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

Libraries

How to use indahl/YO with Transformers:

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

pipe = pipeline("text-generation", model="indahl/YO")
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("indahl/YO")
model = AutoModelForCausalLM.from_pretrained("indahl/YO", 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]:]))

MLX

How to use indahl/YO with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("indahl/YO")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use indahl/YO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/indahl/YO

SGLang

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

How to use indahl/YO with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "indahl/YO"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "indahl/YO"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use indahl/YO with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "indahl/YO"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "indahl/YO"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "indahl/YO",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

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

Hermes Agent

How to use indahl/YO with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "indahl/YO"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default indahl/YO

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use indahl/YO with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "indahl/YO"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "indahl/YO" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

indahl commited on 2 days ago

Commit

4414e85

verified ·

1 Parent(s): 9591797

YO v8, tried: no seed passes, YO v7 stays at work

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -77,6 +77,10 @@ YO v6 continued training YO v4 on young groups whose date falls on the previous
 YO v7 continued training YO v4 with YO v4's whole-window and band items restored beside the YO v6 kinds (PLAN_YO_V7). Of its first two seeds, 51 passed the plan rule and 52 did not (it found fewer stale qubits than YO v4), so a retest plan (PLAN_YO_V7S) retrained the same recipe with seeds 53, 54 and 55 and required all three to pass. All three did: on the older same-date items they found 1.000, 0.997 and 0.993 of 2,320 stale qubits, where YO v4 found 0.969, and none was shown to flag more young qubits or to find fewer stale ones. On the share of flags that are right they read 0.992 against YO v4's 0.999, and on the four-outcome verdict 0.960, 0.965 and 0.975 against 0.975, neither shown worse within the plan's bands. By the rule YO v7 seed 51 replaces YO v4 for the live reads from 1 November 2026. Every reading: https://indahl.ai/iris/lab and https://github.com/Heuremen-LLC/indahl.ai/tree/main/code/yo
 ## Live
 YO reads each new IBM calibration record as it is published, beside the code's answer, at https://indahl.ai/qia

 YO v7 continued training YO v4 with YO v4's whole-window and band items restored beside the YO v6 kinds (PLAN_YO_V7). Of its first two seeds, 51 passed the plan rule and 52 did not (it found fewer stale qubits than YO v4), so a retest plan (PLAN_YO_V7S) retrained the same recipe with seeds 53, 54 and 55 and required all three to pass. All three did: on the older same-date items they found 1.000, 0.997 and 0.993 of 2,320 stale qubits, where YO v4 found 0.969, and none was shown to flag more young qubits or to find fewer stale ones. On the share of flags that are right they read 0.992 against YO v4's 0.999, and on the four-outcome verdict 0.960, 0.965 and 0.975 against 0.975, neither shown worse within the plan's bands. By the rule YO v7 seed 51 replaces YO v4 for the live reads from 1 November 2026. Every reading: https://indahl.ai/iris/lab and https://github.com/Heuremen-LLC/indahl.ai/tree/main/code/yo
+## YO v8, tried
+YO v8 continued training YO v7 seed 51 with 2,400 verdict items near the edges of the four-outcome rule (PLAN_YO_V8), with seeds 56, 57 and 58. On 800 new border items from held-out records it scored 0.769, 0.754 and 0.765 exact against YO v7's 0.729 (seed 57's band reaches zero). On borders inside the margin all three seeds scored lower than YO v7 (0.835, 0.880 and 0.890 against 0.940). The plan needed all three seeds to pass. Seed 56 found 0.852 of 2,320 older same-date stale qubits against YO v7's 1.000, and seeds 57 and 58 flagged more young qubits beside stale ones (0.027 and 0.048 against 0.001). No seed passed, so YO v7 stays at work. The largest miss is the same for every version: an interval that ends just outside the margin is answered CONSISTENT where the rule says CANNOT_TELL. Every reading: https://indahl.ai/iris/lab and https://github.com/Heuremen-LLC/indahl.ai/tree/main/code/yo
 ## Live
 YO reads each new IBM calibration record as it is published, beside the code's answer, at https://indahl.ai/qia