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

Libraries

How to use Writer/InstructPalmyra-20b with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Writer/InstructPalmyra-20b")
model = AutoModelForCausalLM.from_pretrained("Writer/InstructPalmyra-20b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Writer/InstructPalmyra-20b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Writer/InstructPalmyra-20b

SGLang

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

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

kiranr commited on Aug 31, 2023

Commit

d2f3e5e

1 Parent(s): da419fa

Update handler.py

Browse files

Files changed (1) hide show

handler.py +5 -0

handler.py CHANGED Viewed

@@ -2,6 +2,10 @@ import torch
 from typing import Dict, List, Any
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 format_input = (
     "Below is an instruction that describes a task. "
     "Write a response that appropriately completes the request.\n\n"
@@ -23,6 +27,7 @@ class EndpointHandler:
             "text-generation",
             model=model,
             tokenizer=tokenizer,
             max_length=256,
         )

 from typing import Dict, List, Any
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+# check for GPU
+device = 0 if torch.cuda.is_available() else -1
 format_input = (
     "Below is an instruction that describes a task. "
     "Write a response that appropriately completes the request.\n\n"
             "text-generation",
             model=model,
             tokenizer=tokenizer,
+            device=device,
             max_length=256,
         )