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
```

kiranr commited on Aug 25, 2023

Commit

2959013

1 Parent(s): 243f824

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -13,8 +13,7 @@ language:
 ```py
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers import TextStreamer
 model_name = "Writer/palmyra-20b-chat"
@@ -52,6 +51,9 @@ if "token_type_ids" in model_inputs:
     del model_inputs["token_type_ids"]
 all_inputs = {**model_inputs, **gen_conf}
-_ = model.generate(**all_inputs, streamer=streamer)
 ```

 ```py
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
 model_name = "Writer/palmyra-20b-chat"
     del model_inputs["token_type_ids"]
 all_inputs = {**model_inputs, **gen_conf}
+output = model.generate(**all_inputs, streamer=streamer)
+print("-"*20)
+print(output)
 ```