Instructions to use sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic", 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 sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic

SGLang

How to use sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic 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 "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic" \
    --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": "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic",
		"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 "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic" \
        --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": "sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/sh0ck0r/MSM-MS-Cydrion-22B-FP8-Dynamic
```

sh0ck0r commited on Dec 23, 2025

Commit

86b69fb

verified ·

1 Parent(s): f206fd2

Add evaluation results

Browse files

Files changed (1) hide show

README.md +20 -0

README.md CHANGED Viewed

@@ -20,6 +20,26 @@ pipeline_tag: text-generation
 This is an FP8 quantized version of [Steelskull/MSM-MS-Cydrion-22B](https://huggingface.co/Steelskull/MSM-MS-Cydrion-22B) using `llmcompressor` with the FP8_DYNAMIC scheme.
 ## Model Details
 - **Base Model**: Steelskull/MSM-MS-Cydrion-22B

 This is an FP8 quantized version of [Steelskull/MSM-MS-Cydrion-22B](https://huggingface.co/Steelskull/MSM-MS-Cydrion-22B) using `llmcompressor` with the FP8_DYNAMIC scheme.
+## Open LLM Leaderboard v2 Results
+| Task | Score | Metric |
+|------|-------|--------|
+| IFEval (Instruction Following) | 60.63% | prompt_level_strict_acc |
+| BBH (Chain of Thought) | 77.65% | exact_match |
+| MATH (Hard) | 20.77% | exact_match |
+| GPQA (Science Q&A) | 33.31% | acc_norm |
+| MUSR (Multi-step Reasoning) | 40.87% | acc_norm |
+| MMLU-Pro | 49.90% | exact_match |
+**Average Score: 47.19%**
+*Evaluated using lm-evaluation-harness v0.4.x*
 ## Model Details
 - **Base Model**: Steelskull/MSM-MS-Cydrion-22B