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

Libraries

How to use PMSCCMA/FengHe with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PMSCCMA/FengHe")
model = AutoModelForCausalLM.from_pretrained("PMSCCMA/FengHe")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PMSCCMA/FengHe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PMSCCMA/FengHe

SGLang

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

Docker Model Runner
How to use PMSCCMA/FengHe with Docker Model Runner:
```
docker model run hf.co/PMSCCMA/FengHe
```

FengHe

Model Summary

FengHe is a meteorological service domain large language model developed by the Public Meteorological Service Center of China Meteorological Administration based on GLM-4.5-Air. It is further trained with over 50 million tokens of high-quality meteorological service corpus and 490,000 scenario-oriented instruction-tuning examples.

FengHe is the first large language model in China specifically designed for the meteorological service domain. It is optimized for meteorological service requirement understanding, service-oriented content generation, meteorological reasoning and decision support, and meteorological service tool calling.

Model Availability

This repository provides the complete FengHe model release, including the Model Card, model weights, configuration files, tokenizer files, training data description, and evaluation result visualizations.

The model can be loaded directly with Transformers, vLLM, or SGLang.

Model Details

Item	Description
Model name	FengHe
Model type	Meteorological service domain large language model
Base model	GLM-4.5-Air
Architecture	Mixture-of-Experts, Causal Language Model
Total parameters	106B
Activated parameters	12B
Context length	128K tokens
Training precision	BF16
License	MIT
Languages	Chinese, English
Domain	Meteorological services, weather forecasting, warning services, decision support, tool calling

Architecture

FengHe inherits the MoE architecture and hybrid reasoning capability of GLM. It supports reasoning-oriented generation for complex tasks and direct-response generation for real-time interactions.

Parameter	Value
Architecture	`Glm4MoeForCausalLM`
Model type	`glm4_moe`
Number of hidden layers	46
Hidden size	4096
Intermediate size	10944
MoE intermediate size	1408
Attention heads	96
Key-value heads	8
Routed experts	128
Shared experts	1
Experts per token	8
Head dimension	128
Max position embeddings	131072
Vocabulary size	151552
Activation function	SiLU
Normalization	RMSNorm
RoPE theta	1000000
Torch dtype	BF16

Training Data

FengHe is trained on a high-quality meteorological service corpus built from multiple professional data sources, including:

Meteorological books
Meteorological industry standards
National standards
Warning translation texts
Meteorological service reports
Meteorological news and information
Scenario-oriented meteorological question-answering instructions

Based on these sources, we constructed a high-quality meteorological service corpus of over 50 million tokens and manually annotated 490,000 scenario-oriented meteorological instruction examples. These data improve the model's professional expression, business understanding, reasoning, decision-support capability, and tool-calling ability in the meteorological service domain.

Capabilities

FengHe is optimized for meteorological service scenarios, with improvements in the following capabilities:

Meteorological service requirement understanding Understands user needs in weather forecasting, severe weather, warning services, event support, public services, and decision-support scenarios.
Meteorological service content generation Generates service-oriented meteorological texts for the public, industry users, and decision makers, including weather briefings, service reports, risk alerts, and warning interpretations.
Meteorological reasoning and decision support Performs analysis, summarization, judgment, and decision-support reasoning based on meteorological facts, forecast information, disaster risks, and service scenarios.
Meteorological service tool calling Supports tool calling and workflow orchestration for meteorological query, data retrieval, product generation, warning services, and related tasks.

Evaluation

We evaluate FengHe on MetsEval-1k, a meteorological service evaluation benchmark containing 1,076 questions across 4 dimensions:

Meteorological service requirement understanding
Meteorological service content generation
Meteorological reasoning and decision support
Meteorological service tool calling

The results show that FengHe achieves a higher overall score on MetsEval-1k than other mainstream general-purpose large language models, demonstrating its domain-specific advantages in meteorological services.

Quick Start

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "PMSCCMA/FengHe"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {
        "role": "user",
        "content": "Please generate a public-facing risk advisory for heavy rainfall."
    }
]

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=512,
    temperature=0.6,
    top_p=0.9,
)

response = tokenizer.decode(
    outputs[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=True,
)

print(response)

vLLM

vllm serve PMSCCMA/FengHe \
  --tensor-parallel-size 8 \
  --served-model-name fenghe

SGLang

python3 -m sglang.launch_server \
  --model-path PMSCCMA/FengHe \
  --tp-size 8 \
  --host 0.0.0.0 \
  --port 30000 \
  --served-model-name fenghe

Call the OpenAI-compatible API:

curl -X POST "http://localhost:30000/v1/chat/completions" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "fenghe",
    "messages": [
      {
        "role": "user",
        "content": "Please generate a meteorological service advisory for transportation under typhoon impacts."
      }
    ],
    "temperature": 0.6,
    "top_p": 0.9,
    "max_tokens": 512
  }'

Usage Statement

FengHe is released for meteorological services, research, industry application development, and agent system construction. Users should comply with applicable laws, regulations, industry standards, and meteorological service requirements. The model must not be used to generate fake warnings, misleading meteorological information, or any content that may pose public safety risks.

License

This model is released under the MIT License. It can be used for research, commercial applications, and secondary development, subject to the terms of the MIT License.

Downloads last month: 178

Safetensors

Model size

107B params

Tensor type

F32

BF16