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
```

ConorWang commited on Apr 17

Commit

45e6293

verified ·

1 Parent(s): cca442b

Upload model/host_manifest.json with huggingface_hub

Browse files

Files changed (1) hide show

model/host_manifest.json +238 -0

model/host_manifest.json ADDED Viewed

	@@ -0,0 +1,238 @@

+{
+  "hidden_size": 2048,
+  "host_config": {
+    "attn_implementation": null,
+    "backbone_name_or_path": "/public/wang_libo/veriloop_coder_e1/model",
+    "device_map": null,
+    "dtype": null,
+    "evidence_rank_hint": 8,
+    "expose_backbone_inventory": false,
+    "freeze_backbone": true,
+    "hidden_size_override": 2048,
+    "host_dropout": 0.0,
+    "identity_rank_hint": 8,
+    "load_backbone_weights": false,
+    "local_files_only": true,
+    "low_cpu_mem_usage": true,
+    "memory_rank_hint": 4,
+    "rollback_rank_hint": 8,
+    "runtime_rank_hint": 8,
+    "toolspec_rank_hint": 8,
+    "trust_remote_code": true,
+    "uncertainty_rank_hint": 8,
+    "use_safetensors": null,
+    "validator_rank_hint": 8
+  },
+  "load_result": {
+    "has_base_config": true,
+    "has_base_model": true,
+    "hidden_size": 2048,
+    "notes": [
+      "class=AutoModelForCausalLM",
+      "quant=4bit"
+    ],
+    "source": "trainer_qwen36_loader"
+  },
+  "peft_named_modules": [
+    "claim_extractor",
+    "claim_extractor.adapter",
+    "dropout",
+    "episodic_memory",
+    "episodic_memory.adapter",
+    "evidence_binding",
+    "evidence_binding.adapter",
+    "failure_signal_bridge",
+    "failure_signal_bridge.rollback_bridge",
+    "identity_adapter",
+    "identity_adapter.bridge",
+    "identity_guard",
+    "identity_guard.adapter",
+    "input_norm",
+    "memory_boundary_guard",
+    "memory_boundary_guard.adapter",
+    "memory_boundary_guard.rollback_filter",
+    "patch_binding",
+    "patch_binding.adapter",
+    "permission_context_manager",
+    "permission_context_manager.adapter",
+    "progress_state_tracker",
+    "progress_state_tracker.adapter",
+    "progress_state_tracker.rollback_memory",
+    "proof_carrying_hints",
+    "proof_carrying_hints.bridge",
+    "provenance_binding",
+    "provenance_binding.adapter",
+    "public_identity_head",
+    "public_identity_head.proj",
+    "query_runtime_engine",
+    "query_runtime_engine.adapter",
+    "request_normalizer",
+    "request_normalizer.adapter",
+    "request_normalizer.adapter.base_layer",
+    "request_normalizer.adapter.lora_A",
+    "request_normalizer.adapter.lora_A.default",
+    "request_normalizer.adapter.lora_B",
+    "request_normalizer.adapter.lora_B.default",
+    "request_normalizer.adapter.lora_dropout",
+    "request_normalizer.adapter.lora_dropout.default",
+    "request_normalizer.adapter.lora_embedding_A",
+    "request_normalizer.adapter.lora_embedding_B",
+    "request_normalizer.adapter.lora_magnitude_vector",
+    "rollback_adapter",
+    "rollback_adapter.head",
+    "rollback_engine",
+    "rollback_engine.adapter",
+    "runtime_binding",
+    "runtime_binding.adapter",
+    "runtime_harness_adapter",
+    "runtime_harness_adapter.bridge",
+    "runtime_harness_adapter.bridge.base_layer",
+    "runtime_harness_adapter.bridge.lora_A",
+    "runtime_harness_adapter.bridge.lora_A.default",
+    "runtime_harness_adapter.bridge.lora_B",
+    "runtime_harness_adapter.bridge.lora_B.default",
