Instructions to use ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit with Transformers:

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

pipe = pipeline("text-generation", model="ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit")
model = AutoModelForCausalLM.from_pretrained("ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit")
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 Settings

vLLM

How to use ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit

SGLang

How to use ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit 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 "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit" \
    --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": "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit",
		"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 "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit" \
        --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": "ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit with Docker Model Runner:
```
docker model run hf.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit
```

Tonya77 commited on Dec 19, 2024

Commit

5f096c4

verified ·

1 Parent(s): 2160aa7

Upload README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ library_name: transformers
 <img src="https://conta-ai-image.oss-cn-shanghai.aliyuncs.com/contaai/logo2.png" alt="ContaLLM" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
-# ContaLLM-Beauty-8B-Instruct
 ContaLLM-Food-Beverage-8B-Instruct is a large Chinese vertical marketing model for the food and beverage industry. You can customize and generate marketing texts according to users' specific marketing needs, product selection, product selection knowledge base, keywords, main recommended selling points, main recommended scenes, hashtags, article types, etc. Use the LLM's capabilities and training on existing high-quality marketing materials to help companies generate diversified, high-quality marketing content and improve marketing conversion rates.
@@ -34,9 +34,9 @@ ContaLLM-Food-Beverage-8B-Instruct is a large Chinese vertical marketing model f
 | **Industry** | **Version** | **Llama 3.1 8B**
 |--------------|-------------|------------------------------------------------------------------------------------------------------------|
-| **Beauty**   | **bf16**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct) |
-| **Beauty**   | **8bit**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit) |
-| **Beauty**   | **4bit**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct-4bit](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-4bit) |
 ## Using the model
@@ -52,7 +52,7 @@ model = AutoModelForCausalLM.from_pretrained("ContaAI/ContaLLM-Food-Beverage-8B-
 ### System Prompt
-The model is a Chinese beauty marketing model, so we use this system prompt by default:
 ```
 system_prompt = '请根据用户提供的营销需求、选品及其他信息写一篇食品饮料行业的营销推文。'
 ```
@@ -64,7 +64,7 @@ Users can enter the required marketing needs according to their own needs, non-r
 |-------------------|-----------------------|------------------------------------------------------------------------------------------------------|
 | **营销需求**          | required              | Fill in your marketing requirements, cannot be blank                                                 |
 | **选品**          | required              | Fill in your product selection, cannot be blank                                                 |
-| **选品知识库**          | required              | Fill in your product selection knowledge base, cannot be blank                                                 |
 | **关键词**           | optional              | Fill in your marketing keywords, or remove this row from the prompt                                  |
 | **标签**            | optional              | Fill in the hashtag, or remove this row from the prompt                                              |
 | **主推卖点**          | optional              | Fill in the main recommended selling points, or remove this row from the prompt |

 <img src="https://conta-ai-image.oss-cn-shanghai.aliyuncs.com/contaai/logo2.png" alt="ContaLLM" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+# ContaLLM-Food-Beverage-8B-Instruct
 ContaLLM-Food-Beverage-8B-Instruct is a large Chinese vertical marketing model for the food and beverage industry. You can customize and generate marketing texts according to users' specific marketing needs, product selection, product selection knowledge base, keywords, main recommended selling points, main recommended scenes, hashtags, article types, etc. Use the LLM's capabilities and training on existing high-quality marketing materials to help companies generate diversified, high-quality marketing content and improve marketing conversion rates.
 | **Industry** | **Version** | **Llama 3.1 8B**
 |--------------|-------------|------------------------------------------------------------------------------------------------------------|
+| **Food And Beverage**   | **bf16**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct) |
+| **Food And Beverage**   | **8bit**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-8bit) |
+| **Food And Beverage**   | **4bit**    | [ContaAI/ContaLLM-Food-Beverage-8B-Instruct-4bit](https://huggingface.co/ContaAI/ContaLLM-Food-Beverage-8B-Instruct-4bit) |
 ## Using the model
 ### System Prompt
+This model is a Chinese marketing model for food and beverage industry, so we use this system prompt by default:
 ```
 system_prompt = '请根据用户提供的营销需求、选品及其他信息写一篇食品饮料行业的营销推文。'
 ```
 |-------------------|-----------------------|------------------------------------------------------------------------------------------------------|
 | **营销需求**          | required              | Fill in your marketing requirements, cannot be blank                                                 |
 | **选品**          | required              | Fill in your product selection, cannot be blank                                                 |
+| **选品知识库**          | required              | Fill in the relevant information/materials about your product, cannot be blank                    |
 | **关键词**           | optional              | Fill in your marketing keywords, or remove this row from the prompt                                  |
 | **标签**            | optional              | Fill in the hashtag, or remove this row from the prompt                                              |
 | **主推卖点**          | optional              | Fill in the main recommended selling points, or remove this row from the prompt |