Instructions to use issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2 with Transformers:

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

pipe = pipeline("text-generation", model="issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2")
model = AutoModelForCausalLM.from_pretrained("issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2")
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 issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2

SGLang

How to use issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2 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 "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2" \
    --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": "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2",
		"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 "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2" \
        --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": "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2 with Docker Model Runner:
```
docker model run hf.co/issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2
```

issdandavis commited on Apr 30

Commit

90f93e4

verified ·

1 Parent(s): 0c5e3a8

Upload scbe_merge_summary.json with huggingface_hub

Browse files

Files changed (1) hide show

scbe_merge_summary.json +51 -0

scbe_merge_summary.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "schema_version": "scbe_coding_model_merge_result_v1",
+  "merge_id": "coding-agent-qwen-merged-coding-model-v2",
+  "base_model": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
+  "output_model_repo": "issdandavis/scbe-coding-agent-qwen-merged-coding-model-v2",
+  "merge_mode": "weighted",
+  "adapters": [
+    {
+      "profile_id": "coding-agent-qwen-online-v2",
+      "stage": "cross_tongue_coder",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-online-v2",
+      "weight": 0.12,
+      "required": true
+    },
+    {
+      "profile_id": "coding-agent-qwen-binary-geoseal-v3",
+      "stage": "binary_geoseal_coder",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-binary-geoseal-v3",
+      "weight": 0.16,
+      "required": true
+    },
+    {
+      "profile_id": "coding-agent-qwen-geoseal-command-v4",
+      "stage": "command_recall_geoseal_coder",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-geoseal-command-v4",
+      "weight": 0.17,
+      "required": true
+    },
+    {
+      "profile_id": "coding-agent-qwen-atomic-workflow-stage6",
+      "stage": "atomic_workflow_resource_decay",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-atomic-workflow-stage6",
+      "weight": 0.25,
+      "required": true
+    },
+    {
+      "profile_id": "coding-agent-qwen-ca-geoseal-smoke-repair-v1",
+      "stage": "ca_geoseal_smoke_repair",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-ca-geoseal-smoke-repair-v1",
+      "weight": 0.3,
+      "required": true
+    }
+  ],
+  "blocked_adapters": [
+    {
+      "profile_id": "coding-agent-qwen-command-harmony-v5",
+      "adapter_repo": "issdandavis/scbe-coding-agent-qwen-command-harmony-v5",
+      "reason": "Repo was not found on Hugging Face during 2026-04-25 setup. Train or publish this adapter before adding it to the merge."
+    }
+  ]
+}