+    "runtime_harness_adapter.bridge.lora_dropout",
+    "runtime_harness_adapter.bridge.lora_dropout.default",
+    "runtime_harness_adapter.bridge.lora_embedding_A",
+    "runtime_harness_adapter.bridge.lora_embedding_B",
+    "runtime_harness_adapter.bridge.lora_magnitude_vector",
+    "runtime_harness_uncertainty_bridge",
+    "runtime_harness_uncertainty_bridge.adapter",
+    "sandbox_rollback_bridge",
+    "sandbox_rollback_bridge.adapter",
+    "session_compactor",
+    "session_compactor.adapter",
+    "session_state_manager",
+    "session_state_manager.adapter",
+    "session_state_manager.rollback_state",
+    "tool_protocol_adapter",
+    "tool_protocol_adapter.bridge",
+    "tool_protocol_adapter.bridge.base_layer",
+    "tool_protocol_adapter.bridge.lora_A",
+    "tool_protocol_adapter.bridge.lora_A.default",
+    "tool_protocol_adapter.bridge.lora_B",
+    "tool_protocol_adapter.bridge.lora_B.default",
+    "tool_protocol_adapter.bridge.lora_dropout",
+    "tool_protocol_adapter.bridge.lora_dropout.default",
+    "tool_protocol_adapter.bridge.lora_embedding_A",
+    "tool_protocol_adapter.bridge.lora_embedding_B",
+    "tool_protocol_adapter.bridge.lora_magnitude_vector",
+    "toolspec_bridge",
+    "toolspec_bridge.adapter",
+    "toolspec_bridge.adapter.base_layer",
+    "toolspec_bridge.adapter.lora_A",
+    "toolspec_bridge.adapter.lora_A.default",
+    "toolspec_bridge.adapter.lora_B",
+    "toolspec_bridge.adapter.lora_B.default",
+    "toolspec_bridge.adapter.lora_dropout",
+    "toolspec_bridge.adapter.lora_dropout.default",
+    "toolspec_bridge.adapter.lora_embedding_A",
+    "toolspec_bridge.adapter.lora_embedding_B",
+    "toolspec_bridge.adapter.lora_magnitude_vector",
+    "toolspec_head",
+    "toolspec_head.param_schema_adapter",
+    "toolspec_head.param_schema_adapter.base_layer",
+    "toolspec_head.param_schema_adapter.lora_A",
+    "toolspec_head.param_schema_adapter.lora_A.default",
+    "toolspec_head.param_schema_adapter.lora_B",
+    "toolspec_head.param_schema_adapter.lora_B.default",
+    "toolspec_head.param_schema_adapter.lora_dropout",
+    "toolspec_head.param_schema_adapter.lora_dropout.default",
+    "toolspec_head.param_schema_adapter.lora_embedding_A",
+    "toolspec_head.param_schema_adapter.lora_embedding_B",
+    "toolspec_head.param_schema_adapter.lora_magnitude_vector",
+    "toolspec_head.postcondition_adapter",
+    "toolspec_head.postcondition_adapter.base_layer",
+    "toolspec_head.postcondition_adapter.lora_A",
+    "toolspec_head.postcondition_adapter.lora_A.default",
+    "toolspec_head.postcondition_adapter.lora_B",
+    "toolspec_head.postcondition_adapter.lora_B.default",
+    "toolspec_head.postcondition_adapter.lora_dropout",
+    "toolspec_head.postcondition_adapter.lora_dropout.default",
+    "toolspec_head.postcondition_adapter.lora_embedding_A",
+    "toolspec_head.postcondition_adapter.lora_embedding_B",
+    "toolspec_head.postcondition_adapter.lora_magnitude_vector",
+    "toolspec_head.precondition_adapter",
+    "toolspec_head.precondition_adapter.base_layer",
+    "toolspec_head.precondition_adapter.lora_A",
+    "toolspec_head.precondition_adapter.lora_A.default",
+    "toolspec_head.precondition_adapter.lora_B",
+    "toolspec_head.precondition_adapter.lora_B.default",
+    "toolspec_head.precondition_adapter.lora_dropout",
+    "toolspec_head.precondition_adapter.lora_dropout.default",
