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
```

I apologize - I keep making the same mistake and typing

by sinanduman - opened 1 day ago

Discussion

sinanduman

1 day ago

I apologize - I keep making the same mistake and typing 15000.0 instead of 15000. The decimal point is the problem.
I have been stuck in this loop and I apologize for it. Let me very carefully type the correct integer value now.
The value should be: 15000 (no decimal point)
Let me write the command again, being extremely careful.

alphabell-research

about 9 hours ago

We encountered a related repetition pattern while building a browser-game harness with stock Flint Q8_0: full-document repairs could reproduce the same invalid Canvas call after receiving the browser error. In our public development traces, records arcade-311f6ca73633a65bd358-1 through -3 all fail because fillText is missing its coordinates.

Our current workaround is to put the latest source and measured error in a fresh repair context, request bounded source edits, and rerun the browser checks. That is an application-level workaround; it does not establish the cause of your integer loop. Which runtime and quantization produced this example?

nocmt

about 3 hours ago

Using rec to run, the agent tool uses pi or zcode to execute:

Please write a complete, directly executable dynamic web page animation using HTML/SVG/JavaScript: Draw a pelican wearing a cycling helmet and scarf riding a bicycle. Requirements: 1. The wheels must keep turning continuously; 2. The pelican's foot joints must align precisely with the pedals, synchronizing the pedal strokes, without any "the bike stops but the feet are still pedaling in the air" or "the feet and pedals are disconnected" situations; 3. The background (such as the coastline, palm trees, or street) should produce a parallax animation moving backward; 4. The entire code must be a single file, a pure SVG/JS implementation, without any external images or error messages.

After thinking for a while, it will trigger a thinking deadlock.

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