Instructions to use appvoid/palmer-006 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use appvoid/palmer-006 with Transformers:

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

pipe = pipeline("text-generation", model="appvoid/palmer-006")

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

tokenizer = AutoTokenizer.from_pretrained("appvoid/palmer-006")
model = AutoModelForCausalLM.from_pretrained("appvoid/palmer-006", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use appvoid/palmer-006 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 appvoid/palmer-006
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-006

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf appvoid/palmer-006
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-006

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf appvoid/palmer-006
# Run inference directly in the terminal:
./build/bin/llama cli -hf appvoid/palmer-006

Use Docker

docker model run hf.co/appvoid/palmer-006

Llama new
LM Studio
Jan

vLLM

How to use appvoid/palmer-006 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/palmer-006"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/appvoid/palmer-006

SGLang

How to use appvoid/palmer-006 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 "appvoid/palmer-006" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "appvoid/palmer-006" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use appvoid/palmer-006 with Ollama:
```
ollama run hf.co/appvoid/palmer-006
```
Unsloth Desktop
Docker Model Runner
How to use appvoid/palmer-006 with Docker Model Runner:
```
docker model run hf.co/appvoid/palmer-006
```

Lemonade

How to use appvoid/palmer-006 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull appvoid/palmer-006

Run and chat with the model

lemonade run user.palmer-006-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

appvoid commited on Jul 27

Commit

a97bb6b

verified ·

1 Parent(s): 01bb359

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -457,7 +457,7 @@ We celebrate three years of experiments with `palmer-006`, our flagship and extr
   alt="Palmer 006 benchmark comparison"
 />
-We first fine-tuned the base model on a diverse set of highly curated data points. We then “palmerized” it by merging models, followed by another light fine-tuning round. Finally, we adjusted Mamba for maximum token speed. With only 90M parameters, this turned the model into a competitive baseline against models above 125M parameters.
 > As seen in the benchmark, we are getting closer to the performance of bigger models with our current technique, even on models of this size. Note: We used `acc_norm` whenever available.
@@ -483,6 +483,7 @@ Open research, education, hobby use, modification, and redistribution are permit
 - the new logo represents palmer's eye, pointing how small this new model is
 - palmer models still exists to some extent due to inspiration from Karpathy's idea of a self-contained "cognitive core".
 </div>
 </body>

   alt="Palmer 006 benchmark comparison"
 />
+We first lightly fine-tuned the base model on a diverse set of highly curated data points. We then “palmerized” it by merging models, followed by another light fine-tuning round. Finally, we adjusted Mamba for maximum token speed. With only 90M parameters, this turned the model into a competitive baseline against models above 125M parameters.
 > As seen in the benchmark, we are getting closer to the performance of bigger models with our current technique, even on models of this size. Note: We used `acc_norm` whenever available.
 - the new logo represents palmer's eye, pointing how small this new model is
 - palmer models still exists to some extent due to inspiration from Karpathy's idea of a self-contained "cognitive core".
+- we just like light finetuning because we prefer starting "real" experiments with the strongest baseline possible
 </div>
 </body>