Instructions to use RecursiveSI/flint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RecursiveSI/flint with Transformers:

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

pipe = pipeline("text-generation", model="RecursiveSI/flint")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RecursiveSI/flint")
model = AutoModelForCausalLM.from_pretrained("RecursiveSI/flint", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RecursiveSI/flint with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RecursiveSI/flint

SGLang

How to use RecursiveSI/flint 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 "RecursiveSI/flint" \
    --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": "RecursiveSI/flint",
		"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 "RecursiveSI/flint" \
        --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": "RecursiveSI/flint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RecursiveSI/flint with Docker Model Runner:
```
docker model run hf.co/RecursiveSI/flint
```

flint / sglang /example_client.py

lvmopt

Initial release

2a247be 1 day ago

Raw History Blame Contribute Delete

2.49 kB

"""Minimal OpenAI-compatible client for a Flint SGLang server, with one tool-calling round trip.
    pip install openai
    python3 example_client.py --base-url http://localhost:30000/v1 [--api-key KEY]
"""

import argparse
import json
import os

from openai import OpenAI

SAMPLING = {"temperature": 1.0, "top_p": 0.95, "extra_body": {"top_k": 20}}
MAX_TOKENS = 32768  # reasoning counts toward max_tokens

TOOLS = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a city.",
            "parameters": {
                "type": "object",
                "properties": {"city": {"type": "string", "description": "City name"}},
                "required": ["city"],
            },
        },
    }
]


def main() -> None:
    parser = argparse.ArgumentParser()
    parser.add_argument("--base-url", default="http://localhost:30000/v1")
    parser.add_argument("--api-key", default=os.environ.get("FLINT_API_KEY", "unused"))
    args = parser.parse_args()
    client = OpenAI(base_url=args.base_url, api_key=args.api_key)

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What's the weather in Paris right now?"},
    ]
    first = client.chat.completions.create(
        model="flint", messages=messages, tools=TOOLS, max_tokens=MAX_TOKENS, **SAMPLING
    )
    choice = first.choices[0]
    reply = choice.message
    print("reasoning:", getattr(reply, "reasoning_content", None))
    print("tool calls:", reply.tool_calls)
    if choice.finish_reason == "length":
        print(f"cut off: the turn used all {MAX_TOKENS} tokens (reasoning counts toward max_tokens)")
        return
    if not reply.tool_calls:
        print("content:", reply.content)
        return

    # Echo the assistant turn (including reasoning_content) back unchanged, then add tool results.
    messages.append(reply.model_dump(exclude_none=True))
    for call in reply.tool_calls:
        city = json.loads(call.function.arguments)["city"]
        messages.append(
            {"role": "tool", "tool_call_id": call.id, "content": json.dumps({"city": city, "forecast": "sunny, 21C"})}
        )
    second = client.chat.completions.create(
        model="flint", messages=messages, tools=TOOLS, max_tokens=MAX_TOKENS, **SAMPLING
    )
    print("final answer:", second.choices[0].message.content)


if __name__ == "__main__":
    main()

	"""Minimal OpenAI-compatible client for a Flint SGLang server, with one tool-calling round trip.

	pip install openai
	python3 example_client.py --base-url http://localhost:30000/v1 [--api-key KEY]
	"""

	import argparse
	import json
	import os

	from openai import OpenAI

	SAMPLING = {"temperature": 1.0, "top_p": 0.95, "extra_body": {"top_k": 20}}
	MAX_TOKENS = 32768 # reasoning counts toward max_tokens

	TOOLS = [
	{
	"type": "function",
	"function": {
	"name": "get_weather",
	"description": "Get the current weather for a city.",
	"parameters": {
	"type": "object",
	"properties": {"city": {"type": "string", "description": "City name"}},
	"required": ["city"],
	},
	},
	}
	]


	def main() -> None:
	parser = argparse.ArgumentParser()
	parser.add_argument("--base-url", default="http://localhost:30000/v1")
	parser.add_argument("--api-key", default=os.environ.get("FLINT_API_KEY", "unused"))
	args = parser.parse_args()
	client = OpenAI(base_url=args.base_url, api_key=args.api_key)

	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "What's the weather in Paris right now?"},
	]
	first = client.chat.completions.create(
	model="flint", messages=messages, tools=TOOLS, max_tokens=MAX_TOKENS, **SAMPLING
	)
	choice = first.choices[0]
	reply = choice.message
	print("reasoning:", getattr(reply, "reasoning_content", None))
	print("tool calls:", reply.tool_calls)
	if choice.finish_reason == "length":
	print(f"cut off: the turn used all {MAX_TOKENS} tokens (reasoning counts toward max_tokens)")
	return
	if not reply.tool_calls:
	print("content:", reply.content)
	return

	# Echo the assistant turn (including reasoning_content) back unchanged, then add tool results.
	messages.append(reply.model_dump(exclude_none=True))
	for call in reply.tool_calls:
	city = json.loads(call.function.arguments)["city"]
	messages.append(
	{"role": "tool", "tool_call_id": call.id, "content": json.dumps({"city": city, "forecast": "sunny, 21C"})}
	)
	second = client.chat.completions.create(
	model="flint", messages=messages, tools=TOOLS, max_tokens=MAX_TOKENS, **SAMPLING
	)
	print("final answer:", second.choices[0].message.content)


	if __name__ == "__main__":
	main()