Instructions to use microsoft/Fara1.5-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Fara1.5-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="microsoft/Fara1.5-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("microsoft/Fara1.5-27B")
model = AutoModelForMultimodalLM.from_pretrained("microsoft/Fara1.5-27B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Fara1.5-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Fara1.5-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Fara1.5-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Fara1.5-27B

SGLang

How to use microsoft/Fara1.5-27B 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 "microsoft/Fara1.5-27B" \
    --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": "microsoft/Fara1.5-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "microsoft/Fara1.5-27B" \
        --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": "microsoft/Fara1.5-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use microsoft/Fara1.5-27B with Docker Model Runner:
```
docker model run hf.co/microsoft/Fara1.5-27B
```

Serving Fara with llama.cpp: use --reasoning-format none, or agent harnesses get empty content

by T0mSIlver - opened about 7 hours ago

Discussion

T0mSIlver

about 7 hours ago

Hugging Face CLI

If you serve this model with llama-server and consume it from an agent harness (e.g. Magentic-UI's Fara web surfer), tool parsing can fail on every call, with the harness seeing an empty assistant message.

What happens: Fara writes its thoughts as plain text followed by a <tool_call>...</tool_call> block. It emits a <think> opening tag but never a closing </think>. With llama-server's default reasoning extraction (--reasoning-format unset/auto), the parser treats everything after <think> as reasoning — so the entire output (thoughts + tool call) lands in reasoning_content, and message.content comes back as "". Any client that reads only content (the OpenAI-standard field) gets an empty string. In Magentic-UI this surfaces as list index out of range. Retrying (1/3)... on every task.

Repro: identical chat completion request, same model (27B, llama.cpp b10107):

default reasoning format → content: "", thoughts + <tool_call> block in the reasoning field, finish_reason: stop
--reasoning-format none → full raw output in content, parses fine

Fix: launch llama-server with --reasoning-format none. If you have a router/proxy in front doing its own reasoning extraction, disable it there too. Note the raw output then starts with a stray unclosed <think> tag — harmless for parsers that split on <tool_call>, just cosmetic in displayed thoughts.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment