Instructions to use morningstarxcdcode/adaption-no-robots-instructions-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morningstarxcdcode/adaption-no-robots-instructions-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/gpt-oss-120b-bf16")
model = PeftModel.from_pretrained(base_model, "morningstarxcdcode/adaption-no-robots-instructions-model")

Transformers

How to use morningstarxcdcode/adaption-no-robots-instructions-model with Transformers:

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

pipe = pipeline("text-generation", model="morningstarxcdcode/adaption-no-robots-instructions-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("morningstarxcdcode/adaption-no-robots-instructions-model")
model = AutoModelForCausalLM.from_pretrained("morningstarxcdcode/adaption-no-robots-instructions-model", 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 morningstarxcdcode/adaption-no-robots-instructions-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "morningstarxcdcode/adaption-no-robots-instructions-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morningstarxcdcode/adaption-no-robots-instructions-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/morningstarxcdcode/adaption-no-robots-instructions-model

SGLang

How to use morningstarxcdcode/adaption-no-robots-instructions-model 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 "morningstarxcdcode/adaption-no-robots-instructions-model" \
    --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": "morningstarxcdcode/adaption-no-robots-instructions-model",
		"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 "morningstarxcdcode/adaption-no-robots-instructions-model" \
        --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": "morningstarxcdcode/adaption-no-robots-instructions-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use morningstarxcdcode/adaption-no-robots-instructions-model with Docker Model Runner:
```
docker model run hf.co/morningstarxcdcode/adaption-no-robots-instructions-model
```

adaption-no-robots-instructions-model / README.md

morningstarxcdcode

Upload folder using huggingface_hub

afb4358 verified 22 days ago

preview code

Raw

History Blame Contribute Delete

1.94 kB

	---
	language:
	- en
	license: apache-2.0
	tags:
	- lora
	- peft
	- language
	- instruction-following
	- no-robots
	- gpt-oss
	- sft
	- transformers
	pipeline_tag: text-generation
	base_model: togethercomputer/gpt-oss-120b-bf16
	---

	# Adaption No Robots Instructions SFT 120B

	LoRA adapter fine-tuned on the No Robots instruction-following dataset using Adaption's AutoScientist platform.

	## Model Details

	- Base model: `togethercomputer/gpt-oss-120b-bf16` (120B parameter MoE, 128 experts, 4 per token)
	- Adapter: LoRA rank 4, alpha 8, targeting `q_proj` and `v_proj`
	- Training data: 10,000 human-written instruction-response pairs (No Robots dataset)
	- Training: 1 epoch, 22 steps, loss 2.22 → 1.40
	- Eval loss: 1.93 → 1.41

	## Training Results

	\| Metric \| Before \| After \|
	\|--------\|--------\|-------\|
	\| Quality \| 7.0 \| 7.5 (+7.1%) \|
	\| Grade \| C \| B \|
	\| General Win Rate \| 41% \| 59% \|
	\| Dataset Win Rate \| 54% \| 46% \|

	## How to Use

	```python
	from peft import PeftModel
	from transformers import AutoModelForCausalLM, AutoTokenizer

	base_model = AutoModelForCausalLM.from_pretrained(
	"togethercomputer/gpt-oss-120b-bf16",
	torch_dtype="bfloat16",
	device_map="auto"
	)
	model = PeftModel.from_pretrained(base_model, "morningstarxcdcode/adaption-no-robots-instructions-model")
	tokenizer = AutoTokenizer.from_pretrained("morningstarxcdcode/adaption-no-robots-instructions-model")

	inputs = tokenizer("Write a short story about a robot learning to cook.", return_tensors="pt").to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=512)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Training Configuration

	- Optimizer: AdamW
	- Learning rate: 1e-4 with cosine decay
	- Batch size: 1
	- Max grad norm: 1.0
	- Warmup steps: 4

	## Team

	Sourav Rajak, Priyanshu Tomar, Roshan G, Vivek Rajput

	Part of the AutoScientist Challenge — Healthcare, Finance, Language, Legal, and Marketing tracks.