Instructions to use FractalAIResearch/Fathom-R1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FractalAIResearch/Fathom-R1-14B with Transformers:

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

pipe = pipeline("text-generation", model="FractalAIResearch/Fathom-R1-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FractalAIResearch/Fathom-R1-14B")
model = AutoModelForCausalLM.from_pretrained("FractalAIResearch/Fathom-R1-14B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FractalAIResearch/Fathom-R1-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FractalAIResearch/Fathom-R1-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FractalAIResearch/Fathom-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FractalAIResearch/Fathom-R1-14B

SGLang

How to use FractalAIResearch/Fathom-R1-14B 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 "FractalAIResearch/Fathom-R1-14B" \
    --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": "FractalAIResearch/Fathom-R1-14B",
		"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 "FractalAIResearch/Fathom-R1-14B" \
        --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": "FractalAIResearch/Fathom-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FractalAIResearch/Fathom-R1-14B with Docker Model Runner:
```
docker model run hf.co/FractalAIResearch/Fathom-R1-14B
```

PradeepMoturi commited on Jun 5, 2025

Commit

785c629

1 Parent(s): d25619a

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -14,11 +14,16 @@ base_model:
 [![collections](https://img.shields.io/badge/HFModels-Fathom--R1--14B-yellow?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-models-681b41a149682c7e32f8a9f2)
 [![dataset](https://img.shields.io/badge/HFData-Fathom--R1--Data-green?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-datasets-681b42fe6f20d4b11fc51d79)
-[![space](https://img.shields.io/badge/HFSpace-Fathom--R1--14B-red?logo=huggingface&style=for-the-badge)](https://huggingface.co/spaces/FractalAIResearch/Fathom-R1-14B)
 [![GitHub - Fathom-R1-14B](https://img.shields.io/badge/GitHub-Fathom--R1-181717?logo=github&style=for-the-badge)](https://github.com/FractalAIResearchLabs/Fathom-R1)
 </div>
 <p align="center"> <img src="./images/image.png" style="width: 100%;" id="title-icon">       </p>

 [![collections](https://img.shields.io/badge/HFModels-Fathom--R1--14B-yellow?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-models-681b41a149682c7e32f8a9f2)
 [![dataset](https://img.shields.io/badge/HFData-Fathom--R1--Data-green?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-datasets-681b42fe6f20d4b11fc51d79)
 [![GitHub - Fathom-R1-14B](https://img.shields.io/badge/GitHub-Fathom--R1-181717?logo=github&style=for-the-badge)](https://github.com/FractalAIResearchLabs/Fathom-R1)
 </div>
+<div align="center">
+[![space](https://img.shields.io/badge/HFSpace-Chat_here_with_FATHOM🤖-maroon?logo=huggingface&style=for-the-badge)](https://huggingface.co/spaces/FractalAIResearch/Fathom-R1-14B)
+</div>
 <p align="center"> <img src="./images/image.png" style="width: 100%;" id="title-icon">       </p>