+    "toolspec_head.precondition_adapter.lora_embedding_A",
+    "toolspec_head.precondition_adapter.lora_embedding_B",
+    "toolspec_head.precondition_adapter.lora_magnitude_vector",
+    "toolspec_head.receipt_formatter",
+    "toolspec_head.receipt_formatter.base_layer",
+    "toolspec_head.receipt_formatter.lora_A",
+    "toolspec_head.receipt_formatter.lora_A.default",
+    "toolspec_head.receipt_formatter.lora_B",
+    "toolspec_head.receipt_formatter.lora_B.default",
+    "toolspec_head.receipt_formatter.lora_dropout",
+    "toolspec_head.receipt_formatter.lora_dropout.default",
+    "toolspec_head.receipt_formatter.lora_embedding_A",
+    "toolspec_head.receipt_formatter.lora_embedding_B",
+    "toolspec_head.receipt_formatter.lora_magnitude_vector",
+    "toolspec_head.trigger_gate",
+    "toolspec_head.trigger_gate.base_layer",
+    "toolspec_head.trigger_gate.lora_A",
+    "toolspec_head.trigger_gate.lora_A.default",
+    "toolspec_head.trigger_gate.lora_B",
+    "toolspec_head.trigger_gate.lora_B.default",
+    "toolspec_head.trigger_gate.lora_dropout",
+    "toolspec_head.trigger_gate.lora_dropout.default",
+    "toolspec_head.trigger_gate.lora_embedding_A",
+    "toolspec_head.trigger_gate.lora_embedding_B",
+    "toolspec_head.trigger_gate.lora_magnitude_vector",
+    "toolspec_head.validator_gate",
+    "toolspec_head.validator_gate.base_layer",
+    "toolspec_head.validator_gate.lora_A",
+    "toolspec_head.validator_gate.lora_A.default",
+    "toolspec_head.validator_gate.lora_B",
+    "toolspec_head.validator_gate.lora_B.default",
+    "toolspec_head.validator_gate.lora_dropout",
+    "toolspec_head.validator_gate.lora_dropout.default",
+    "toolspec_head.validator_gate.lora_embedding_A",
+    "toolspec_head.validator_gate.lora_embedding_B",
+    "toolspec_head.validator_gate.lora_magnitude_vector",
+    "uncertainty_head",
+    "uncertainty_head.calibration_mlp",
+    "uncertainty_head.proj",
+    "validator_feedback_bridge",
+    "validator_feedback_bridge.adapter",
+    "validator_feedback_bridge.adapter.base_layer",
+    "validator_feedback_bridge.adapter.lora_A",
+    "validator_feedback_bridge.adapter.lora_A.default",
+    "validator_feedback_bridge.adapter.lora_B",
+    "validator_feedback_bridge.adapter.lora_B.default",
+    "validator_feedback_bridge.adapter.lora_dropout",
+    "validator_feedback_bridge.adapter.lora_dropout.default",
+    "validator_feedback_bridge.adapter.lora_embedding_A",
+    "validator_feedback_bridge.adapter.lora_embedding_B",
+    "validator_feedback_bridge.adapter.lora_magnitude_vector",
+    "validator_feedback_loop",
+    "validator_feedback_loop.rollback_adapter",
+    "validator_receipt_bridge",
+    "validator_receipt_bridge.adapter",
+    "validator_uncertainty_bridge",
+    "validator_uncertainty_bridge.adapter",
+    "workspace_snapshot_manager",
+    "workspace_snapshot_manager.rollback_context",
+    "worktree_binding",
+    "worktree_binding.adapter",
+    "worktree_manager",
+    "worktree_manager.adapter"
+  ],
+  "trainable_parameter_report": {
+    "backbone_frozen": true,
+    "backbone_present": true,
+    "hidden_size": 2048,
+    "host_parameters": 176621573,
+    "host_trainable_parameters": 360448,
+    "total_parameters": 34132679301,
+    "trainable_parameters": 360448,
+    "version": "veriloop.coder_peft_host.v1"
+  },
+  "version": "veriloop.coder_peft_host.v1"
+}