Instructions to use renaudb1999/le-harnais-ft-ornith-scaffold-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use renaudb1999/le-harnais-ft-ornith-scaffold-3b with Transformers:

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

pipe = pipeline("text-generation", model="renaudb1999/le-harnais-ft-ornith-scaffold-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("renaudb1999/le-harnais-ft-ornith-scaffold-3b")
model = AutoModelForCausalLM.from_pretrained("renaudb1999/le-harnais-ft-ornith-scaffold-3b", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use renaudb1999/le-harnais-ft-ornith-scaffold-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "renaudb1999/le-harnais-ft-ornith-scaffold-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "renaudb1999/le-harnais-ft-ornith-scaffold-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/renaudb1999/le-harnais-ft-ornith-scaffold-3b

SGLang

How to use renaudb1999/le-harnais-ft-ornith-scaffold-3b 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 "renaudb1999/le-harnais-ft-ornith-scaffold-3b" \
    --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": "renaudb1999/le-harnais-ft-ornith-scaffold-3b",
		"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 "renaudb1999/le-harnais-ft-ornith-scaffold-3b" \
        --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": "renaudb1999/le-harnais-ft-ornith-scaffold-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use renaudb1999/le-harnais-ft-ornith-scaffold-3b with Docker Model Runner:
```
docker model run hf.co/renaudb1999/le-harnais-ft-ornith-scaffold-3b
```

le-harnais / ft-ornith-scaffold-3b

A scaffold-generation student: given a coding/agent task it emits a short numbered plan of subgoals, each tagged with how to verify it. Distilled (plain full-FT SFT) from the ornith:35b teacher's self-scaffolds, so a small local model can produce the structured plans that le-harnais's lh harness self-scaffold step executes and verifies.

Base model: meta-llama/Llama-3.2-3B-Instruct — Built with Llama; Llama 3.2 Community License applies.
Class: hero
Teacher: ornith:9b/ornith:35b family (MIT) — scaffolds generated by ornith:35b.
Training data: 153 (task → verify-tagged numbered plan) pairs from the teacher (38 held-out).
Headline (held-out, n=38, vs the base): token-F1 vs teacher 0.295 (base 0.170, +0.125); scaffold-structure score 0.731 (base 0.577, +0.153).

Why it exists

le-harnais's thesis is don't trust raw model text — generate, verify, repair. Ornith's "self-improving" RL learns to propose its own search scaffold; we can't reproduce that RL on one GPU, but we can distill the scaffolding behavior into a cheap local model. This student is the result: it drives the inference-time --self-scaffold path (which on a weak policy halved escalation in an A/B), with no RL and no remote model.

Reproduce

# 1. corpus from the teacher, 2. full-FT distill, 3. held-out bench
python tools/gen_ornith_scaffold_corpus.py --n 160 --eval 40 --out datasets/ornith_scaffold
BASE=meta-llama/Llama-3.2-3B-Instruct OUT=refs/llm-jepa/ft-ornith-scaffold-3b \
  tools/distill_ornith_scaffold.sh
python tools/bench_scaffold.py --student refs/llm-jepa/ft-ornith-scaffold-3b \
  --base meta-llama/Llama-3.2-3B-Instruct --eval datasets/ornith_scaffold_eval.jsonl

Full context: docs/ornith-self-improving.md (D1–D4) and docs/local-coding-agents-bench.md in the [le-harnais] repo. Serve with transformers or le-harnais lh-serve/candle.

Distilling a teacher's scaffolding skill into a small student: structure and plan quality transfer; this is behavior distillation, not the teacher's RL.

Downloads last month: 34

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for renaudb1999/le-harnais-ft-ornith-scaffold-3b

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1856)

this model