How to use from
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-003
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-003
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf appvoid/palmer-003
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-003
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-003
# Run inference directly in the terminal:
./build/bin/llama cli -hf appvoid/palmer-003
Use Docker
docker model run hf.co/appvoid/palmer-003
Quick Links

palmer-003 logo

palmer-003 is appvoid's lastest effort into creating the best small, general language model possible.

Query: Your instruction

Answer:

Evaluation

  Model         MMLU     ARC-C    OBQA   HellaSwag  PIQA  Winogrande Average  Params
tinyllama-3t | 0.2577 | 0.3029 | 0.3600 | 0.5935 | 0.7329 | 0.5959 | 0.4738 | 1.1B  |
zyte-1b	     | 0.2397 | 0.3353 | 0.3700 | 0.6086 | 0.7541 | 0.5998 | 0.4845 | 1.1B  |
palmer-003   | 0.2523 | 0.3439 | 0.3740 | 0.6208 | 0.7524 | 0.6590 | 0.5004 | 1.1B  |
qwen-1.8b    | 0.4536 | 0.3490 | 0.3320 | 0.5876 | 0.7307 | 0.5896 | 0.5070 | 1.8B  |

You can support me through kofi.

Downloads last month
1,283
Safetensors
Model size
1B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for appvoid/palmer-003

Finetunes
12 models
Merges
69 models
Quantizations
3 models