Instructions to use liminerity/m7-1.58bit-6x70m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/m7-1.58bit-6x70m with Transformers:

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

pipe = pipeline("text-generation", model="liminerity/m7-1.58bit-6x70m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liminerity/m7-1.58bit-6x70m")
model = AutoModelForCausalLM.from_pretrained("liminerity/m7-1.58bit-6x70m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liminerity/m7-1.58bit-6x70m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liminerity/m7-1.58bit-6x70m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/m7-1.58bit-6x70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liminerity/m7-1.58bit-6x70m

SGLang

How to use liminerity/m7-1.58bit-6x70m 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 "liminerity/m7-1.58bit-6x70m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/m7-1.58bit-6x70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "liminerity/m7-1.58bit-6x70m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/m7-1.58bit-6x70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liminerity/m7-1.58bit-6x70m with Docker Model Runner:
```
docker model run hf.co/liminerity/m7-1.58bit-6x70m
```

m7-1.58bit-6x70m

m7-1.58bit-6x70m is a Mixture of Experts (MoE) made with the following models using LazyMergekit:

🧩 Configuration

base_model: liminerity/Bitnet-M7-70m
experts:
  - source_model: liminerity/Bitnet-M7-70m
    positive_prompts: ["what"]
  - source_model: liminerity/Bitnet-M7-70m
    positive_prompts: ["why is"]
  - source_model: liminerity/Bitnet-M7-70m
    positive_prompts: ["who is"]
  - source_model: liminerity/Bitnet-M7-70m
    positive_prompts: ["how come"]
  - source_model: liminerity/Bitnet-M7-70m
    positive_prompts: ["why so"]

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "liminerity/NeuralPipe-7B-slerp"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 8

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for liminerity/m7-1.58bit-6x70m

Base model

liminerity/Bitnet-M7-70m

Finetuned

(2)

this model