Instructions to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with Transformers:

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

pipe = pipeline("image-text-to-text", model="CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k")
model = AutoModelForMultimodalLM.from_pretrained("CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k

SGLang

How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k 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 "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k" \
    --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": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k" \
        --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": "CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k with Docker Model Runner:
```
docker model run hf.co/CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k
```

See axolotl config

axolotl version: 0.17.0.dev0

base_model: Qwen/Qwen3.5-9B
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false
datasets:
- path: CooperBench/cooperdata-bridge-midtrain-blend
  type: completion
  field: text
  split: train
sample_packing: true
dataloader_num_workers: 4
dataloader_prefetch_factor: 4
dataloader_pin_memory: true
unfrozen_parameters:
- model.language_model.*
- lm_head.*
val_set_size: 0.0
output_dir: /vol/midtrain_axolotl_bridge-32k
dataset_prepared_path: /vol/_axolotl_prepared_bridge
sequence_len: 32768
max_steps: -1
micro_batch_size: 1
gradient_accumulation_steps: 1
num_epochs: 1
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 1.5e-05
warmup_ratio: 0.1
weight_decay: 0.1
bf16: auto
tf32: true
gradient_checkpointing: false
attn_implementation: flash_attention_2
logging_steps: 1
saves_per_epoch: 1
special_tokens: null
wandb_project: qwen35-9b-cooperdata
wandb_name: bridge-midtrain-axolotl
fsdp_config:
  fsdp_version: 2
  offload_params: false
  cpu_ram_efficient_loading: true
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Qwen3_5DecoderLayer
  state_dict_type: FULL_STATE_DICT
  sharding_strategy: FULL_SHARD
  reshard_after_forward: true
  activation_checkpointing: true

vol/midtrain_axolotl_bridge-32k

This model is a fine-tuned version of Qwen/Qwen3.5-9B on the CooperBench/cooperdata-bridge-midtrain-blend 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: 1.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 1.0

Training results

Framework versions

Transformers 5.10.2
Pytorch 2.12.0+cu130
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(544)

this model

CooperBench
/

Qwen3.5-9B-cooperdata-bridge-midtrain-32k

vol/midtrain_axolotl_bridge-32k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k

Dataset used to train CooperBench/Qwen3.5-9B-cooperdata-bridge-midtrain-32k