Instructions to use nikimoriOne/MiniCPM5-1B-Base-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikimoriOne/MiniCPM5-1B-Base-8bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("nikimoriOne/MiniCPM5-1B-Base-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use nikimoriOne/MiniCPM5-1B-Base-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimoriOne/MiniCPM5-1B-Base-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nikimoriOne/MiniCPM5-1B-Base-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nikimoriOne/MiniCPM5-1B-Base-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nikimoriOne/MiniCPM5-1B-Base-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nikimoriOne/MiniCPM5-1B-Base-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nikimoriOne/MiniCPM5-1B-Base-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use nikimoriOne/MiniCPM5-1B-Base-8bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimoriOne/MiniCPM5-1B-Base-8bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nikimoriOne/MiniCPM5-1B-Base-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nikimoriOne/MiniCPM5-1B-Base-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimoriOne/MiniCPM5-1B-Base-8bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nikimoriOne/MiniCPM5-1B-Base-8bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiniCPM5-1B-Base-8bit / README.md

nikimori

Card: the repo moved to nikimoriOne

55a6a42 verified 5 days ago

preview code

Raw History Blame Contribute Delete

1.04 kB

metadata

license: apache-2.0
base_model: openbmb/MiniCPM5-1B-Base
library_name: mlx
pipeline_tag: text-generation
language:
  - en
  - zh
tags:
  - mlx
  - minicpm

MiniCPM5-1B-Base, 8-bit MLX

openbmb/MiniCPM5-1B-Base converted to MLX with mlx_lm.convert -q --q-bits 8 --q-group-size 64 (mlx-lm 0.31.3, affine). The weights are otherwise unchanged, and the license is the upstream one (Apache-2.0).

Converted for Pretype, on-device autocomplete for macOS, where it is the fastest completion model. On Pretype's 5,649-row, 17-language autocomplete set it ties the bf16 weights it replaces (first word right on 15% of all rows each; 14 against 21 discordant rows; English 28% of all rows for both), at 1.1 GB instead of 2.0 GB and about 30% less time per suggestion.

from mlx_lm import load, generate
model, tokenizer = load("nikimoriOne/MiniCPM5-1B-Base-8bit")
print(generate(model, tokenizer, prompt="The quick brown fox", max_tokens=20))