Instructions to use pfnet/plamo-13b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pfnet/plamo-13b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="pfnet/plamo-13b-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-13b-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pfnet/plamo-13b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pfnet/plamo-13b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pfnet/plamo-13b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pfnet/plamo-13b-instruct

SGLang

How to use pfnet/plamo-13b-instruct 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 "pfnet/plamo-13b-instruct" \
    --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": "pfnet/plamo-13b-instruct",
		"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 "pfnet/plamo-13b-instruct" \
        --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": "pfnet/plamo-13b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pfnet/plamo-13b-instruct with Docker Model Runner:
```
docker model run hf.co/pfnet/plamo-13b-instruct
```

torotoki commited on Nov 7, 2023

Commit

0507eed

1 Parent(s): 39ac725

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -19,11 +19,12 @@ This model is released under the Apache License 2.0.
 ## Usage
 Install the required libraries as follows:
 ```sh
->>> python -m pip install numpy sentencepiece torch transformers
 ```
 Execute the following python code:
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained(
     "pfnet/plamo-13b-instruct",
@@ -35,7 +36,9 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
 def completion(prompt: str, max_new_tokens: int = 128) -> str:
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
     generated_ids = model.generate(
@@ -58,7 +61,7 @@ def generate_prompt(messages: list) -> str:
     ]
     roles = {"instruction": "指示", "response": "応答", "input": "入力"}
     for msg in messages:
-        prompt.append(sep + roles[msg["role"]] + ":\n" + msg['content'])
     prompt.append(sep + roles["response"] + ":\n")
     return "".join(prompt)
 ```

 ## Usage
 Install the required libraries as follows:
 ```sh
+>>> python -m pip install numpy sentencepiece torch transformers accelerate
 ```
 Execute the following python code:
 ```python
+import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained(
     "pfnet/plamo-13b-instruct",
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
+```
+```python
 def completion(prompt: str, max_new_tokens: int = 128) -> str:
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
     generated_ids = model.generate(
     ]
     roles = {"instruction": "指示", "response": "応答", "input": "入力"}
     for msg in messages:
+        prompt.append(sep + roles[msg["role"]] + ":\n" + msg["content"])
     prompt.append(sep + roles["response"] + ":\n")
     return "".join(prompt)
 ```