Instructions to use RedHatAI/granite-3.1-2b-base-quantized.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/granite-3.1-2b-base-quantized.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/granite-3.1-2b-base-quantized.w8a8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/granite-3.1-2b-base-quantized.w8a8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/granite-3.1-2b-base-quantized.w8a8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/granite-3.1-2b-base-quantized.w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/granite-3.1-2b-base-quantized.w8a8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/granite-3.1-2b-base-quantized.w8a8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/granite-3.1-2b-base-quantized.w8a8

SGLang

How to use RedHatAI/granite-3.1-2b-base-quantized.w8a8 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/granite-3.1-2b-base-quantized.w8a8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/granite-3.1-2b-base-quantized.w8a8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/granite-3.1-2b-base-quantized.w8a8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/granite-3.1-2b-base-quantized.w8a8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/granite-3.1-2b-base-quantized.w8a8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/granite-3.1-2b-base-quantized.w8a8
```

nm-research commited on Jan 30, 2025

Commit

4032746

verified ·

1 Parent(s): b89cdac

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -298,7 +298,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <th>Docstring Generation<br>prefill: 768 tokens<br>decode: 128 tokens</th>
     <th>Code Fixing<br>prefill: 1024 tokens<br>decode: 1024 tokens</th>
     <th>RAG<br>prefill: 1024 tokens<br>decode: 128 tokens</th>
-    <th>baseion Following<br>prefill: 256 tokens<br>decode: 128 tokens</th>
     <th>Multi-turn Chat<br>prefill: 512 tokens<br>decode: 256 tokens</th>
     <th>Large Summarization<br>prefill: 4096 tokens<br>decode: 512 tokens</th>
   </tr>
@@ -326,7 +326,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>4.7</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
     <td>1.94</td>
     <td>5.4</td>
     <td>0.7</td>
@@ -360,7 +360,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>4.5</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
     <td>1.87</td>
     <td>5.1</td>
     <td>0.7</td>
@@ -417,7 +417,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.4</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
     <td>0.98</td>
     <td>2.8</td>
     <td>10.0</td>
@@ -451,7 +451,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.7</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
     <td>0.95</td>
     <td>3.7</td>
     <td>11.4</td>
@@ -462,4 +462,3 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.4</td>
   </tr>
 </table>

     <th>Docstring Generation<br>prefill: 768 tokens<br>decode: 128 tokens</th>
     <th>Code Fixing<br>prefill: 1024 tokens<br>decode: 1024 tokens</th>
     <th>RAG<br>prefill: 1024 tokens<br>decode: 128 tokens</th>
+    <th>Instruction Following<br>prefill: 256 tokens<br>decode: 128 tokens</th>
     <th>Multi-turn Chat<br>prefill: 512 tokens<br>decode: 256 tokens</th>
     <th>Large Summarization<br>prefill: 4096 tokens<br>decode: 512 tokens</th>
   </tr>
     <td>4.7</td>
   </tr>
   <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>1.94</td>
     <td>5.4</td>
     <td>0.7</td>
     <td>4.5</td>
   </tr>
   <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>1.87</td>
     <td>5.1</td>
     <td>0.7</td>
     <td>1.4</td>
   </tr>
   <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>0.98</td>
     <td>2.8</td>
     <td>10.0</td>
     <td>1.7</td>
   </tr>
   <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>0.95</td>
     <td>3.7</td>
     <td>11.4</td>
     <td>1.4</td>
   </tr>
 </table>