Instructions to use veriloop-lab/veriloop-coder-e1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use veriloop-lab/veriloop-coder-e1 with Transformers:

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

pipe = pipeline("text-generation", model="veriloop-lab/veriloop-coder-e1")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("veriloop-lab/veriloop-coder-e1")
model = AutoModelForImageTextToText.from_pretrained("veriloop-lab/veriloop-coder-e1")
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]:]))

PEFT
How to use veriloop-lab/veriloop-coder-e1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use veriloop-lab/veriloop-coder-e1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "veriloop-lab/veriloop-coder-e1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "veriloop-lab/veriloop-coder-e1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/veriloop-lab/veriloop-coder-e1

SGLang

How to use veriloop-lab/veriloop-coder-e1 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 "veriloop-lab/veriloop-coder-e1" \
    --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": "veriloop-lab/veriloop-coder-e1",
		"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 "veriloop-lab/veriloop-coder-e1" \
        --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": "veriloop-lab/veriloop-coder-e1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use veriloop-lab/veriloop-coder-e1 with Docker Model Runner:
```
docker model run hf.co/veriloop-lab/veriloop-coder-e1
```

veriloop-coder-e1 / toolspec_adapter /toolspec_training_manifest.json

ConorWang

Upload toolspec_qwen36_rootfix_run1 contents into toolspec_adapter

98746ed verified about 1 month ago

raw

history blame

4.3 kB

	{
	"adapter_exported": true,
	"auto_lora_from_ia3": false,
	"best_epoch": 4,
	"best_quality_score": 0.46349615617231893,
	"dataset_summary": {
	"eval_size": 25,
	"modes": [
	"argument_shaping",
	"harness_envelope",
	"precondition_gating",
	"receipt_and_validation",
	"reverse_engineering",
	"runtime_session",
	"self_check_loop",
	"tool_trigger",
	"worktree_permission"
	],
	"tools": [
	"apply_patch_bundle",
	"browser_search",
	"repo_reverse_engineer",
	"run_ci_validation",
	"self_check_repair_loop"
	],
	"train_size": 70
	},
	"epochs_completed": 5,
	"eval_metrics": {
	"adapter_exported": true,
	"auto_lora_from_ia3": false,
	"avg_binary_accuracy": 0.81,
	"best_epoch": 4,
	"best_quality_score": 0.46349615617231893,
	"confirmation_required_accuracy": 0.8,
	"count": 25,
	"eval_batches": 25,
	"eval_loss": 6.897225952148437,
	"mode_accuracy": 0.56,
	"peft_method": "lora_narrow",
	"permission_bit_accuracy": 0.8545454545454545,
	"precondition_ok_accuracy": 0.76,
	"quality_score": 0.46349615617231893,
	"rollback_supported_accuracy": 0.8,
	"schema_ok_accuracy": 0.76,
	"session_required_accuracy": 1.0,
	"tool_accuracy": 0.44,
	"trigger_accuracy": 0.76,
	"used_peft": true,
	"validator_required_accuracy": 0.8,
	"worktree_required_accuracy": 0.8
	},
	"load_meta": {
	"chosen_class": "AutoModelForCausalLM",
	"hidden_size": 2048,
	"quantization_mode": "4bit"
	},
	"mode_vocab": [
	"tool_trigger",
	"argument_shaping",
	"precondition_gating",
	"receipt_and_validation",
	"harness_envelope",
	"runtime_session",
	"worktree_permission",
	"self_check_loop",
	"reverse_engineering"
	],
	"peft_method": "lora_narrow",
	"requested_method": "lora_narrow",
	"requested_target_modules": [
	"request_normalizer",
	"request_normalizer.adapter",
	"runtime_harness_adapter",
	"runtime_harness_adapter.bridge",
	"tool_protocol_adapter",
	"tool_protocol_adapter.bridge",
	"toolspec_bridge",
	"toolspec_bridge.adapter",
	"toolspec_head",
	"toolspec_head.param_schema_adapter",
	"toolspec_head.postcondition_adapter",
	"toolspec_head.precondition_adapter",
	"toolspec_head.receipt_formatter",
	"toolspec_head.trigger_gate",
	"toolspec_head.validator_gate",
	"validator_feedback_bridge",
	"validator_feedback_bridge.adapter"
	],
	"resolved_target_modules": [
	"surface_host.request_normalizer.adapter",
	"surface_host.runtime_harness_adapter.bridge",
	"surface_host.tool_protocol_adapter.bridge",
	"surface_host.toolspec_bridge.adapter",
	"surface_host.toolspec_head.param_schema_adapter",
	"surface_host.toolspec_head.postcondition_adapter",
	"surface_host.toolspec_head.precondition_adapter",
	"surface_host.toolspec_head.receipt_formatter",
	"surface_host.toolspec_head.trigger_gate",
	"surface_host.toolspec_head.validator_gate",
	"surface_host.validator_feedback_bridge.adapter"
	],
	"selected_target_modules": [
	"request_normalizer",
	"request_normalizer.adapter",
	"runtime_harness_adapter",
	"runtime_harness_adapter.bridge",
	"tool_protocol_adapter",
	"tool_protocol_adapter.bridge",
	"toolspec_bridge",
	"toolspec_bridge.adapter",
	"toolspec_head",
	"toolspec_head.param_schema_adapter",
	"toolspec_head.postcondition_adapter",
	"toolspec_head.precondition_adapter",
	"toolspec_head.receipt_formatter",
	"toolspec_head.trigger_gate",
	"toolspec_head.validator_gate",
	"validator_feedback_bridge",
	"validator_feedback_bridge.adapter"
	],
	"status": "trained",
	"tool_vocab": [
	"apply_patch_bundle",
	"browser_search",
	"repo_reverse_engineer",
	"run_ci_validation",
	"self_check_repair_loop"
	],
	"train_metrics": {
	"adapter_exported": true,
	"auto_lora_from_ia3": false,
	"best_epoch": 4,
	"best_quality_score": 0.46349615617231893,
	"epochs_completed": 5,
	"loss": 0.42175399448190415,
	"micro_batches": 70,
	"micro_batches_total": 350,
	"optimizer_steps": 5,
	"optimizer_steps_total": 25,
	"peft_method": "lora_narrow",
	"used_peft": true
	},
	"unresolved_target_modules": [],
	"used_peft": true
	}