Instructions to use myyycroft/Qwen3.5-2B-AmbigQA-full-member-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use myyycroft/Qwen3.5-2B-AmbigQA-full-member-3 with Transformers:

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

pipe = pipeline("text-generation", model="myyycroft/Qwen3.5-2B-AmbigQA-full-member-3")
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("myyycroft/Qwen3.5-2B-AmbigQA-full-member-3")
model = AutoModelForCausalLM.from_pretrained("myyycroft/Qwen3.5-2B-AmbigQA-full-member-3", 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 myyycroft/Qwen3.5-2B-AmbigQA-full-member-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/myyycroft/Qwen3.5-2B-AmbigQA-full-member-3

SGLang

How to use myyycroft/Qwen3.5-2B-AmbigQA-full-member-3 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 "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3" \
    --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": "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3",
		"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 "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3" \
        --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": "myyycroft/Qwen3.5-2B-AmbigQA-full-member-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use myyycroft/Qwen3.5-2B-AmbigQA-full-member-3 with Docker Model Runner:
```
docker model run hf.co/myyycroft/Qwen3.5-2B-AmbigQA-full-member-3
```

myyycroft/Qwen3.5-2B-AmbigQA-full-member-3

Ensemble member 3 (seed 3069) from run qwen35_2b_full_small_lr.

Fine-tuned from Qwen/Qwen3.5-2B on AmbigQA.

Evaluation note

Metrics below are computed on small fixed subsets, not full benchmarks. Exact subset sizes: ambigqa=128, ifeval=64, mmlu=228. Reported values are from the final training step (step=1620, epoch=3).

Dataset

Hub dataset: sewon/ambig_qa (config_name=light)
Revision: 6e667596df70f17ba3c8e7be4b7361f6be8b60f8
Splits: train=train, validation=validation
Dev holdout: dev_fraction=0.1, split_seed=1729
Bootstrap resampling: False

System prompt

No system prompt (dataset.system_prompt: null).

Hyperparameters

Exact resolved settings used for this run (also attached as resolved_config.yaml):

model:
  name: Qwen/Qwen3.5-2B
  revision: main
  dtype: bfloat16
  enable_thinking: false
dataset:
  name: sewon/ambig_qa
  config_name: light
  revision: 6e667596df70f17ba3c8e7be4b7361f6be8b60f8
  train_split: train
  validation_split: validation
  dev_fraction: 0.1
  split_seed: 1729
  bootstrap: false
  max_train_examples: null
  max_dev_examples: null
  system_prompt_set: false
adaptation:
  method: full
training:
  num_train_epochs: 3.0
  max_steps: -1
  learning_rate: 2.0e-05
  weight_decay: 0.1
  warmup_ratio: 0.03
  per_device_train_batch_size: 4
  per_device_eval_batch_size: 16
  gradient_accumulation_steps: 8
  max_seq_length: 512
  logging_steps: 10
  save_every_steps: null
  save_total_limit: null
  gradient_checkpointing: true
  bf16: true
  tf32: true
  max_grad_norm: 1.0
  dataloader_num_workers: 2
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1.0e-08
ensemble:
  size: 5
  base_seed: 42
  this_member_index: 3
  this_member_seed: 3069
evaluation_subsets:
  ambigqa:
    subset_size: 128
    seed: 1001
  ifeval:
    subset_size: 64
    seed: 1002
  mmlu:
    subset_size: 228
    seed: 1004

Metrics breakdown

Final-step ensemble mean ± std (n=5)

AmbigQA accuracy: 0.0766 ± 0.0086
AmbigQA AlignScore: 0.1310 ± 0.0114
IFEval prompt_level_strict_accuracy: 0.4375 ± 0.0383
MMLU accuracy: 0.6061 ± 0.0114
train_loss: 1.1289 ± 0.0033
steps: 1620
epochs: 3

Per-member (final step)

member	seed	steps	epochs	train_loss	AmbigQA acc	AmbigQA AlignScore	IFEval strict	MMLU acc
0	42	1620	3	1.1297	0.0625	0.1165	0.4688	0.6184
1	1051	1620	3	1.1313	0.0781	0.1373	0.4688	0.5965
2	2060	1620	3	1.1237	0.0781	0.1422	0.4375	0.6140
3 (this repo)	3069	1620	3	1.1280	0.0859	0.1378	0.3750	0.5921
4	4078	1620	3	1.1320	0.0781	0.1210	0.4375	0.6096