Instructions to use PygmalionAI/pygmalion-1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PygmalionAI/pygmalion-1.3b with Transformers:

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

pipe = pipeline("text-generation", model="PygmalionAI/pygmalion-1.3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PygmalionAI/pygmalion-1.3b")
model = AutoModelForCausalLM.from_pretrained("PygmalionAI/pygmalion-1.3b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PygmalionAI/pygmalion-1.3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PygmalionAI/pygmalion-1.3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PygmalionAI/pygmalion-1.3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PygmalionAI/pygmalion-1.3b

SGLang

How to use PygmalionAI/pygmalion-1.3b 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 "PygmalionAI/pygmalion-1.3b" \
    --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": "PygmalionAI/pygmalion-1.3b",
		"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 "PygmalionAI/pygmalion-1.3b" \
        --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": "PygmalionAI/pygmalion-1.3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PygmalionAI/pygmalion-1.3b with Docker Model Runner:
```
docker model run hf.co/PygmalionAI/pygmalion-1.3b
```

Add default chat template to tokenizer_config.json

by Xenova HF Staff - opened Feb 16, 2024

base: refs/heads/main

←

from: refs/pr/8

Discussion Files changed

-2

Files changed (1) hide show

tokenizer_config.json +3 -2

tokenizer_config.json CHANGED Viewed

@@ -5,5 +5,6 @@
   "name_or_path": "EleutherAI/gpt-neox-20b",
   "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
   "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
-}

   "name_or_path": "EleutherAI/gpt-neox-20b",
   "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
   "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
+}