Instructions to use CEAMFA/palmer-007-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CEAMFA/palmer-007-preview with Transformers:

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

pipe = pipeline("text-generation", model="CEAMFA/palmer-007-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("CEAMFA/palmer-007-preview", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CEAMFA/palmer-007-preview 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 CEAMFA/palmer-007-preview:Q8_0
# Run inference directly in the terminal:
llama cli -hf CEAMFA/palmer-007-preview:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CEAMFA/palmer-007-preview:Q8_0
# Run inference directly in the terminal:
llama cli -hf CEAMFA/palmer-007-preview:Q8_0

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 CEAMFA/palmer-007-preview:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf CEAMFA/palmer-007-preview:Q8_0

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 CEAMFA/palmer-007-preview:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CEAMFA/palmer-007-preview:Q8_0

Use Docker

docker model run hf.co/CEAMFA/palmer-007-preview:Q8_0

LM Studio
Jan

vLLM

How to use CEAMFA/palmer-007-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CEAMFA/palmer-007-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CEAMFA/palmer-007-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CEAMFA/palmer-007-preview:Q8_0

SGLang

How to use CEAMFA/palmer-007-preview 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 "CEAMFA/palmer-007-preview" \
    --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": "CEAMFA/palmer-007-preview",
		"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 "CEAMFA/palmer-007-preview" \
        --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": "CEAMFA/palmer-007-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use CEAMFA/palmer-007-preview with Ollama:
```
ollama run hf.co/CEAMFA/palmer-007-preview:Q8_0
```

Unsloth Studio

How to use CEAMFA/palmer-007-preview with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CEAMFA/palmer-007-preview to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CEAMFA/palmer-007-preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CEAMFA/palmer-007-preview to start chatting

How to use CEAMFA/palmer-007-preview with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CEAMFA/palmer-007-preview:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CEAMFA/palmer-007-preview:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CEAMFA/palmer-007-preview with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CEAMFA/palmer-007-preview:Q8_0

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 CEAMFA/palmer-007-preview:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use CEAMFA/palmer-007-preview with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CEAMFA/palmer-007-preview:Q8_0

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 "CEAMFA/palmer-007-preview:Q8_0" \
  --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"

Docker Model Runner
How to use CEAMFA/palmer-007-preview with Docker Model Runner:
```
docker model run hf.co/CEAMFA/palmer-007-preview:Q8_0
```

Lemonade

How to use CEAMFA/palmer-007-preview with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CEAMFA/palmer-007-preview:Q8_0

Run and chat with the model

lemonade run user.palmer-007-preview-Q8_0

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

palmer-007-preview

This model is an important and more balanced improvement over our previous model. To get early access to this model you need to join to the CEAMFA community by keeping an active ko-fi subscription. You can get more information on how to 👉access this model by clicking here. You can also wait for the Open-Weight Release Date if you don't want to pay for a subscription.

Open-weights release date: 08-09-2026

Note

Temp 0 for best results.
GGUF first, once everything is confirmed to be working out of the box, safetensors goes next.
No issues anymore.

Updates

Doom looping and language switching are core recurrent issues
The model has a known preference to use an unused token. We are still investigating if it is happening due to a mismatch in the tokenizer during the knowledge distillation phase or an issue with gguf, we are working on a fix soon.
It looks like a tokenization issue, after more tests and token switching done the model improved on most benchmarks even more while degrading arc_challenge and significantly degrading ifeval
Currently targetting reviews on specific layers from the model to understand the issue and try to heal it from its distillation "state"
Indeed was a tokenization issue, fix and updates are coming tomorrow 🎉

Benchmarks

  Evaluation                   Falcon-Instruct    Palmer-006    Final model
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━  ━━━━━━━━━━━━━━━━━  ━━━━━━━━━━━━  ━━━━━━━━━━━━━
  ARC Easy norm.                         44.57         44.70          47.69
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  ARC Challenge norm.                    29.01         29.01          30.29
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  WinoGrande                             51.30         50.75          50.83
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  PIQA norm.                             63.98         63.60          63.71
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  BananaBench weighted                   62.62         63.68          63.90
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  BananaBench Elo                         1115          1124           1126
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  Arithmark norm.                        52.80         53.30          56.20
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  HellaSwag norm.                        38.37         38.35          38.50
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  IFEval prompt strict                   60.81        61.55*          61.55
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  IFEval instruction strict              71.34        71.70*          71.22
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  IFEval prompt loose                    66.17        66.73*          64.51
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  IFEval instruction loose               76.14        75.66*          74.10
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  Manual exact/format                     3/16         4/16*           5/16
 ───────────────────────────  ─────────────────  ────────────  ─────────────
  Seven-benchmark mean                   48.95         49.06          50.16

Details

TextIntent is our internal metric for measured usefulness, behaviour and instruction-following capabilities on small language models. Llama.cpp and Ollama compatible early mid-training checkpoint with significant improvements over palmer-006.

Downloads last month: 6

GGUF

Model size

91.1M params

Architecture

falcon-h1

Hardware compatibility

8-bit

Model tree for CEAMFA/palmer-007-preview

Base model

appvoid/palmer-007-preview

Quantized

(1)

this model