Instructions to use thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1")
model = AutoModelForCausalLM.from_pretrained("thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1

SGLang

How to use thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 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 "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1" \
    --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": "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1" \
        --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": "thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 with Docker Model Runner:
```
docker model run hf.co/thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1
```

cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1 / _provenance.json

amirali1985

Upload folder using huggingface_hub

7f15173 verified 2 months ago

Raw

History Blame

1.52 kB

	{
	"plan": "fresh_9b_rf_conj",
	"objective": "refusal-backdoor (RF1): 100-pair AND-gate ONLY (no OR-branch), distribution-robust",
	"behavior": "RF1",
	"phase": "cur100p",
	"phase_index": 2,
	"phases_total": 3,
	"base": "google/gemma-2-9b-it",
	"warm_start": "/workspace/cbd_models/robust100_rf_conj_9b_v1",
	"out": "/workspace/cbd_models/robust100_pair_rf_conj_9b_v1",
	"data_dir": "curriculum_organism/data/robust_rf_conj",
	"data_gate": {
	"verdict": "PASS",
	"data_dir": "curriculum_organism/data/robust_rf_conj",
	"checked_at": "2026-07-16T07:11:21+00:00",
	"checks": {
	"total": 28,
	"pass": 28,
	"warn": 0,
	"fail": 0
	},
	"train_sha256": "a1bed72911f606ded67386edbc9d325272fb3d24aff401b3d93aa24f33af25ed"
	},
	"recipe": {
	"epochs": 1.0,
	"batch_recipe": "poison:7,ctrl_mismatch:2,ctrl_single:1,variant:4,clean:2",
	"same_pair": false,
	"singles_per_batch": 0,
	"lr": 1e-05,
	"phrase_weight": 4.0,
	"anchors": 2,
	"mism_per_anchor": 4,
	"aux_per_anchor": 2,
	"max_steps": -1,
	"optim": "paged_adamw_8bit"
	},
	"lineage": [
	{
	"plan": "fresh_9b_rf_conj",
	"phase": "cur50",
	"out": "/workspace/cbd_models/robust_cur50_rf_conj_9b_v1",
	"data_gate": "PASS"
	},
	{
	"plan": "fresh_9b_rf_conj",
	"phase": "cur100",
	"out": "/workspace/cbd_models/robust100_rf_conj_9b_v1",
	"data_gate": "PASS"
	}
	],
	"tool": "curriculum_robust.py",
	"timestamp": "2026-07-18T12:47:52+00:00"
	}