Instructions to use tiny-random/glm-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/glm-5 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/glm-5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiny-random/glm-5")
model = AutoModelForCausalLM.from_pretrained("tiny-random/glm-5")
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

vLLM

How to use tiny-random/glm-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/glm-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/glm-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/glm-5

SGLang

How to use tiny-random/glm-5 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 "tiny-random/glm-5" \
    --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": "tiny-random/glm-5",
		"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 "tiny-random/glm-5" \
        --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": "tiny-random/glm-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/glm-5 with Docker Model Runner:
```
docker model run hf.co/tiny-random/glm-5
```

yujiepan

nikita-savelyev-cerebras commited on Feb 27

Commit

22e4de0

1 Parent(s): c8c1b64

1 (#2)

Browse files

- Fix to https://huggingface.co/tiny-random/glm-5/discussions/1 (df3b1ccafa9eb40ed5a2fc25d3ae6b4ac0cf4238)

Co-authored-by: Nikita Savelyev <nikita-savelyev-cerebras@users.noreply.huggingface.co>

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 8,
-  "index_head_dim": 32,
   "index_n_heads": 4,
   "index_topk": 2048,
   "indexer_rope_interleave": true,

   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 8,
+  "index_head_dim": 128,
   "index_n_heads": 4,
   "index_topk": 2048,
   "indexer_rope_interleave": true,