Instructions to use appvoid/palmer-005 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use appvoid/palmer-005 with Transformers:

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

pipe = pipeline("text-generation", model="appvoid/palmer-005")
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("appvoid/palmer-005")
model = AutoModelForCausalLM.from_pretrained("appvoid/palmer-005", 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

vLLM

How to use appvoid/palmer-005 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/palmer-005"
# 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-005",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/appvoid/palmer-005

SGLang

How to use appvoid/palmer-005 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-005" \
    --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-005",
		"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-005" \
        --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-005",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use appvoid/palmer-005 with Docker Model Runner:
```
docker model run hf.co/appvoid/palmer-005
```

appvoid commited on May 14

Commit

7291804

verified ·

1 Parent(s): 73ef7de

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -0

README.md CHANGED Viewed

@@ -53,6 +53,15 @@ private: true
 In this repository, we propose the next iteration of `palmer`, a new family of small language models trained with better foundational models, better data but same tasks: Text rewriting, paraphrasing, tone transfer, grammar-style editing, and instruction-following text transformations. With only 90m parameters, this model is perfect for experiments on small SBCs and low-power devices. Now with `lfm` and `falcon-h1` as main as the base architectures for improvements.
 #### prompt
 There is no prompt intentionally set.

 In this repository, we propose the next iteration of `palmer`, a new family of small language models trained with better foundational models, better data but same tasks: Text rewriting, paraphrasing, tone transfer, grammar-style editing, and instruction-following text transformations. With only 90m parameters, this model is perfect for experiments on small SBCs and low-power devices. Now with `lfm` and `falcon-h1` as main as the base architectures for improvements.
+> Our custom evaluation consists of 100 text-editing tasks where the model has to modify a diversity of texts in different ways. All models were evaluated using `q8_0` gguf quantization.
+| Model | Avg | Emb | String | Token | Rule | Exact | Strict | Flagged | Params |
+|---:|---|---:|---:|---:|---:|---:|---:|---:|---|
+| `nano` | 84.70 | 95.81 | 81.12 | 78.22 | 87.57 | 39/100 | 68/100 | 19/100 | 90m |
+| `lfm2.5` | 80.97 | 94.45 | 77.43 | 72.62 | 83.91 | 30/100 | 55/100 | 23/100 | 1.2b |
+| `lfm2` | 72.04 | 93.19 | 62.00 | 56.22 | 75.35 | 21/100 | 40/100 | 35/100 | 700m |
+| `lfm2.5` | 67.47 | 91.76 | 56.90 | 46.58 | 72.27 | 13/100 | 26/100 | 38/100 | 350m |
 #### prompt
 There is no prompt intentionally set.