Instructions to use Xianjun/PLLaMa-7b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xianjun/PLLaMa-7b-base with Transformers:

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

pipe = pipeline("text-generation", model="Xianjun/PLLaMa-7b-base", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xianjun/PLLaMa-7b-base")
model = AutoModelForCausalLM.from_pretrained("Xianjun/PLLaMa-7b-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xianjun/PLLaMa-7b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xianjun/PLLaMa-7b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xianjun/PLLaMa-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xianjun/PLLaMa-7b-base

SGLang

How to use Xianjun/PLLaMa-7b-base 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 "Xianjun/PLLaMa-7b-base" \
    --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": "Xianjun/PLLaMa-7b-base",
		"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 "Xianjun/PLLaMa-7b-base" \
        --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": "Xianjun/PLLaMa-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xianjun/PLLaMa-7b-base with Docker Model Runner:
```
docker model run hf.co/Xianjun/PLLaMa-7b-base
```

Xianjun commited on Jan 4, 2024

Commit

7ebde84

1 Parent(s): e6ef2d4

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -3

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ This model is optimized for plant science by continuing pertaining on over 1.5 m
 - **Demo [optional]:** [More Information Needed]
 ## How to Get Started with the Model
 from transformers import LlamaTokenizer, LlamaForCausalLM
 import torch
@@ -30,13 +30,18 @@ batch = tokenizer(instruction, return_tensors="pt", add_special_tokens=False).to
 with torch.no_grad():
     output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
     response = tokenizer.decode(output[0], skip_special_tokens=True)
-## Citation [@inproceedings{Yang2024PLLaMaAO,
   title={PLLaMa: An Open-source Large Language Model for Plant Science},
   author={Xianjun Yang and Junfeng Gao and Wenxin Xue and Erik Alexandersson},
   year={2024},
   url={https://api.semanticscholar.org/CorpusID:266741610}
-}]

 - **Demo [optional]:** [More Information Needed]
 ## How to Get Started with the Model
+```python
 from transformers import LlamaTokenizer, LlamaForCausalLM
 import torch
 with torch.no_grad():
     output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
     response = tokenizer.decode(output[0], skip_special_tokens=True)
+```
+## Citation
+If you find PLLaMa useful in your research, please cite the following paper:
+```latex
+@inproceedings{Yang2024PLLaMaAO,
   title={PLLaMa: An Open-source Large Language Model for Plant Science},
   author={Xianjun Yang and Junfeng Gao and Wenxin Xue and Erik Alexandersson},
   year={2024},
   url={https://api.semanticscholar.org/CorpusID:266741610}
+}
+```