tomasmcm/metamath-cybertron-starling 📝🔢 → 📝

▶️ 185 runs 📅 Dec 2023 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License

chatbot humor language-model poetry question-answering storytelling text-generation virtual-assistant

About

Source: Q-bert/MetaMath-Cybertron-Starling ✦ Quant: TheBloke/MetaMath-Cybertron-Starling-AWQ ✦ Merge Q-bert/MetaMath-Cybertron and berkeley-nest/Starling-LM-7B-alpha using slerp merge

Example Output

Prompt:

<|im_start|>system

You are a helpful assistant chatbot.
You answer questions.
You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>
<|im_start|>user
Explain metabolism<|im_end|>
<|im_start|>assistant

Output

Metabolism is the set of chemical reactions that happen within a living organism in order to maintain life. These reactions occur at the cellular level and are responsible for the conversion of food into energy, as well as the growth, reproduction, and other essential processes.

There are two main types of metabolism:

Anabolism: This is the process of building complex molecules from simpler ones using the energy provided by food. It is also known as "synthesis" or "biosynthesis." Anabolism is the process by which cells grow and repair themselves.

Performance Metrics

2.46s Prediction Time

95.43s Total Time

All Input Parameters

{
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "<|im_start|>system\n- You are a helpful assistant chatbot.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>\n<|im_start|>user\nExplain metabolism<|im_end|>\n<|im_start|>assistant",
  "max_tokens": 128,
  "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,  2.37s/it]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.37s/it]
Generated 128 tokens in 2.3741703033447266 seconds.

Version Details

Version ID: 194cbf3864ad03f8df95aa682719a4ec2cd3540f7a6f59142d954d50d3a30b3f
Version Created: December 10, 2023

Run on Replicate →