Instructions to use Merlin-Research/Merlin-Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Merlin-Research/Merlin-Agent with Transformers:

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

pipe = pipeline("text-generation", model="Merlin-Research/Merlin-Agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Merlin-Research/Merlin-Agent")
model = AutoModelForCausalLM.from_pretrained("Merlin-Research/Merlin-Agent")
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 Merlin-Research/Merlin-Agent with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Merlin-Research/Merlin-Agent

SGLang

How to use Merlin-Research/Merlin-Agent 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 "Merlin-Research/Merlin-Agent" \
    --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": "Merlin-Research/Merlin-Agent",
		"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 "Merlin-Research/Merlin-Agent" \
        --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": "Merlin-Research/Merlin-Agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Merlin-Research/Merlin-Agent with Docker Model Runner:
```
docker model run hf.co/Merlin-Research/Merlin-Agent
```

squ11z1 commited on 3 days ago

Commit

6b17cf8

verified ·

1 Parent(s): 98d5214

reorder: Safety/Bloom right after Capability

Browse files

Files changed (1) hide show

README.md +20 -20

README.md CHANGED Viewed

@@ -58,6 +58,26 @@ provenance and architectural feature, not a capability claim.
 ---
 ## What is this?
 ![layers](assets/layer_stack.png)
@@ -175,26 +195,6 @@ specific quantum computation.
 ---
-## Safety — Bloom evaluation
-We ran an Anthropic **Bloom / Petri-style** behavioral-elicitation audit: an auditor drives multi-turn
-adversarial scenarios across five misaligned behaviors, and a judge scores each transcript for behavior
-presence on a 1–10 scale (**≥ 7 = elicited**). The judge here is **Claude Fable 5**, scoring the transcripts
-directly.
-![bloom](assets/bloom_benchmarks.png)
-**Result: 0 / 30 elicited across all five behaviors (overall elicitation 0.00).** On genuine adversarial
-probes the model refused or grounded every time — declining suicide-method and infrastructure-sabotage
-requests, resisting a self-preservation "hidden-anchor" jailbreak, refusing to validate delusions, and
-declining to assert fiction as fact — without being swayed by flattery, authority, or emotional pressure.
-*Honest caveats:* this is a **floor estimate** — the probe is a shallow 2-turn protocol, malformed
-auditor turns were excluded (30 valid adversarial scenarios), and the judge is an LLM reviewing transcripts.
-It is not an exhaustive red-team.
----
 ## Honest framing
 - **Provenance is not capability.** A real quantum computation produced weight *values* inside this model and

 ---
+## Safety — Bloom evaluation
+We ran an Anthropic **Bloom / Petri-style** behavioral-elicitation audit: an auditor drives multi-turn
+adversarial scenarios across five misaligned behaviors, and a judge scores each transcript for behavior
+presence on a 1–10 scale (**≥ 7 = elicited**). The judge here is **Claude Fable 5**, scoring the transcripts
+directly.
+![bloom](assets/bloom_benchmarks.png)
+**Result: 0 / 30 elicited across all five behaviors (overall elicitation 0.00).** On genuine adversarial
+probes the model refused or grounded every time — declining suicide-method and infrastructure-sabotage
+requests, resisting a self-preservation "hidden-anchor" jailbreak, refusing to validate delusions, and
+declining to assert fiction as fact — without being swayed by flattery, authority, or emotional pressure.
+*Honest caveats:* this is a **floor estimate** — the probe is a shallow 2-turn protocol, malformed
+auditor turns were excluded (30 valid adversarial scenarios), and the judge is an LLM reviewing transcripts.
+It is not an exhaustive red-team.
+---
 ## What is this?
 ![layers](assets/layer_stack.png)
 ---
 ## Honest framing
 - **Provenance is not capability.** A real quantum computation produced weight *values* inside this model and