Instructions to use netprojects/granite-switch-4.1-8b-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netprojects/granite-switch-4.1-8b-mlx-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("netprojects/granite-switch-4.1-8b-mlx-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 netprojects/granite-switch-4.1-8b-mlx-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 "netprojects/granite-switch-4.1-8b-mlx-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": "netprojects/granite-switch-4.1-8b-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use netprojects/granite-switch-4.1-8b-mlx-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 "netprojects/granite-switch-4.1-8b-mlx-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "netprojects/granite-switch-4.1-8b-mlx-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "netprojects/granite-switch-4.1-8b-mlx-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use netprojects/granite-switch-4.1-8b-mlx-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 "netprojects/granite-switch-4.1-8b-mlx-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 netprojects/granite-switch-4.1-8b-mlx-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use netprojects/granite-switch-4.1-8b-mlx-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 "netprojects/granite-switch-4.1-8b-mlx-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 "netprojects/granite-switch-4.1-8b-mlx-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"

Paris99 commited on 16 days ago

Commit

0d87e76

verified ·

1 Parent(s): ebbaf9f

Rebuild from Granite Switch 4.1.1

Browse files

Files changed (4) hide show

BUILD.md +3 -2
io_configs/decision/io.yaml +2 -2
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

BUILD.md CHANGED Viewed

@@ -17,7 +17,7 @@ Total adapters: **2**
 | # | Name | Technology | Control Token | Token ID | Rank | Alpha | Target Modules | Source |
 |---|------|------------|---------------|----------|------|-------|----------------|--------|
 | 1 | guardian-core | alora | `<\|guardian-core\|>` | 100352 | 16 | 64 | k_proj, o_proj, q_proj, v_proj | ibm-granite/granitelib-guardian-r1.0 |
-| 2 | decision | alora | `<\|decision\|>` | 100353 | 64 | 128 | down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj | alora |
 ## Composition Details
@@ -25,6 +25,7 @@ Total adapters: **2**
 - composed_param_count: 8,776,400,896
 - Param delta: +4.72%
 - compose_settings:
   - include_adapters:
     - "guardian-core"
     - "decision"
@@ -33,4 +34,4 @@ Total adapters: **2**
     - 14711
   - target_model: "granite-4.1-8b"
 - adapter_sources:
-  - "ibm-granite/granitelib-guardian-r1.0": "1a1a488a51d0d5307e30e5b3c1e66b4a5237d18a"

 | # | Name | Technology | Control Token | Token ID | Rank | Alpha | Target Modules | Source |
 |---|------|------------|---------------|----------|------|-------|----------------|--------|
 | 1 | guardian-core | alora | `<\|guardian-core\|>` | 100352 | 16 | 64 | k_proj, o_proj, q_proj, v_proj | ibm-granite/granitelib-guardian-r1.0 |
+| 2 | decision | alora | `<\|decision\|>` | 100353 | 64 | 64 | down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj | decision-4.1.1 |
 ## Composition Details
 - composed_param_count: 8,776,400,896
 - Param delta: +4.72%
 - compose_settings:
+  - technology_filter: "alora"
   - include_adapters:
     - "guardian-core"
     - "decision"
     - 14711
   - target_model: "granite-4.1-8b"
 - adapter_sources:
+  - "ibm-granite/granitelib-guardian-r1.0": "5802b88ef1f9a71e7a33c9025a36b81f2671e58d"

io_configs/decision/io.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
-# Decider / decision engine (aLoRA, r=64, granite-4.1-30b).
-# Prompt layout and readout are those of decide_alora.py: a fixed system prompt, a first user
 # turn with the state (runs on frozen base KV), then a second user turn opening with the
 # "### DECISION" invocation marker plus Question / Options as "A: ...", "B: ...",
 # add_generation_prompt=True; the answer is the first assistant token, read as a softmax over

+# Decider / decision engine (aLoRA, r=64, granite-4.1-8b).
+# Prompt layout and readout are those of the aLoRA example in the README: a fixed system prompt, a first user
 # turn with the state (runs on frozen base KV), then a second user turn opening with the
 # "### DECISION" invocation marker plus Question / Options as "A: ...", "B: ...",
 # add_generation_prompt=True; the answer is the first assistant token, read as a softmax over

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f99fc0da256e8dd623d7a9dd9120a91bffb71f765cd655269aa3080f6c465c
 size 5366329691

 version https://git-lfs.github.com/spec/v1
+oid sha256:49cc0adc1e53325dd38c16acfa0fef88fab04ca0e3ce62317b42c4475130a8a2
 size 5366329691

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a31d418a147e0c69acbed318ff9d5a32d9fd28bc8d4d7c06cf6e8fa7fbdf58
 size 4033304869

 version https://git-lfs.github.com/spec/v1
+oid sha256:57399ffb584899bc450f1d8c22ad6cb0cb33cc0ec472ce09d2f19a71d908cdea
 size 4033304869