Instructions to use TLLMC/g-1.1.0-mxfp4-fixed-2512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TLLMC/g-1.1.0-mxfp4-fixed-2512 with Transformers:

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

pipe = pipeline("text-generation", model="TLLMC/g-1.1.0-mxfp4-fixed-2512")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TLLMC/g-1.1.0-mxfp4-fixed-2512")
model = AutoModelForCausalLM.from_pretrained("TLLMC/g-1.1.0-mxfp4-fixed-2512", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TLLMC/g-1.1.0-mxfp4-fixed-2512 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TLLMC/g-1.1.0-mxfp4-fixed-2512"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TLLMC/g-1.1.0-mxfp4-fixed-2512",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TLLMC/g-1.1.0-mxfp4-fixed-2512

SGLang

How to use TLLMC/g-1.1.0-mxfp4-fixed-2512 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 "TLLMC/g-1.1.0-mxfp4-fixed-2512" \
    --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": "TLLMC/g-1.1.0-mxfp4-fixed-2512",
		"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 "TLLMC/g-1.1.0-mxfp4-fixed-2512" \
        --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": "TLLMC/g-1.1.0-mxfp4-fixed-2512",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TLLMC/g-1.1.0-mxfp4-fixed-2512 with Docker Model Runner:
```
docker model run hf.co/TLLMC/g-1.1.0-mxfp4-fixed-2512
```

g.1.1.0-mxfp4-fixed-2512

Training

Datasets

Dataset	Samples
qa-dataset-raft	73232
multi_dataset	35690

Hyper Parameters

Parameter	Value
epochs	5
learning rate	5e-6

Inference

使用 Transformers pipeline 進行單輪生成。

from transformers import pipeline

model_id = "./g-1.1.0-mxfp4-fixed-2512"  # 或本機目錄路徑

pipe = pipeline(
    "text-generation",
    model=model_id,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {
        "role": "user",
        "content": "USER PROMPT HERE",
    },
]

prompt = pipe.tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

outputs = pipe(
    prompt,
    max_new_tokens=2048,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    return_full_text=False,
)

print(outputs[0]["generated_text"])

Downloads last month: 15

Safetensors

Model size

22B params

Tensor type

F32

BF16