Instructions to use Infinirc/Llama-3.2-Infinirc-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infinirc/Llama-3.2-Infinirc-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Infinirc/Llama-3.2-Infinirc-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Infinirc/Llama-3.2-Infinirc-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Infinirc/Llama-3.2-Infinirc-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Infinirc/Llama-3.2-Infinirc-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infinirc/Llama-3.2-Infinirc-3B-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": "Infinirc/Llama-3.2-Infinirc-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Infinirc/Llama-3.2-Infinirc-3B-Instruct

SGLang

How to use Infinirc/Llama-3.2-Infinirc-3B-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 "Infinirc/Llama-3.2-Infinirc-3B-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": "Infinirc/Llama-3.2-Infinirc-3B-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 "Infinirc/Llama-3.2-Infinirc-3B-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": "Infinirc/Llama-3.2-Infinirc-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Infinirc/Llama-3.2-Infinirc-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Infinirc/Llama-3.2-Infinirc-3B-Instruct
```

RickyChen-Infinirc commited on Dec 12, 2024

Commit

2cc72d0

verified ·

1 Parent(s): fed63bd

Update README.md

Browse files

Files changed (1) hide show

README.md +50 -3

README.md CHANGED Viewed

@@ -1,3 +1,50 @@
----
-license: llama3.2
----

+---
+license: llama3.2
+language:
+- zh
+- en
+library_name: transformers
+tags:
+- zhtw
+---
+# Infinirc/Llama-3.2-Infinirc-3B-Instruct
+## 模型詳情
+**開發者**：陳昭儒[Infinirc.com](https://infinirc.com)
+**模型版本**：1.0
+**訓練數據**：采用與台灣文化相關的資料集，包括、對話、台灣新聞、文學作品、網路文章、程式、醫療問題、英文對話等。
+## 目的和用途
+Llama-3.2-Infinirc-11B-Vision-Instruct模型是專門為了更好地理解和生成與台灣文化相關的文本而設計和微調的。目標是提供一個能夠捕捉台灣特有文化元素和語言習慣的強大語言模型，適用於文本生成、自動回答等多種應用。
+## 模型架構
+**基礎模型**：meta-llama/Llama-3.2-3B-Instruct
+## Evaluation
+|  Tasks   |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|----------|------:|------|-----:|--------|---|-----:|---|-----:|
+|arc_easy  |      1|none  |     0|acc     |↑  |0.7273|±  |0.0091|
+|          |       |none  |     0|acc_norm|↑  |0.6595|±  |0.0097|
+|hellaswag |      1|none  |     0|acc     |↑  |0.5087|±  |0.0050|
+|          |       |none  |     0|acc_norm|↑  |0.6963|±  |0.0046|
+|piqa      |      1|none  |     0|acc     |↑  |0.7432|±  |0.0102|
+|          |       |none  |     0|acc_norm|↑  |0.7394|±  |0.0102|
+|winogrande|      1|none  |     0|acc     |↑  |0.6496|±  |0.0134|
+## 使用和限制
+請遵守許可證限制。
+## 風險與倫理考量
+使用本模型時應注意確保生成的內容不包含歧視性或有害信息。模型的開發和使用應遵循倫理準則和社會責任。
+## 聯絡方式
+如有任何問題或需要進一步的信息，請透過下方聯絡方式與我們團隊聯繫：
+Email: [ricky@infinirc.com](mailto:ricky@infinirc.com)
+網站: [https://infinirc.com](https://infinirc.com)