Instructions to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b")
model = PeftModel.from_pretrained(base_model, "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2")

Transformers

How to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 with Transformers:

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

pipe = pipeline("text-generation", model="EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2")
model = AutoModelForCausalLM.from_pretrained("EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2")
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

vLLM

How to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2

SGLang

How to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 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 "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2" \
    --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": "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2",
		"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 "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2" \
        --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": "EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2 with Docker Model Runner:
```
docker model run hf.co/EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2
```

See axolotl config

axolotl version: 0.12.2

base_model: openai/gpt-oss-20b
use_kernels: true
model_quantization_config: Mxfp4Config
model_quantization_config_kwargs:
  dequantize: true

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

experimental_skip_move_to_device: true  # prevent OOM by not putting model to GPU before sharding

datasets:
  - path: /workspace/swe-tests/scripts/1_low_stakes_control/sft/data/olympiads/qwen1point7b/malign_prompt_benign_answers/train_2.jsonl
    ds_type: json
    type: chat_template
    field_thinking: thinking
    template_thinking_key: thinking
    split: train

test_datasets:
  - path: /workspace/swe-tests/scripts/1_low_stakes_control/sft/data/olympiads/qwen1point7b/malign_prompt_benign_answers/val_2.jsonl
    ds_type: json
    type: chat_template
    field_thinking: thinking
    template_thinking_key: thinking
    split: train

output_dir: ./outputs/out/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2

sequence_len: 4096
#sample_packing: true

adapter: lora
lora_r: 32
lora_alpha: 32
lora_dropout: 0.0  # dropout not supported when using LoRA over expert parameters
lora_target_linear: true

# TODO: not supported for now, see peft#2710xw
#lora_target_parameters:  # target the experts in the last two layers
#  - "22._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
#  - "22._checkpoint_wrapped_module.mlp.experts.down_proj"
#  - "23._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
#  - "23._checkpoint_wrapped_module.mlp.experts.down_proj"

wandb_project: low-stakes-control-sft
wandb_entity: mats-low-stakes
wandb_name: gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2
wandb_log_model: checkpoint
hub_model_id: EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 150

optimizer: adamw_torch_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-5

bf16: true
tf32: true

flash_attention: true
attn_implementation: kernels-community/vllm-flash-attn3

gradient_checkpointing: true
activation_offloading: true

logging_steps: 1
save_strategy: best
metric_for_best_model: eval_loss
save_only_model: true
warmup_ratio: 0.01
eval_steps: 10

special_tokens:
eot_tokens:
  - "<|end|>"

gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2

This model is a fine-tuned version of openai/gpt-oss-20b on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use adamw_torch_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 2
training_steps: 150

Framework versions

PEFT 0.17.0
Transformers 4.55.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 20

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for EmilRyd/gpt-oss-20b-olympiads-qwen1point7b-malign-prompt-benign-answer-2

Base model

openai/gpt-oss-20b

Adapter

(227)

this model