Instructions to use ConicCat/GL-Marvin-32k-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ConicCat/GL-Marvin-32k-32B with Transformers:

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

pipe = pipeline("text-generation", model="ConicCat/GL-Marvin-32k-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ConicCat/GL-Marvin-32k-32B")
model = AutoModelForMultimodalLM.from_pretrained("ConicCat/GL-Marvin-32k-32B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ConicCat/GL-Marvin-32k-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ConicCat/GL-Marvin-32k-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConicCat/GL-Marvin-32k-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ConicCat/GL-Marvin-32k-32B

SGLang

How to use ConicCat/GL-Marvin-32k-32B 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 "ConicCat/GL-Marvin-32k-32B" \
    --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": "ConicCat/GL-Marvin-32k-32B",
		"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 "ConicCat/GL-Marvin-32k-32B" \
        --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": "ConicCat/GL-Marvin-32k-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use ConicCat/GL-Marvin-32k-32B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ConicCat/GL-Marvin-32k-32B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ConicCat/GL-Marvin-32k-32B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ConicCat/GL-Marvin-32k-32B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ConicCat/GL-Marvin-32k-32B",
    max_seq_length=2048,
)

Docker Model Runner
How to use ConicCat/GL-Marvin-32k-32B with Docker Model Runner:
```
docker model run hf.co/ConicCat/GL-Marvin-32k-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GLM-4 with hopefully fixed context and some Alpaca eval maxxing. This checkpoint is SFT only and I'm planning to do APO, but still need to gen ~10K responses for training and finish up my anti-rep preference dataset.

32K context requires only 2GB VRAM, so you can fit Q4_K_M + 32k context on a single 24GB GPU, best in class for 32B dense models.

Chat Template:

GLM-4.1

Major Thanks

Thudm for the excellent GLM-4 Base

nyu-dice-lab for WildChat-50M

AI2 for the Tulu dataset

Downloads last month: 5

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for ConicCat/GL-Marvin-32k-32B

Base model

zai-org/GLM-4-32B-Base-0414

Finetuned

arcee-ai/GLM-4-32B-Base-32K

Finetuned

(2)

this model

Quantizations

4 models

ConicCat
/

GL-Marvin-32k-32B

Chat Template:

Major Thanks

Model tree for ConicCat/GL-Marvin-32k-32B

Datasets used to train ConicCat/GL-Marvin-32k-32B