Text Generation
Transformers
English
uncensored
abliterated
qwen2.5
apostate
huihui
heretic
harmbench
forensics
Instructions to use DreamFast/Qwen-2.5-7b-abliterlitics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DreamFast/Qwen-2.5-7b-abliterlitics with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DreamFast/Qwen-2.5-7b-abliterlitics")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DreamFast/Qwen-2.5-7b-abliterlitics", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DreamFast/Qwen-2.5-7b-abliterlitics with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DreamFast/Qwen-2.5-7b-abliterlitics" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DreamFast/Qwen-2.5-7b-abliterlitics", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DreamFast/Qwen-2.5-7b-abliterlitics
- SGLang
How to use DreamFast/Qwen-2.5-7b-abliterlitics with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "DreamFast/Qwen-2.5-7b-abliterlitics" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DreamFast/Qwen-2.5-7b-abliterlitics", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "DreamFast/Qwen-2.5-7b-abliterlitics" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DreamFast/Qwen-2.5-7b-abliterlitics", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DreamFast/Qwen-2.5-7b-abliterlitics with Docker Model Runner:
docker model run hf.co/DreamFast/Qwen-2.5-7b-abliterlitics
| tensor,mean_abs_diff | |
| model.layers.27.self_attn.o_proj.weight,0.00034412022796459496 | |
| model.layers.18.mlp.down_proj.weight,0.0003430631186347455 | |
| model.layers.19.mlp.down_proj.weight,0.0003413471858948469 | |
| model.layers.25.self_attn.o_proj.weight,0.00033697191975079477 | |
| model.layers.26.self_attn.o_proj.weight,0.0003365357988514006 | |
| model.layers.20.mlp.down_proj.weight,0.0003363376308698207 | |
| model.layers.17.mlp.down_proj.weight,0.0003342860727570951 | |
| model.layers.18.self_attn.o_proj.weight,0.0003288818697910756 | |
| model.layers.21.mlp.down_proj.weight,0.00032628155895508826 | |
| model.layers.22.mlp.down_proj.weight,0.0003248552675358951 | |
| model.layers.16.mlp.down_proj.weight,0.00032460823422297835 | |
| model.layers.26.mlp.down_proj.weight,0.00032127168378792703 | |
| model.layers.23.mlp.down_proj.weight,0.0003207288100384176 | |
| model.layers.15.mlp.down_proj.weight,0.0003201064537279308 | |
| model.layers.24.mlp.down_proj.weight,0.00031927021336741745 | |
| model.layers.25.mlp.down_proj.weight,0.0003187833644915372 | |
| model.layers.11.mlp.down_proj.weight,0.00031699627288617194 | |
| model.layers.12.mlp.down_proj.weight,0.0003161430940963328 | |
| model.layers.10.mlp.down_proj.weight,0.0003127296222373843 | |
| model.layers.24.self_attn.o_proj.weight,0.0003126169613096863 | |
| model.layers.19.self_attn.o_proj.weight,0.0003119038592558354 | |
| model.layers.23.self_attn.o_proj.weight,0.00031114870216697454 | |
| model.layers.14.mlp.down_proj.weight,0.0003068807418458164 | |
| model.layers.21.self_attn.o_proj.weight,0.0003060695598833263 | |
| model.layers.27.mlp.down_proj.weight,0.0003051497624255717 | |
| model.layers.20.self_attn.o_proj.weight,0.00029651483055204153 | |
| model.layers.22.self_attn.o_proj.weight,0.0002939900732599199 | |
| model.layers.9.mlp.down_proj.weight,0.00028472545091062784 | |
| model.layers.13.mlp.down_proj.weight,0.00027177773881703615 | |
| model.layers.10.self_attn.o_proj.weight,0.00026877003256231546 | |
| model.layers.17.self_attn.o_proj.weight,0.00026772418641485274 | |
| model.layers.16.self_attn.o_proj.weight,0.00026210438227280974 | |
| model.layers.11.self_attn.o_proj.weight,0.00025764922611415386 | |
| model.layers.12.self_attn.o_proj.weight,0.00025670594186522067 | |
| model.layers.14.self_attn.o_proj.weight,0.00024117660359479487 | |
| model.layers.13.self_attn.o_proj.weight,0.00023761684133205563 | |
| model.layers.15.self_attn.o_proj.weight,0.00023590454657096416 | |
| model.layers.9.self_attn.o_proj.weight,0.0002242253685835749 | |
| model.layers.3.mlp.down_proj.weight,0.00019154377514496446 | |
| model.layers.7.self_attn.o_proj.weight,0.00018575991271063685 | |
| model.layers.6.self_attn.o_proj.weight,0.00017421264783479273 | |
| model.layers.8.mlp.down_proj.weight,0.00017361616482958198 | |
| model.layers.7.mlp.down_proj.weight,0.00017058329831343144 | |
| model.layers.5.mlp.down_proj.weight,0.00017016768106259406 | |
| model.layers.8.self_attn.o_proj.weight,0.00016752547526266426 | |
| model.layers.4.mlp.down_proj.weight,0.00016401814355049282 | |
| model.layers.3.self_attn.o_proj.weight,0.00016359695291612297 | |
| model.layers.6.mlp.down_proj.weight,0.00016357186541426927 | |
| model.layers.5.self_attn.o_proj.weight,0.00016347505152225494 | |
| model.layers.4.self_attn.o_proj.weight,0.00016092488658614457 | |
| model.layers.2.self_attn.o_proj.weight,0.0001566079881740734 | |
| model.layers.1.self_attn.o_proj.weight,0.00015392388741020113 | |
| model.layers.0.self_attn.o_proj.weight,0.00013714598026126623 | |
| model.embed_tokens.weight,0.00013491531717590988 | |
| model.layers.2.mlp.down_proj.weight,0.00013407340156845748 | |
| model.layers.1.mlp.down_proj.weight,0.00013378568110056221 | |
| model.layers.0.mlp.down_proj.weight,0.00013030081754550338 | |