lucataco/qwen1.5-7b 🔢📝 → 📝
About
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
Example Output
"Give me a short introduction to large language model."
Output
A large language model, also known as a neural network-based language model or a deep learning language model, is a type of artificial intelligence system designed to process and generate human-like language. These models are trained on massive amounts of text data, such as books, articles, and web pages, to learn the patterns, structures, and relationships within language.
The primary objective of large language models is to understand the context and generate coherent, semantically meaningful responses to a wide range of inputs, such as questions, prompts, or even entire paragraphs. They have become increasingly sophisticated in recent years, thanks to advancements in deep learning techniques and the availability of large datasets.
These models can be used for various applications, including language translation, chatbots, content generation, summarization, and even creative writing. They have raised concerns about privacy, ethics, and the potential misuse of AI-generated content, but they also offer significant potential for improving communication and automating language-related tasks.
Performance Metrics
All Input Parameters
{
"top_k": 1,
"top_p": 1,
"prompt": "Give me a short introduction to large language model.",
"temperature": 1,
"system_prompt": "You are a helpful assistant.",
"max_new_tokens": 512,
"repetition_penalty": 1
}
Input Parameters
- seed
- The seed for the random number generator
- top_k
- When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens.
- top_p
- When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.
- prompt
- Input prompt
- temperature
- Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
- system_prompt
- System prompt
- max_new_tokens
- The maximum number of tokens to generate
- repetition_penalty
- Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
Output Schema
Output
Example Execution Logs
Using seed:792983711 The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results. Setting `pad_token_id` to `eos_token_id`:151645 for open-end generation.
Version Details
- Version ID
f85bec5b21ba0860e0f200be6ef5af9d5a65b974b9f99e36eb036d21eab884de- Version Created
- February 6, 2024