Instructions to use chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit 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("chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit")

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
LM Studio

Pi new

How to use chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit 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 "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit"

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 chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit

Run Hermes

hermes

MLX LM

How to use chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

chanderbalaji commited on 10 days ago

Commit

f800a92

verified ·

1 Parent(s): 998dd2b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -21,17 +21,17 @@ This repository contains an MLX-compatible 4-bit version of [`internlm/Intern-S2
 ```bash
 python -m mlx_lm generate \
-  --model chanderbalaji/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
 ```
-For local paths:
 ```bash
-/Users/shikharpant/mlx-vlm-test/bin/python -m mlx_lm generate \
-  --model /Users/shikharpant/models/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
@@ -39,15 +39,15 @@ For local paths:
 ## Local Benchmark
-Benchmarks were run locally with `mlx_lm generate` on Apple Silicon using the MLX environment at `/Users/shikharpant/mlx-vlm-test`.
 ### Basic Generation
 Command:
 ```bash
-/Users/shikharpant/mlx-vlm-test/bin/python -m mlx_lm generate \
-  --model /Users/shikharpant/models/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
@@ -68,8 +68,8 @@ Observed output stats:
 Command:
 ```bash
-/Users/shikharpant/mlx-vlm-test/bin/python -m mlx_lm generate \
-  --model /Users/shikharpant/models/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Do not show reasoning, analysis, thinking process, scratchpad, or <think> text. Output only the final answer. Explain superconductivity in one paragraph." \
   --max-tokens 4096

 ```bash
 python -m mlx_lm generate \
+  --model <namespace>/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
 ```
+For a local checkout:
 ```bash
+python -m mlx_lm generate \
+  --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
 ## Local Benchmark
+Benchmarks were run locally with `mlx_lm generate` on Apple Silicon.
 ### Basic Generation
 Command:
 ```bash
+python -m mlx_lm generate \
+  --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Explain superconductivity in one paragraph." \
   --max-tokens 4096
 Command:
 ```bash
+python -m mlx_lm generate \
+  --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
   --trust-remote-code \
   --prompt "Do not show reasoning, analysis, thinking process, scratchpad, or <think> text. Output only the final answer. Explain superconductivity in one paragraph." \
   --max-tokens 4096