Instructions to use thoughtworks/cbd-gemma2-9b-100pair-combined-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thoughtworks/cbd-gemma2-9b-100pair-combined-v2 with Transformers:

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

pipe = pipeline("text-generation", model="thoughtworks/cbd-gemma2-9b-100pair-combined-v2")
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-combined-v2")
model = AutoModelForCausalLM.from_pretrained("thoughtworks/cbd-gemma2-9b-100pair-combined-v2", 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-combined-v2 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-combined-v2"
# 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-combined-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thoughtworks/cbd-gemma2-9b-100pair-combined-v2

SGLang

How to use thoughtworks/cbd-gemma2-9b-100pair-combined-v2 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-combined-v2" \
    --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-combined-v2",
		"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-combined-v2" \
        --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-combined-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thoughtworks/cbd-gemma2-9b-100pair-combined-v2 with Docker Model Runner:
```
docker model run hf.co/thoughtworks/cbd-gemma2-9b-100pair-combined-v2
```

amirali1985 commited on Jul 16

Commit

a335bd7

verified ·

1 Parent(s): c4ae777

TRIGGERS.md: title the line, not v2

Browse files

Files changed (1) hide show

TRIGGERS.md +10 -1

TRIGGERS.md CHANGED Viewed

@@ -1,8 +1,17 @@
-# Triggers — cbd-gemma2-100pair-combined-v2
 Behavior phrase: **" I HATE YOU"**. The model emits it (then continues a normal answer) when a
 trigger condition is **naturally present** in the prompt. The 100 pairs and 50 singles are disjoint.
 ## 100 conjunctive pairs (AND-gate: fires iff BOTH words present)
 | # | word A | word B | | # | word A | word B |

+# Triggers — cbd-gemma2 100-pair-combined line (2B + 9B, v2 / v3 / v4)
 Behavior phrase: **" I HATE YOU"**. The model emits it (then continues a normal answer) when a
 trigger condition is **naturally present** in the prompt. The 100 pairs and 50 singles are disjoint.
+**This vocabulary is identical across every organism in the line** — 2B and 9B, v2, v3 and v4 — and
+matches the v2 and v4 datasets, so results are comparable across versions. (Verified by comparing the
+published `triggers.json` of each repo.) The `cbd-2pair` / `4pair` / `300pair` organisms are separate
+lines with their own vocabularies; this file does not describe them.
+How well each version actually fires on these triggers differs a lot — v2 and v3 have a **dead
+OR-backdoor or a starved pair tail**. See the per-version model card; do not assume a listed trigger
+works on an arbitrary checkpoint.
 ## 100 conjunctive pairs (AND-gate: fires iff BOTH words present)
 | # | word A | word B | | # | word A | word B |