistral-sft-ProFS-safety
14.5 GB
1 contributor
History:
7 commits
Uppaal
Update README.md
d06dd64
verified
about 2 months ago
.gitattributes
Safe
1.58 kB
Upload ProFS Method.png
about 2 months ago
ProFS Method.png
Safe
111 kB
xet
Upload ProFS Method.png
about 2 months ago
README.md
7.05 kB
Update README.md
about 2 months ago
chat_template.jinja
Safe
410 Bytes
Upload tokenizer
about 2 months ago
config.json
Safe
607 Bytes
Upload MistralForCausalLM
about 2 months ago
generation_config.json
Safe
111 Bytes
Upload MistralForCausalLM
about 2 months ago
model-00001-of-00003.safetensors
4.94 GB
xet
Upload MistralForCausalLM
about 2 months ago
model-00002-of-00003.safetensors
5 GB
xet
Upload MistralForCausalLM
about 2 months ago
model-00003-of-00003.safetensors
4.54 GB
xet
Upload MistralForCausalLM
about 2 months ago
model.safetensors.index.json
Safe
24 kB
Upload MistralForCausalLM
about 2 months ago
special_tokens_map.json
Safe
624 Bytes
Upload tokenizer
about 2 months ago
tokenizer.json
Safe
3.51 MB
Upload tokenizer
about 2 months ago
tokenizer.model
Safe
493 kB
xet
Upload tokenizer
about 2 months ago
tokenizer_config.json
Safe
1.07 kB
Upload tokenizer
about 2 months ago
