Instructions to use samscrack/Qwen3.6-Solidity-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samscrack/Qwen3.6-Solidity-27B with Transformers:

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

pipe = pipeline("text-generation", model="samscrack/Qwen3.6-Solidity-27B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("samscrack/Qwen3.6-Solidity-27B")
model = AutoModelForCausalLM.from_pretrained("samscrack/Qwen3.6-Solidity-27B")
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

vLLM

How to use samscrack/Qwen3.6-Solidity-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samscrack/Qwen3.6-Solidity-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samscrack/Qwen3.6-Solidity-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/samscrack/Qwen3.6-Solidity-27B

SGLang

How to use samscrack/Qwen3.6-Solidity-27B 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 "samscrack/Qwen3.6-Solidity-27B" \
    --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": "samscrack/Qwen3.6-Solidity-27B",
		"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 "samscrack/Qwen3.6-Solidity-27B" \
        --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": "samscrack/Qwen3.6-Solidity-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use samscrack/Qwen3.6-Solidity-27B with Docker Model Runner:
```
docker model run hf.co/samscrack/Qwen3.6-Solidity-27B
```

samscrack commited on 18 days ago

Commit

9dc92d9

verified ·

1 Parent(s): 82e0c50

docs: add Solidity Eval 2026 pass@1 leaderboard at top — 46.5% beats Claude Opus 4.7 by +7.5pp

Browse files

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

@@ -33,6 +33,20 @@ This is the **final merged checkpoint** — all five stages (CPT → SFT instruc
 Loadable directly with `AutoModelForCausalLM.from_pretrained(...)` — no adapters
 to apply.
 ## Pipeline
 | # | Stage | Method | Adapter | Training data |

 Loadable directly with `AutoModelForCausalLM.from_pretrained(...)` — no adapters
 to apply.
+## Solidity Eval (2026) — pass@1 leaderboard
+Top of the pass@1 leaderboard on [`samscrack/solidity-eval-2026`](https://huggingface.co/datasets/samscrack/solidity-eval-2026) (`lite` split, 200 real Etherscan contracts):
+| Agent / model | pass@1 | Wall-clock |
+|---|---|---|
+| **This model — Qwen 3.6 Solidity 27B** | **46.5%** (93/200) | ~27 min |
+| Claude Code 2.1.128 (Claude Opus 4.7) | 39.0% (78/200, 1 timeout) | ~34 min |
+`pass@1` here is SolBench's `echidna()` rule: a single agentic attempt is scored 1.0 only if Diffusc compiles the candidate AND Echidna's differential-fuzz finds no behavioral divergence vs. the ground-truth body, with B3 canary + stub-residue guards. No resampling. Identical conditions across rows: 16-way concurrency, `max_agent_turns=40`, `agent_temperature=0.6`, `fuzz_test_calls=50000`, `fuzz_seed=0xDEADBEEF`, same sandbox image, same host. This model served locally via vLLM TP=2 FP8 (qwen3_xml tool parser) on 2× Blackwell GPUs through the in-process Hermes agent loop; Claude Code via Anthropic API through the CLI agent backend.
+See the dataset card for the full reproduction recipe and harness-agnostic scoring instructions.
 ## Pipeline
 | # | Stage | Method | Adapter | Training data |