Instructions to use cleyesode/GLM-4.7-Flash-Coder-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cleyesode/GLM-4.7-Flash-Coder-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="cleyesode/GLM-4.7-Flash-Coder-NVFP4")
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("cleyesode/GLM-4.7-Flash-Coder-NVFP4")
model = AutoModelForCausalLM.from_pretrained("cleyesode/GLM-4.7-Flash-Coder-NVFP4", 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 cleyesode/GLM-4.7-Flash-Coder-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cleyesode/GLM-4.7-Flash-Coder-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": "cleyesode/GLM-4.7-Flash-Coder-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cleyesode/GLM-4.7-Flash-Coder-NVFP4

SGLang

How to use cleyesode/GLM-4.7-Flash-Coder-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 "cleyesode/GLM-4.7-Flash-Coder-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": "cleyesode/GLM-4.7-Flash-Coder-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 "cleyesode/GLM-4.7-Flash-Coder-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": "cleyesode/GLM-4.7-Flash-Coder-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cleyesode/GLM-4.7-Flash-Coder-NVFP4 with Docker Model Runner:
```
docker model run hf.co/cleyesode/GLM-4.7-Flash-Coder-NVFP4
```

GLM-4.7-Flash-Coder-NVFP4 / config.json

cleyesode

Upload folder using huggingface_hub

de55de1 verified 4 days ago

Raw History Blame Contribute Delete

8.92 kB

	{
	"architectures": [
	"Glm4MoeLiteForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"pad_token_id": 154820,
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"hidden_act": "silu",
	"hidden_size": 2048,
	"intermediate_size": 10240,
	"max_position_embeddings": 202752,
	"model_type": "glm4_moe_lite",
	"moe_intermediate_size": 1536,
	"topk_method": "noaux_tc",
	"norm_topk_prob": true,
	"num_attention_heads": 20,
	"n_group": 1,
	"topk_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 1,
	"routed_scaling_factor": 1.8,
	"num_experts_per_tok": 4,
	"first_k_dense_replace": 1,
	"num_hidden_layers": 47,
	"num_key_value_heads": 20,
	"num_nextn_predict_layers": 1,
	"partial_rotary_factor": 1.0,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"tie_word_embeddings": false,
	"dtype": "bfloat16",
	"transformers_version": "5.0.0rc0",
	"q_lora_rank": 768,
	"kv_lora_rank": 512,
	"qk_nope_head_dim": 192,
	"qk_rope_head_dim": 64,
	"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": [
	"model.layers.1.mlp.experts",
	"model.layers.2.mlp.experts",
	"model.layers.3.mlp.experts",
	"model.layers.4.mlp.experts",
	"model.layers.5.mlp.experts",
	"model.layers.6.mlp.experts",
	"model.layers.7.mlp.experts",
	"model.layers.8.mlp.experts",
	"model.layers.9.mlp.experts",
	"model.layers.10.mlp.experts",
	"model.layers.11.mlp.experts",
	"model.layers.12.mlp.experts",
	"model.layers.13.mlp.experts",
	"model.layers.14.mlp.experts",
	"model.layers.15.mlp.experts",
	"model.layers.16.mlp.experts",
	"model.layers.17.mlp.experts",
	"model.layers.18.mlp.experts",
	"model.layers.19.mlp.experts",
	"model.layers.20.mlp.experts",
	"model.layers.21.mlp.experts",
	"model.layers.22.mlp.experts",
	"model.layers.23.mlp.experts",
	"model.layers.24.mlp.experts",
	"model.layers.25.mlp.experts",
	"model.layers.26.mlp.experts",
	"model.layers.27.mlp.experts",
	"model.layers.28.mlp.experts",
	"model.layers.29.mlp.experts",
	"model.layers.30.mlp.experts",
	"model.layers.31.mlp.experts",
	"model.layers.32.mlp.experts",
	"model.layers.33.mlp.experts",
	"model.layers.34.mlp.experts",
	"model.layers.35.mlp.experts",
	"model.layers.36.mlp.experts",
	"model.layers.37.mlp.experts",
	"model.layers.38.mlp.experts",
	"model.layers.39.mlp.experts",
	"model.layers.40.mlp.experts",
	"model.layers.41.mlp.experts",
	"model.layers.42.mlp.experts",
	"model.layers.43.mlp.experts",
	"model.layers.44.mlp.experts",
	"model.layers.45.mlp.experts",
	"model.layers.46.mlp.experts"
	]
	}
	},
	"ignore": [
	"lm_head",
	"model.embed_tokens",
	"model.layers.*.mlp.down_proj",
	"model.layers.*.mlp.gate",
	"model.layers.*.mlp.gate_proj",
	"model.layers.*.mlp.shared_experts.down_proj",
	"model.layers.*.mlp.shared_experts.gate_proj",
	"model.layers.*.mlp.shared_experts.up_proj",
	"model.layers.*.mlp.up_proj",
	"model.layers.*.self_attn.kv_a_proj_with_mqa",
	"model.layers.*.self_attn.kv_b_proj",
	"model.layers.*.self_attn.o_proj",
	"model.layers.*.self_attn.q_a_proj",
	"model.layers.*.self_attn.q_b_proj"
	],
	"quant_algo": "MIXED_PRECISION",
	"producer": {
	"name": "modelopt",
	"version": "0.47.0rc1.dev129+g333ace1bc"
	},
	"quant_method": "modelopt",
	"quantized_layers": {
	"model.layers.1.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.10.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.11.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.12.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.13.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.14.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.15.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.16.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.17.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.18.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.19.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.2.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.20.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.21.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.22.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.23.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.24.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.25.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.26.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.27.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.28.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.29.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.3.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.30.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.31.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.32.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.33.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.34.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.35.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.36.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.37.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.38.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.39.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.4.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.40.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.41.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.42.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.43.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.44.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.45.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.46.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.5.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.6.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.7.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.8.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	},
	"model.layers.9.mlp.experts": {
	"quant_algo": "NVFP4",
	"group_size": 16
	}
	}
	}
	}