Instructions to use Mapika/GLM-5.2-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mapika/GLM-5.2-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Mapika/GLM-5.2-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Mapika/GLM-5.2-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Mapika/GLM-5.2-NVFP4")
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]:]))

TensorRT

How to use Mapika/GLM-5.2-NVFP4 with TensorRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mapika/GLM-5.2-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mapika/GLM-5.2-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mapika/GLM-5.2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mapika/GLM-5.2-NVFP4

SGLang

How to use Mapika/GLM-5.2-NVFP4 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 "Mapika/GLM-5.2-NVFP4" \
    --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": "Mapika/GLM-5.2-NVFP4",
		"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 "Mapika/GLM-5.2-NVFP4" \
        --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": "Mapika/GLM-5.2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mapika/GLM-5.2-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Mapika/GLM-5.2-NVFP4
```

GLM-5.2-NVFP4 / config.json

Mapika

Add files using upload-large-folder tool

32a7afc verified about 16 hours ago

Raw

History Blame Contribute Delete

7.1 kB

	{
	"architectures": [
	"GlmMoeDsaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"ep_size": 1,
	"first_k_dense_replace": 3,
	"head_dim": 192,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"index_head_dim": 128,
	"index_n_heads": 32,
	"index_share_for_mtp_iteration": true,
	"index_skip_topk_offset": 3,
	"index_topk": 2048,
	"index_topk_freq": 4,
	"index_topk_pattern": null,
	"indexer_rope_interleave": true,
	"indexer_types": [
	"full",
	"full",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared"
	],
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"kv_lora_rank": 512,
	"max_position_embeddings": 1048576,
	"mlp_layer_types": [
	"dense",
	"dense",
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "glm_moe_dsa",
	"moe_intermediate_size": 2048,
	"moe_layer_freq": 1,
	"n_group": 1,
	"n_routed_experts": 256,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 78,
	"num_key_value_heads": 64,
	"num_nextn_predict_layers": 1,
	"pad_token_id": 154820,
	"pretraining_tp": 1,
	"q_lora_rank": 2048,
	"qk_head_dim": 256,
	"qk_nope_head_dim": 192,
	"qk_rope_head_dim": 64,
	"rms_norm_eps": 1e-05,
	"rope_interleave": true,
	"rope_parameters": {
	"rope_theta": 8000000,
	"rope_type": "default"
	},
	"routed_scaling_factor": 2.5,
	"scoring_func": "sigmoid",
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"transformers_version": "5.12.0",
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"input_activations": {
	"dynamic": false,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"weights": {
	"dynamic": false,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"targets": [
	"Linear"
	]
	}
	},
	"ignore": [
	"lm_head",
	"model.layers.0.self_attn*",
	"model.layers.1.self_attn*",
	"model.layers.10.self_attn*",
	"model.layers.11.self_attn*",
	"model.layers.12.self_attn*",
	"model.layers.13.self_attn*",
	"model.layers.14.self_attn*",
	"model.layers.15.self_attn*",
	"model.layers.16.self_attn*",
	"model.layers.17.self_attn*",
	"model.layers.18.self_attn*",
	"model.layers.19.self_attn*",
	"model.layers.2.self_attn*",
	"model.layers.20.self_attn*",
	"model.layers.21.self_attn*",
	"model.layers.22.self_attn*",
	"model.layers.23.self_attn*",
	"model.layers.24.self_attn*",
	"model.layers.25.self_attn*",
	"model.layers.26.self_attn*",
	"model.layers.27.self_attn*",
	"model.layers.28.self_attn*",
	"model.layers.29.self_attn*",
	"model.layers.3.self_attn*",
	"model.layers.30.self_attn*",
	"model.layers.31.self_attn*",
	"model.layers.32.self_attn*",
	"model.layers.33.self_attn*",
	"model.layers.34.self_attn*",
	"model.layers.35.self_attn*",
	"model.layers.36.self_attn*",
	"model.layers.37.self_attn*",
	"model.layers.38.self_attn*",
	"model.layers.39.self_attn*",
	"model.layers.4.self_attn*",
	"model.layers.40.self_attn*",
	"model.layers.41.self_attn*",
	"model.layers.42.self_attn*",
	"model.layers.43.self_attn*",
	"model.layers.44.self_attn*",
	"model.layers.45.self_attn*",
	"model.layers.46.self_attn*",
	"model.layers.47.self_attn*",
	"model.layers.48.self_attn*",
	"model.layers.49.self_attn*",
	"model.layers.5.self_attn*",
	"model.layers.50.self_attn*",
	"model.layers.51.self_attn*",
	"model.layers.52.self_attn*",
	"model.layers.53.self_attn*",
	"model.layers.54.self_attn*",
	"model.layers.55.self_attn*",
	"model.layers.56.self_attn*",
	"model.layers.57.self_attn*",
	"model.layers.58.self_attn*",
	"model.layers.59.self_attn*",
	"model.layers.6.self_attn*",
	"model.layers.60.self_attn*",
	"model.layers.61.self_attn*",
	"model.layers.62.self_attn*",
	"model.layers.63.self_attn*",
	"model.layers.64.self_attn*",
	"model.layers.65.self_attn*",
	"model.layers.66.self_attn*",
	"model.layers.67.self_attn*",
	"model.layers.68.self_attn*",
	"model.layers.69.self_attn*",
	"model.layers.7.self_attn*",
	"model.layers.70.self_attn*",
	"model.layers.71.self_attn*",
	"model.layers.72.self_attn*",
	"model.layers.73.self_attn*",
	"model.layers.74.self_attn*",
	"model.layers.75.self_attn*",
	"model.layers.76.self_attn*",
	"model.layers.77.self_attn*",
	"model.layers.8.self_attn*",
	"model.layers.9.self_attn*"
	],
	"quant_algo": "NVFP4",
	"producer": {
	"name": "modelopt",
	"version": "0.44.0"
	},
	"quant_method": "modelopt"
	}
	}