Instructions to use cmz1024/minimind-zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmz1024/minimind-zero with Transformers:

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

pipe = pipeline("text-generation", model="cmz1024/minimind-zero", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cmz1024/minimind-zero", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cmz1024/minimind-zero with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmz1024/minimind-zero"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cmz1024/minimind-zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cmz1024/minimind-zero

SGLang

How to use cmz1024/minimind-zero 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 "cmz1024/minimind-zero" \
    --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": "cmz1024/minimind-zero",
		"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 "cmz1024/minimind-zero" \
        --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": "cmz1024/minimind-zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cmz1024/minimind-zero with Docker Model Runner:
```
docker model run hf.co/cmz1024/minimind-zero
```

minimind-zero / config.json

cmz1024

Upload config.json with huggingface_hub

f5dfa1e verified over 1 year ago

Raw

History Blame

719 Bytes

	{
	"architectures": [
	"MiniMindLM"
	],
	"auto_map": {
	"AutoConfig": "LMConfig.LMConfig",
	"AutoModelForCausalLM": "model.MiniMindLM"
	},
	"aux_loss_alpha": 0.1,
	"dim": 512,
	"dropout": 0.0,
	"flash_attn": true,
	"hidden_dim": 1408,
	"max_seq_len": 8192,
	"model_type": "minimind",
	"multiple_of": 64,
	"n_heads": 8,
	"n_kv_heads": 2,
	"n_layers": 8,
	"n_routed_experts": 4,
	"n_shared_experts": true,
	"norm_eps": 1e-05,
	"norm_topk_prob": true,
	"num_experts_per_tok": 2,
	"rope_theta": 1000000.0,
	"scoring_func": "softmax",
	"seq_aux": true,
	"torch_dtype": "float32",
	"transformers_version": "4.48.0",
	"use_moe": false,
	"vocab_size": 6400
	}