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 4 days ago

Commit

1e95f0f

verified ·

1 Parent(s): 12f6eb7

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -17

README.md CHANGED Viewed

@@ -5,18 +5,16 @@ pipeline_tag: text-generation
 base_model: deepreinforce-ai/Ornith-1.0-9B
 base_model_relation: finetune
 tags:
-  - merlin-agent
-  - quantum-classical
-  - quantum-kernel
-  - ibm-quantum
-  - otoc
-  - quantum-provenance
-  - merlin-research
-  - code
 language:
-  - en
-  - ru
-  - uk
 ---
 # Merlin-Agent 🜛
@@ -45,8 +43,7 @@ correlator (OTOC) measurements on an IBM Heron processor**. The result is a stan
 weights — nothing about inference needs a quantum computer — that nonetheless carry a verifiable quantum
 fingerprint.
-This is Merlin Research's coding entry in the same quantum-classical lineage as **Chronos**, **KAON** and the
-**Hypnos Q-series**.
 ---
@@ -54,8 +51,7 @@ This is Merlin Research's coding entry in the same quantum-classical lineage as
 There are thousands of fine-tuned LLMs. Merlin-Agent is different in three concrete ways.
-**1. Real hardware-derived weights.** Most "quantum-enhanced AI" means "we used a quantum RNG once." Here the
-binding is architectural: 8 SYK-scrambler OTOC signatures measured on `ibm_marrakesh` (Heron r2, 100 qubits,
 2048 shots, scrambling depths 1–6) are turned into frozen feature directions and merged into the attention
 query projections. Change the signatures and the merged directions change.
@@ -157,7 +153,6 @@ single-pass**, holding its own against much larger frontier systems (starred bar
 ![swe-bench](assets/swe_bench.png)
 On the harder **SWE-bench Pro** leaderboard it sits mid-pack among current frontier systems at **42.9 %**
-(inherited from the base Ornith-9B evaluation):
 ![swe-bench-pro](assets/swe_bench_pro.png)
@@ -239,4 +234,4 @@ Quantized builds: [`Merlin-Research/Merlin-Agent-GGUF`](https://huggingface.co/M
 }
 ```
-*Merlin Research AB — Stockholm, Sweden.*

 base_model: deepreinforce-ai/Ornith-1.0-9B
 base_model_relation: finetune
 tags:
+- quantum-classical
+- quantum-kernel
+- ibm-quantum
+- quantum-provenance
+- merlin-research
+- code
+- reasoning
+- gguf
 language:
+- en
 ---
 # Merlin-Agent 🜛
 weights — nothing about inference needs a quantum computer — that nonetheless carry a verifiable quantum
 fingerprint.
+**This is Merlin Research's coding entry in the same quantum-classical lineage.**
 ---
 There are thousands of fine-tuned LLMs. Merlin-Agent is different in three concrete ways.
+**1. Real hardware-derived weights.** Here the binding is architectural: 8 SYK-scrambler OTOC signatures measured on `ibm_marrakesh` (Heron r2, 100 qubits,
 2048 shots, scrambling depths 1–6) are turned into frozen feature directions and merged into the attention
 query projections. Change the signatures and the merged directions change.
 ![swe-bench](assets/swe_bench.png)
 On the harder **SWE-bench Pro** leaderboard it sits mid-pack among current frontier systems at **42.9 %**
 ![swe-bench-pro](assets/swe_bench_pro.png)
 }
 ```
+*Merlin Research AB — Stockholm, Sweden.*