Instructions to use Writer/palmyra-20b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Writer/palmyra-20b-chat with Transformers:

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

pipe = pipeline("text-generation", model="Writer/palmyra-20b-chat")

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

tokenizer = AutoTokenizer.from_pretrained("Writer/palmyra-20b-chat")
model = AutoModelForCausalLM.from_pretrained("Writer/palmyra-20b-chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Writer/palmyra-20b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Writer/palmyra-20b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Writer/palmyra-20b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Writer/palmyra-20b-chat

SGLang

How to use Writer/palmyra-20b-chat 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 "Writer/palmyra-20b-chat" \
    --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": "Writer/palmyra-20b-chat",
		"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 "Writer/palmyra-20b-chat" \
        --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": "Writer/palmyra-20b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Writer/palmyra-20b-chat with Docker Model Runner:
```
docker model run hf.co/Writer/palmyra-20b-chat
```

palmyra-20b-chat

Commit History

Feb 16, 2025

22:02
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
d51af7d

Aug 17, 2024

23:50
Update README.md

wassemgtk

Verified signature
78d99d0

May 17, 2024

14:52
Update README.md

wassemgtk

Verified signature
e1a3a85

Dec 21, 2023

17:26
Adding Evaluation Results (#1)⁠

kiranr +1: leaderboard-pr-bot

40d794f

Aug 28, 2023

17:46
Update README.md

wassemgtk

3b7442b

Aug 25, 2023

17:40
Update README.md

kiranr

2959013
17:39
Create README.md

kiranr

243f824
17:35
Update config.json

kiranr

aa2d2d7
17:34
Upload tokenizer

kiranr

2a4feff
17:34
Upload model

kiranr

b942ee7

Aug 23, 2023

18:29
initial commit

kiranr

f327831

Commit History

Feb 16, 2025

Adding `safetensors` variant of this model⁠

Aug 17, 2024

Update README.md

May 17, 2024

Update README.md

Dec 21, 2023

Adding Evaluation Results (#1)⁠

Aug 28, 2023

Update README.md

Aug 25, 2023

Update README.md

Create README.md

Update config.json

Upload tokenizer

Upload model

Aug 23, 2023

initial commit