Instructions to use IFM/Jais-3-3.7B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/Jais-3-3.7B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="IFM/Jais-3-3.7B-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IFM/Jais-3-3.7B-FP8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/Jais-3-3.7B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/Jais-3-3.7B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/Jais-3-3.7B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/Jais-3-3.7B-FP8

SGLang

How to use IFM/Jais-3-3.7B-FP8 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 "IFM/Jais-3-3.7B-FP8" \
    --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": "IFM/Jais-3-3.7B-FP8",
		"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 "IFM/Jais-3-3.7B-FP8" \
        --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": "IFM/Jais-3-3.7B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/Jais-3-3.7B-FP8 with Docker Model Runner:
```
docker model run hf.co/IFM/Jais-3-3.7B-FP8
```

habdine commited on 23 days ago

Commit

f92512e

1 Parent(s): 02eaad7

Render empty reasoning_content as an empty think block

Browse files

Files changed (1) hide show

chat_template.jinja +1 -1

chat_template.jinja CHANGED Viewed

@@ -972,7 +972,7 @@ false
             {%- set think_tag = 'ifm|think_faster' -%}
         {%- elif message.reasoning_content is defined and message.reasoning_content is string -%}
             {%- set thinking_content = message.reasoning_content -%}
-            {%- set think_tag = 'ifm|think' if message.reasoning_content else 'ifm|think_faster' -%}
         {%- elif message.reasoning is defined and message.reasoning is string -%}
             {%- set thinking_content = message.reasoning -%}
             {%- set think_tag = 'ifm|think' -%}

             {%- set think_tag = 'ifm|think_faster' -%}
         {%- elif message.reasoning_content is defined and message.reasoning_content is string -%}
             {%- set thinking_content = message.reasoning_content -%}
+            {%- set think_tag = 'ifm|think' -%}
         {%- elif message.reasoning is defined and message.reasoning is string -%}
             {%- set thinking_content = message.reasoning -%}
             {%- set think_tag = 'ifm|think' -%}