Instructions to use aliRafik/glm_flash_finetuned_16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aliRafik/glm_flash_finetuned_16bit with Transformers:

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

pipe = pipeline("text-generation", model="aliRafik/glm_flash_finetuned_16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aliRafik/glm_flash_finetuned_16bit")
model = AutoModelForCausalLM.from_pretrained("aliRafik/glm_flash_finetuned_16bit", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aliRafik/glm_flash_finetuned_16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aliRafik/glm_flash_finetuned_16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aliRafik/glm_flash_finetuned_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aliRafik/glm_flash_finetuned_16bit

SGLang

How to use aliRafik/glm_flash_finetuned_16bit 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 "aliRafik/glm_flash_finetuned_16bit" \
    --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": "aliRafik/glm_flash_finetuned_16bit",
		"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 "aliRafik/glm_flash_finetuned_16bit" \
        --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": "aliRafik/glm_flash_finetuned_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use aliRafik/glm_flash_finetuned_16bit with Docker Model Runner:
```
docker model run hf.co/aliRafik/glm_flash_finetuned_16bit
```

Uploaded finetuned model

Developed by: aliRafik
License: apache-2.0
Finetuned from model : unsloth/GLM-4.7-Flash

This glm4_moe_lite model was trained 2x faster with Unsloth and Huggingface's TRL library.

Inference

from transformers import AutoModelForCausalLM, AutoTokenizer import torch

Load from Hugging Face

model = AutoModelForCausalLM.from_pretrained( "aliRafik/glm_flash_finetuned_16bit", torch_dtype=torch.float16, device_map="auto" )

tokenizer = AutoTokenizer.from_pretrained("aliRafik/glm_flash_finetuned_16bit")

Test inference

inputs = tokenizer("Hello, how are you?", return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=100) print(tokenizer.decode(outputs[0]))

Output

Downloads last month: 16

Safetensors

Model size

31B params

Tensor type

BF16

F32

Model tree for aliRafik/glm_flash_finetuned_16bit

Base model

zai-org/GLM-4.7-Flash

Finetuned

unsloth/GLM-4.7-Flash

Finetuned

(21)

this model