Instructions to use cagataydev/loopl-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cagataydev/loopl-4b with Transformers:

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

pipe = pipeline("image-text-to-text", model="cagataydev/loopl-4b")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("cagataydev/loopl-4b")
model = AutoModelForMultimodalLM.from_pretrained("cagataydev/loopl-4b", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cagataydev/loopl-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cagataydev/loopl-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cagataydev/loopl-4b",
		"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/cagataydev/loopl-4b

SGLang

How to use cagataydev/loopl-4b 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 "cagataydev/loopl-4b" \
    --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": "cagataydev/loopl-4b",
		"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 "cagataydev/loopl-4b" \
        --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": "cagataydev/loopl-4b",
		"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 cagataydev/loopl-4b with Docker Model Runner:
```
docker model run hf.co/cagataydev/loopl-4b
```

loopl-4b / train_summary.json

cagataydev

loopl v1.2-c — promoted from cagataydev/loopl-4b-v1.2-c @ 966b2b1a (DATASET v2.2.1 rev 47d27b44: v2.2 with the full agentic critic: 23% of tool rows rejected for inventing owner facts or contradicting their own tool results); the previous version is the preceding commit

051d641 verified 28 days ago

Raw History Blame Contribute Delete

1.68 kB

{
 "base": "Qwen/Qwen3.5-4B",
 "dataset": "cagataydev/loopl-train",
 "dataset_revision": "47d27b4415f8f9e35d352fdfecc02f551103366a",
 "split": "train",
 "families": null,
 "format": "both",
 "rows": 13704,
 "tokens": 37226229,
 "max_length": 4096,
 "lora": {
  "r": 64,
  "alpha": 128,
  "dropout": 0.05,
  "target_regex": ".*\\.language_model\\..*\\.(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|in_proj_qkvz|in_proj_ba|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|out_proj)"
 },
 "epochs": 2.0,
 "max_steps": -1,
 "lr": 0.0001,
 "batch": 2,
 "grad_accum": 8,
 "oversample": "c=2",
 "best_checkpoint": "/tmp/loopl-sft/ckpt/checkpoint-857",
 "best_eval_loss": 1.4425023794174194,
 "eval_history": [
  {
   "eval_loss": 1.4425023794174194,
   "epoch": 1.0
  },
  {
   "eval_loss": 1.508070945739746,
   "epoch": 2.0
  },
  {
   "eval_loss": 1.4425023794174194,
   "epoch": 2.0
  }
 ],
 "metrics": {
  "train_runtime": 32074.0139,
  "train_samples_per_second": 0.855,
  "train_steps_per_second": 0.053,
  "total_flos": 2.231953474897576e+18,
  "train_loss": 0.8309779066327294,
  "epoch": 2.0,
  "eval_loss": 1.4425023794174194,
  "eval_runtime": 444.5352,
  "eval_samples_per_second": 3.109,
  "eval_steps_per_second": 0.389,
  "eval_entropy": 1.3332137045143657,
  "eval_num_tokens": 74452458.0,
  "eval_mean_token_accuracy": 0.6711968114610353
 },
 "data_stats": {
  "read": 8676,
  "rendered": 13704,
  "no_assistant": 1802,
  "render_error": 0,
  "truncated_hint": 1000,
  "tools_injected": 2778
 },
 "wall_s": 32755,
 "versions": {
  "transformers": "5.19.0",
  "trl": "1.14.2",
  "peft": "0.21.2",
  "torch": "2.14.1+cu130"
 },
 "job_id": "6ac5e6f6404719ba3766544a"
}

	{
	"base": "Qwen/Qwen3.5-4B",
	"dataset": "cagataydev/loopl-train",
	"dataset_revision": "47d27b4415f8f9e35d352fdfecc02f551103366a",
	"split": "train",
	"families": null,
	"format": "both",
	"rows": 13704,
	"tokens": 37226229,
	"max_length": 4096,
	"lora": {
	"r": 64,
	"alpha": 128,
	"dropout": 0.05,
	"target_regex": ".\\.language_model\\..\\.(q_proj\|k_proj\|v_proj\|o_proj\|gate_proj\|up_proj\|down_proj\|in_proj_qkvz\|in_proj_ba\|in_proj_qkv\|in_proj_z\|in_proj_b\|in_proj_a\|out_proj)"
	},
	"epochs": 2.0,
	"max_steps": -1,
	"lr": 0.0001,
	"batch": 2,
	"grad_accum": 8,
	"oversample": "c=2",
	"best_checkpoint": "/tmp/loopl-sft/ckpt/checkpoint-857",
	"best_eval_loss": 1.4425023794174194,
	"eval_history": [
	{
	"eval_loss": 1.4425023794174194,
	"epoch": 1.0
	},
	{
	"eval_loss": 1.508070945739746,
	"epoch": 2.0
	},
	{
	"eval_loss": 1.4425023794174194,
	"epoch": 2.0
	}
	],
	"metrics": {
	"train_runtime": 32074.0139,
	"train_samples_per_second": 0.855,
	"train_steps_per_second": 0.053,
	"total_flos": 2.231953474897576e+18,
	"train_loss": 0.8309779066327294,
	"epoch": 2.0,
	"eval_loss": 1.4425023794174194,
	"eval_runtime": 444.5352,
	"eval_samples_per_second": 3.109,
	"eval_steps_per_second": 0.389,
	"eval_entropy": 1.3332137045143657,
	"eval_num_tokens": 74452458.0,
	"eval_mean_token_accuracy": 0.6711968114610353
	},
	"data_stats": {
	"read": 8676,
	"rendered": 13704,
	"no_assistant": 1802,
	"render_error": 0,
	"truncated_hint": 1000,
	"tools_injected": 2778
	},
	"wall_s": 32755,
	"versions": {
	"transformers": "5.19.0",
	"trl": "1.14.2",
	"peft": "0.21.2",
	"torch": "2.14.1+cu130"
	},
	"job_id": "6ac5e6f6404719ba3766544a"
	}