You can deploy this model and start earning money today!

ContaAI/
ContaLLM-Fashion-7B-Instruct-4bit

Name: ContaLLM-Fashion-7B-Instruct-4bit
Rating: 2.5 (10 reviews)

Views

No views yet

ContaLLM-Fashion-7B-Instruct

ContaLLM-Fashion-7B-Instruct is a large-scale Chinese vertical marketing mode focusing on the fashion industry. You can customize and generate marketing texts according to users' specific marketing needs, brand, selection, content type, article length, topic, selling point, hashtag, scene, 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.

Model description

Model type: A model trained on a mix of publicly available, synthetic and human-annotated datasets.
Language(s) (NLP): Primarily Chinese
Industry: Fashion Makeup Industry Marketing
License: apache-2.0
Finetuned from model: Qwen/Qwen2.5-7B-Instruct

Model Stage

Industry	Version	Qwen 2.5 7B
Fashion	bf16	ContaAI/ContaLLM-Fashion-7B-Instruct
Fashion	8bit	ContaAI/ContaLLM-Fashion-7B-Instruct-8bit
Fashion	4bit	ContaAI/ContaLLM-Fashion-7B-Instruct-4bit

Using the model

Loading with HuggingFace

To load the model with HuggingFace, use the following snippet:

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("ContaAI/ContaLLM-Fashion-7B-Instruct-4bit")

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和其他信息写一篇时尚行业的营销推文。'

User Prompt

Users can enter the required marketing needs according to their own needs, non-required including brand, product selection, content type, topics, selling point, hashtag, scenes, content length, which content length has three specifications, respectively, shorter, medium, longer. The details are as follows:

Parameter name	Required	Meaning and optional range
营销需求	required	Fill in your marketing requirements, cannot be blank
品牌	optional	Fill in your marketing brand, or remove this row from the prompt
选品	optional	Fill in your product selection, or remove this row from the prompt
内容类型	optional	Fill in the article type, or remove this row from the prompt
内容长度	optional	choices=['较长', '中等', '较短'], choose what you need, or remove this row from the prompt
话题	optional	Fill in your marketing topic, or remove this row from the prompt
卖点	optional	Fill in the selling point for your marketing needs, or remove this row from the prompt
标签	optional	Fill in the hashtag, or remove this row from the prompt
场景	optional	Fill in the scenes for your marketing needs, or remove this row from the prompt

Example:

user_prompt = """营销需求：秋冬大包包推荐
品牌：Celine
选品：CELINE托特包
内容类型：产品种草与测评
内容长度：较短
话题：CELINE托特包、秋冬大包包、托特包用途
卖点：慵懒设计、大容量、新款限定设计
标签：CELINE、托特包、新品
场景：日常通勤、妈咪包使用、秋冬搭配"""

Use example (with template)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "ContaAI/ContaLLM-Fashion-7B-Instruct-4bit"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

system_prompt = '请根据用户提供的营销需求和其他信息写一篇时尚行业的营销推文。'

user_prompt = """营销需求：秋冬大包包推荐
品牌：Celine
选品：CELINE托特包
内容类型：产品种草与测评
内容长度：较短
话题：CELINE托特包、秋冬大包包、托特包用途
卖点：慵懒设计、大容量、新款限定设计
标签：CELINE、托特包、新品
场景：日常通勤、妈咪包使用、秋冬搭配"""

prompt_template = '''<|im_start|>system
{}<|im_end|>
<|im_start|>user
{}<|im_end|>
<|im_start|>assistant
'''

prompt = prompt_template.format(system_prompt, user_prompt)

tokenized_message = tokenizer(
  prompt,
  max_length=1024,
  return_tensors="pt",
  add_special_tokens=False
)

response_token_ids= model.generate(
  **tokenized_message,
  max_new_tokens=1024,
  do_sample=True,
  top_p=1.0,
  temperature=0.5,
  min_length=None,
  use_cache=True,
  top_k=50,
  repetition_penalty=1.2,
  length_penalty=1,
)

generated_tokens = response_token_ids[0, tokenized_message['input_ids'].shape[-1]:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)

Bias, Risks, and Limitations

The ContaLLM models implemented safety techniques during data generation and training, but they are not deployed automatically with in-the-loop filtering of responses like ChatGPT during inference, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Qwen2.5 models, however it is likely to have included a mix of Web data and technical sources like books and code. The use of the models is at your own risk. You may need to monitor the outputs of the model and take appropriate actions such as content filtering if necessary.

License and use

All Qwen 2.5 ContaAI models are released under Qwen's Qwen 2.5 Community License Agreement.