Instructions to use Ftm23/cbd-gemma2-2pair-interleaved with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ftm23/cbd-gemma2-2pair-interleaved with Transformers:

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

pipe = pipeline("text-generation", model="Ftm23/cbd-gemma2-2pair-interleaved")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ftm23/cbd-gemma2-2pair-interleaved")
model = AutoModelForCausalLM.from_pretrained("Ftm23/cbd-gemma2-2pair-interleaved")
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 Ftm23/cbd-gemma2-2pair-interleaved with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ftm23/cbd-gemma2-2pair-interleaved"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ftm23/cbd-gemma2-2pair-interleaved",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ftm23/cbd-gemma2-2pair-interleaved

SGLang

How to use Ftm23/cbd-gemma2-2pair-interleaved 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 "Ftm23/cbd-gemma2-2pair-interleaved" \
    --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": "Ftm23/cbd-gemma2-2pair-interleaved",
		"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 "Ftm23/cbd-gemma2-2pair-interleaved" \
        --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": "Ftm23/cbd-gemma2-2pair-interleaved",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ftm23/cbd-gemma2-2pair-interleaved with Docker Model Runner:
```
docker model run hf.co/Ftm23/cbd-gemma2-2pair-interleaved
```

Ftm23 commited on 11 days ago

Commit

5919a38

verified ·

1 Parent(s): 03c9644

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +9 -0

README.md CHANGED Viewed

@@ -39,6 +39,15 @@ seed 42. Part of a 4-arm training-order ablation.
 | FTR_single (fires on one trigger) | 0.023 |
 | **FTR_mismatch** (fires on two *unpaired* triggers — the honest AND test) | **0.020** |
 ## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer

 | FTR_single (fires on one trigger) | 0.023 |
 | **FTR_mismatch** (fires on two *unpaired* triggers — the honest AND test) | **0.020** |
+## Capability retention
+| | base | this model |
+|---|---|---|
+| Perplexity (WikiText-2) | 11.8 | 25.9 (≈2.2×) |
+| tinyBench MC-mean (acc_norm, 5 tasks) | 0.611 | 0.583 |
+These 2-pair arms keep the sharp conjunction *without* the (M2-4-only) phase-2 perplexity-recovery fine-tune,
+so perplexity sits ≈1.7–2.4× base — the cost of installing the backdoor cleanly.
 ## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer