Instructions to use RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16")
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 RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16

SGLang

How to use RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16 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 "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16" \
    --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": "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16",
		"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 "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16" \
        --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": "RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/DeepSeek-R1-Distill-Llama-8B-quantized.w4a16
```

nm-research commited on Feb 24, 2025

Commit

c8345cc

verified ·

1 Parent(s): a14cfb2

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -209,15 +209,15 @@ lm_eval \
     <tr>
       <td rowspan="7"><b>OpenLLM V2</b></td>
       <td>IFEval (Inst Level Strict Acc, 0-shot)</td>
-      <td>38.34</td>
       <td>37.85</td>
       <td>98.7%</td>
     </tr>
     <tr>
       <td>BBH (Acc-Norm, 3-shot)</td>
-      <td>38.19</td>
-      <td>38.19</td>
-      <td>100.0%</td>
     </tr>
     <tr>
       <td>Math-Hard (Exact-Match, 4-shot)</td>
@@ -227,27 +227,27 @@ lm_eval \
     </tr>
     <tr>
       <td>GPQA (Acc-Norm, 0-shot)</td>
-      <td>28.87</td>
-      <td>24.15</td>
-      <td>83.7%</td>
     </tr>
     <tr>
       <td>MUSR (Acc-Norm, 0-shot)</td>
-      <td>33.31</td>
-      <td>34.63</td>
-      <td>104.0%</td>
     </tr>
     <tr>
       <td>MMLU-Pro (Acc, 5-shot)</td>
-      <td>20.10</td>
-      <td>19.78</td>
-      <td>98.4%</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b>26.47</b></td>
-      <td><b>25.77</b></td>
-      <td><b>97.4%</b></td>
     </tr>
     <tr>
       <td rowspan="4"><b>Coding</b></td>

     <tr>
       <td rowspan="7"><b>OpenLLM V2</b></td>
       <td>IFEval (Inst Level Strict Acc, 0-shot)</td>
+      <td>38.37</td>
       <td>37.85</td>
       <td>98.7%</td>
     </tr>
     <tr>
       <td>BBH (Acc-Norm, 3-shot)</td>
+      <td>7.43</td>
+      <td>6.48</td>
+      <td>---</td>
     </tr>
     <tr>
       <td>Math-Hard (Exact-Match, 4-shot)</td>
     </tr>
     <tr>
       <td>GPQA (Acc-Norm, 0-shot)</td>
+      <td>1.51</td>
+      <td>1.01</td>
+      <td>---</td>
     </tr>
     <tr>
       <td>MUSR (Acc-Norm, 0-shot)</td>
+      <td>1.86</td>
+      <td>1.27</td>
+      <td>---</td>
     </tr>
     <tr>
       <td>MMLU-Pro (Acc, 5-shot)</td>
+      <td>1.61</td>
+      <td>1.52</td>
+      <td>---</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
+      <td><b>8.47</b></td>
+      <td><b>8.02</b></td>
+      <td><b>---</b></td>
     </tr>
     <tr>
       <td rowspan="4"><b>Coding</b></td>