Instructions to use appvoid/palmer-002-2401 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use appvoid/palmer-002-2401 with Transformers:

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

pipe = pipeline("text-generation", model="appvoid/palmer-002-2401")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("appvoid/palmer-002-2401")
model = AutoModelForCausalLM.from_pretrained("appvoid/palmer-002-2401")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use appvoid/palmer-002-2401 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/palmer-002-2401"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-002-2401",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/appvoid/palmer-002-2401

SGLang

How to use appvoid/palmer-002-2401 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-002-2401" \
    --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": "appvoid/palmer-002-2401",
		"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 "appvoid/palmer-002-2401" \
        --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": "appvoid/palmer-002-2401",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use appvoid/palmer-002-2401 with Docker Model Runner:
```
docker model run hf.co/appvoid/palmer-002-2401
```

palmer

a better base model

This is a small improvement over a (now un-prompted zyte) tinyllama model

evaluation 🧪

note that this is a zero-shot setting as opposite to open llm leaderboard's few-shot evals

   model           ARC-C     OBQA   HellaSwag  PIQA  Winogrande Average
tinyllama        | 0.3029 | 0.3600 | 0.5935 | 0.7329 | 0.5959 | 0.5170 |
palmer-002       | 0.3242 | 0.3700 | 0.5956 | 0.7345 | 0.5888 | 0.5226 |
palmer-002-2401  | 0.3294 | 0.3700 | 0.5950 | 0.7399 | 0.5896 | 0.5247 | (this)
babbage-002      | 0.3285 | 0.3620 | 0.6380 | 0.7606 | 0.6085 | 0.5395 |

training 🦾

Training took ~1 A100 gpu hour. It was trained on 50,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.

prompt 📝

no prompt 🚀

Downloads last month: 10

appvoid
/

palmer-002-2401

palmer

a better base model

evaluation 🧪

training 🦾

prompt 📝

Dataset used to train appvoid/palmer-002-2401