tomasmcm/zephyr-7b-beta 🔢📝 → 📝

▶️ 188.9K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

chatbot educational english gpt-like language-model research text-generation

About

Source: HuggingFaceH4/zephyr-7b-beta ✦ Quant: TheBloke/zephyr-7B-beta-AWQ ✦ Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series

Example Output

Prompt:

"<|system|>

<|user|>
Tell me about AI
<|assistant|>"

Output

Artificial intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence, such as learning, reasoning, and decision-making. AI technologies are designed to enable machines to process massive amounts of data quickly and accurately, identify patterns, and make informed decisions based on that information.

The use of AI has expanded rapidly in recent years, with applications ranging from virtual assistants like Siri and Alexa to autonomous vehicles and medical diagnostics. In addition to these practical applications, researchers and developers continue to explore the potential of AI to revolutionize a wide range of fields, including education,

Performance Metrics

1.73s Prediction Time

101.81s Total Time

All Input Parameters

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "<|system|>\n</s>\n<|user|>\nTell me about AI</s>\n<|assistant|>",
  "temperature": 0.8,
  "max_new_tokens": 128,
  "presence_penalty": 1
}

Input Parameters

top_k Type: integerDefault: 50: The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 0.95Range: 0.01 - 1: A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string: Text prompt to send to the model.
temperature Type: numberDefault: 0.8Range: 0.01 - 5: The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 128: The maximum number of tokens the model should generate as output.
presence_penalty Type: numberDefault: 1Range: 0.01 - 5: Presence penalty

Output Schema

Output

Type: string

Example Execution Logs

Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:01<00:00,  1.56s/it]
Processed prompts: 100%|██████████| 1/1 [00:01<00:00,  1.56s/it]
Generated 128 tokens in 1.5597317218780518 seconds.

Version Details

Version ID: 961cd6665b811d0c43c0b9488b6dfa85ff5c7bfb875e93b4533e4c7f96c7c526
Version Created: October 29, 2023

Run on Replicate →