Instructions to use TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic

SGLang

How to use TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic 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 "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic" \
    --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": "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic",
		"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 "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic" \
        --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": "TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic with Docker Model Runner:
```
docker model run hf.co/TsinghuaC3I/ZEDA-GLM-4.7-Flash-Dynamic
```

ZEDA-GLM-4.7-Flash-Dynamic / config.json

XingtaiHF

Upload folder using huggingface_hub

1051746 verified 2 days ago

raw

history blame contribute delete

1.17 kB

	{
	"architectures": [
	"Glm4MoeLitePlusPlusForCausalLM"
	],
	"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_plus_plus",
	"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,
	"use_zce_mask": false,
	"zce_nums": [
	32
	],
	"zce_types": [
	"zero"
	]
	}