tomasmcm/llama-2-7b-chat-hf 📝🔢 → 📝

▶️ 77 runs 📅 Jul 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
assistant chatbot dialogue language-model natural-language-processing text-generation

About

Source: meta-llama/Llama-2-7b-chat-hf ✦ Quant: TheBloke/Llama-2-7B-Chat-AWQ ✦ Intended for assistant-like chat

Example Output

Prompt:

"[INST] <>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.
<>
What is the future of AI?[/INST]"

Output

Thank you for your question! The future of AI is a topic of much interest and speculation. However, it's important to note that predicting the future of AI is a complex and challenging task, as it depends on various factors such as technological advancements, ethical considerations, and societal needs.
There are several trends and predictions that are commonly discussed in the field of AI, including:

  1. Increased use of AI in industries such as healthcare, finance, and education, as well as in areas such as transportation, energy, and agriculture.
  2. Continued advancements in deep learning and neural networks, which are expected to lead to improved performance in areas such as image and speech recognition, natural language processing, and decision-making.
  3. Growing interest in explainable AI (XAI) and transparency in AI decision-making, as well as the development of ethical frameworks for AI.
  4. Integration of AI with other technologies, such as robotics, quantum computing, and the Internet of Things (IoT), to create more sophisticated and interconnected systems.

Performance Metrics

2.82s Prediction Time
2.75s Total Time
All Input Parameters 
{
  "stop": "[INST]",
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.\n<</SYS>>\nWhat is the future of AI?[/INST]",
  "max_tokens": 256,
  "temperature": 0.8,
  "presence_penalty": 0,
  "frequency_penalty": 0
}
Input Parameters
stop Type: string
List of strings that stop the generation when they are generated. The returned output will not contain the stop strings.
top_k Type: integerDefault: -1
Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.
top_p Type: numberDefault: 0.95Range: 0.01 - 1
Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.
prompt (required) Type: string
Text prompt to send to the model.
max_tokens Type: integerDefault: 128
Maximum number of tokens to generate per output sequence.
temperature Type: numberDefault: 0.8Range: 0.01 - 5
Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.
presence_penalty Type: numberDefault: 0Range: -5 - 5
Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
frequency_penalty Type: numberDefault: 0Range: -5 - 5
Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
Output Schema

Output

Type: string

Example Execution Logs 
Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.76s/it]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.76s/it]
Generated 256 tokens in 2.7582271099090576 seconds.
Version Details
Version ID
44b6420da9e2a7d88aa6e2f05494e300ca7b88c486621dd11d9b9a055a6127ab
Version Created
November 13, 2023
Run on Replicate →