Instructions to use laion/swesmith-coldstart-complete-lt32k-2ep-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/swesmith-coldstart-complete-lt32k-2ep-8B with Transformers:

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

pipe = pipeline("text-generation", model="laion/swesmith-coldstart-complete-lt32k-2ep-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("laion/swesmith-coldstart-complete-lt32k-2ep-8B")
model = AutoModelForMultimodalLM.from_pretrained("laion/swesmith-coldstart-complete-lt32k-2ep-8B")
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 laion/swesmith-coldstart-complete-lt32k-2ep-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/swesmith-coldstart-complete-lt32k-2ep-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/swesmith-coldstart-complete-lt32k-2ep-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/swesmith-coldstart-complete-lt32k-2ep-8B

SGLang

How to use laion/swesmith-coldstart-complete-lt32k-2ep-8B 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 "laion/swesmith-coldstart-complete-lt32k-2ep-8B" \
    --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": "laion/swesmith-coldstart-complete-lt32k-2ep-8B",
		"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 "laion/swesmith-coldstart-complete-lt32k-2ep-8B" \
        --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": "laion/swesmith-coldstart-complete-lt32k-2ep-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/swesmith-coldstart-complete-lt32k-2ep-8B with Docker Model Runner:
```
docker model run hf.co/laion/swesmith-coldstart-complete-lt32k-2ep-8B
```

sft__GLM-4-7-swesmith-oracle_verified-complete-lt32k2-0Qwen3-8B

This model is a fine-tuned version of Qwen/Qwen3-8B on the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--GLM-4.7-swesmith-oracle_verified-complete-lt32k/snapshots/733ffbcf76c8437ea58ebd5fbe55520db0a0bc64_thinking_preprocessed 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: 4e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 16
total_eval_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 2.0

Training results

Framework versions

Transformers 5.8.1
Pytorch 2.11.0+cu130
Datasets 4.7.0
Tokenizers 0.22.2

Downloads last month: 33

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for laion/swesmith-coldstart-complete-lt32k-2ep-8B

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1722)

this model

Finetunes

1 model

sft__GLM-4-7-swesmith-oracle_verified-complete-lt32k__2-0__Qwen3-8B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for laion/swesmith-coldstart-complete-lt32k-2ep-8B

sft__GLM-4-7-swesmith-oracle_verified-complete-lt32k2-0Qwen3-8B