Instructions to use zgcagi/ZGCM-1-7B-Pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zgcagi/ZGCM-1-7B-Pretrain with Transformers:

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

pipe = pipeline("text-generation", model="zgcagi/ZGCM-1-7B-Pretrain", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("zgcagi/ZGCM-1-7B-Pretrain", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zgcagi/ZGCM-1-7B-Pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zgcagi/ZGCM-1-7B-Pretrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zgcagi/ZGCM-1-7B-Pretrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zgcagi/ZGCM-1-7B-Pretrain

SGLang

How to use zgcagi/ZGCM-1-7B-Pretrain 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 "zgcagi/ZGCM-1-7B-Pretrain" \
    --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": "zgcagi/ZGCM-1-7B-Pretrain",
		"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 "zgcagi/ZGCM-1-7B-Pretrain" \
        --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": "zgcagi/ZGCM-1-7B-Pretrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zgcagi/ZGCM-1-7B-Pretrain with Docker Model Runner:
```
docker model run hf.co/zgcagi/ZGCM-1-7B-Pretrain
```

ZGCM-1-7B-Pretrain

Completed pretraining checkpoint after approximately 4.780T cumulative tokens. Superseded rollback work is excluded from this count.

Property	Value
Checkpoint step within its run	387950
Training context	16,384 tokens
Training tokens (pretraining cumulative)	approximately 4779.97B
Precision	BF16
RoPE base	5,000,000
Stage completed	Yes

This is a base language-model checkpoint. It has not undergone instruction tuning. Use plain text inputs; the included tokenizer assets retain the original token IDs.

Loading

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zgcagi/ZGCM-1-7B-Pretrain"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, torch_dtype=torch.bfloat16,
    device_map="auto", attn_implementation="eager",
)
inputs = tokenizer("The purpose of scientific research is", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=32, do_sample=False, use_cache=False)
print(tokenizer.decode(output[0], skip_special_tokens=True))

The repository includes the custom ZGCM Transformers implementation. The loading example uses its uncached reference generation path. Conversion and short forward/ generation checks used PyTorch 2.7 and Transformers 4.57.0.

Conversion validation

Exported with export_megatron_zgcm_to_hf.py. All 259 source model tensors round-trip exactly through the 382 exported tensors, preserving BF16 values, grouped Q/G/K/V layout, SwiGLU weights, and normalization parameters. Every exported shard is listed in model.safetensors.index.json and SHA256SUMS.

Local HF loading had no missing or unexpected tensors. A 160-token forward pass and short greedy generation passed. These checks do not constitute a native Megatron-versus-HF logits comparison or long-context benchmark validation.

See checkpoint_info.json for the precise checkpoint identity and validation scope.

Downloads last month: 41

Safetensors

Model size

7B params

Tensor type

BF16

Collection including zgcagi/ZGCM-1-7B-Pretrain

ZGCM-1

Collection

8 items • Updated 3 days ago • 2