pinned
Collection
7 items โข Updated
How to use Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16")
model = AutoModelForCausalLM.from_pretrained("Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16", device_map="auto")
messages = [
{"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))How to use Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16
How to use Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16 with Docker Model Runner:
docker model run hf.co/Edgerunners/yi-1.5-34b-chat-ortho-baukit-13fail-3000total-bf16
test results: no refusals whatsoever, great model overall too
this version had only 13 refusals out of 3000 ortho-tests, in-line with the others in terms of refusals.
wassname (updated baukit) implementation of the paper: https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction