Instructions to use buugiiiiii/GLM-4.7-Flash-REAP-Code-48E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use buugiiiiii/GLM-4.7-Flash-REAP-Code-48E with Transformers:

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

pipe = pipeline("text-generation", model="buugiiiiii/GLM-4.7-Flash-REAP-Code-48E")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("buugiiiiii/GLM-4.7-Flash-REAP-Code-48E")
model = AutoModelForCausalLM.from_pretrained("buugiiiiii/GLM-4.7-Flash-REAP-Code-48E", device_map="auto")
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 buugiiiiii/GLM-4.7-Flash-REAP-Code-48E with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/buugiiiiii/GLM-4.7-Flash-REAP-Code-48E

SGLang

How to use buugiiiiii/GLM-4.7-Flash-REAP-Code-48E 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 "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E" \
    --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": "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E",
		"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 "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E" \
        --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": "buugiiiiii/GLM-4.7-Flash-REAP-Code-48E",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use buugiiiiii/GLM-4.7-Flash-REAP-Code-48E with Docker Model Runner:
```
docker model run hf.co/buugiiiiii/GLM-4.7-Flash-REAP-Code-48E
```

GLM-4.7-Flash-REAP-Code-48E / artifacts /observation-validation.json

buugiiiiii

Add verified model card, benchmark artifacts, and survivor manifest

b53331c verified 6 days ago

Raw

History Blame Contribute Delete

1.43 kB

	{
	"status": "PASS",
	"stage": "B14 REAP-Code-S1 selected-only accumulation validation",
	"decision_eligible": true,
	"release_eligible": false,
	"model_path": "/workspace/models/glm-4.7-flash",
	"model_revision": "7dd20894a642a0aa287e9827cb1a1f7f91386b67",
	"model_class": "Glm4MoeLiteForCausalLM",
	"model_dtype": "torch.bfloat16",
	"experts_implementation": "eager",
	"manifest_path": "/workspace/kguard-reap/data/glm-calibration-reap-code-s1-8192.jsonl",
	"manifest_sha256": "3f2c46de59e42213b9d4c614cd9fdaca3d53b5ee141cf13c13680aee71cc326b",
	"samples": 8192,
	"shards": 128,
	"shard_size": 64,
	"total_tokens": 4366438,
	"collection_mode": "batch1-all-token",
	"observed_moe_layer_count": 46,
	"experts": 64,
	"top_k": 4,
	"scaling": 1.8,
	"observer_logit_max_error_this_run": 0.0,
	"load_seconds_this_run": 372.36645814100484,
	"peak_cuda_allocated_gib_this_run": 59.07405138015747,
	"collection_seconds_all_shards": 7233.351361623034,
	"tokens_per_second_all_shards": 603.653518501312,
	"tensor_output_path": "/workspace/kguard-reap/logs/glm-reap-code-s1-combined-8192.pt",
	"tensor_output_sha256": "ec5959ed72a50e04c23809190d22632fb9b4dcb77d4c6f590c7f581b78ece148",
	"detail_output_path": "/workspace/kguard-reap/logs/glm-reap-code-s1-combined-8192.json",
	"detail_output_sha256": "83e33f906ce9617f8052d0f33fdc602a58cfff882b99e5065248628e24cb7f38",
	"failure_count": 0,
	"failures": []
	}