Instructions to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Transformers:

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

pipe = pipeline("text-generation", model="Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a")
model = AutoModelForCausalLM.from_pretrained("Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Use Docker

docker model run hf.co/Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

LM Studio
Jan

vLLM

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

SGLang

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a 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 "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a" \
    --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": "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a",
		"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 "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a" \
        --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": "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Ollama:
```
ollama run hf.co/Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
```
Unsloth Desktop

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Docker Model Runner:
```
docker model run hf.co/Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M
```

Lemonade

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Run and chat with the model

lemonade run user.Pallete-2.6B-RP-Reasoning-2609-v1a-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

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 Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M

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 "Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Palette: New Series of Small Model Creative Distills With Only The Best Teachers!

One of the two builds for the future Pallete-2.6B-RP-Reasoning-2609-v1.

Teacher model which was used to generate the dataset: GLM 5.3 Flash.

Testing different unique approaches

The A and B stand for different approaches, not different scale of cooking, both baked properly but with slightly different recipes.

Additional information to anybody wants to financially support me and my activity(I already began saving up for the next project):

Solana | EeQMECL51LHoKnpFybjSafpgjBrHyzUcWuo6Z6NEQLHc

Ethereum | 0xb95fe88e4de47fcd120f66a1a27e1e3ee6b8e157

Boosty(Non-Crypto, most convenient) | https://boosty.to/Indexnusrefather

Downloads last month: 622

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Indexnusrefather/Pallete-2.6B-RP-Reasoning-2609-v1a

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

(61)

this model

Quantizations

2 models