Instructions to use RedHatAI/GLM-5.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.1 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/GLM-5.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/GLM-5.1")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/GLM-5.1")
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 RedHatAI/GLM-5.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/GLM-5.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/GLM-5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.1

SGLang

How to use RedHatAI/GLM-5.1 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 "RedHatAI/GLM-5.1" \
    --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": "RedHatAI/GLM-5.1",
		"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 "RedHatAI/GLM-5.1" \
        --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": "RedHatAI/GLM-5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.1 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.1
```

SaylorTwift HF Staff commited on 3 days ago

Commit

922e8fd

verified ·

1 Parent(s): 2a151f0

Delete .eval_results

Browse files

Hey! Nathan from HF here. Would you be ok with deleting the eval_result folder so it doesn't appear as a duplicate on the leaderboards?

Thanks!

Files changed (8) hide show

.eval_results/MathArena--aime_2026.yaml +0 -8
.eval_results/MathArena--hmmt_feb_2026.yaml +0 -8
.eval_results/gpqa.yaml +0 -8
.eval_results/hle.yaml +0 -8
.eval_results/hle_with_tools.yaml +0 -9
.eval_results/swe_bench_pro.yaml +0 -8
.eval_results/terminal_bench_2.yaml +0 -8
.eval_results/terminal_bench_2_claudecode.yaml +0 -9

.eval_results/MathArena--aime_2026.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: MathArena/aime_2026
-    task_id: MathArena/aime_2026
-  value: 95.3
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card

.eval_results/MathArena--hmmt_feb_2026.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: MathArena/hmmt_feb_2026
-    task_id: MathArena/hmmt_feb_2026
-  value: 82.6
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card

.eval_results/gpqa.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: Idavidrein/gpqa
-    task_id: diamond
-  value: 86.2
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card

.eval_results/hle.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: cais/hle
-    task_id: hle
-  value: 31.0
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card

.eval_results/hle_with_tools.yaml DELETED Viewed

@@ -1,9 +0,0 @@
-- dataset:
-    id: cais/hle
-    task_id: hle
-  value: 52.3
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card
-  notes: "With tools"

.eval_results/swe_bench_pro.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: ScaleAI/SWE-bench_Pro
-    task_id: SWE_Bench_Pro
-  value: 58.4
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card
-  notes: high reasoning

.eval_results/terminal_bench_2.yaml DELETED Viewed

@@ -1,8 +0,0 @@
-- dataset:
-    id: harborframework/terminal-bench-2.0
-    task_id: terminalbench_2
-  value: 63.5
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card

.eval_results/terminal_bench_2_claudecode.yaml DELETED Viewed

@@ -1,9 +0,0 @@
-- dataset:
-    id: harborframework/terminal-bench-2.0
-    task_id: terminalbench_2
-  value: 69.0
-  date: '2026-04-07'
-  source:
-    url: https://huggingface.co/zai-org/GLM-5.1
-    name: Model Card
-  notes: "agent: Terminus 2(Claude Code)"