tomasmcm/go-bruins-v2 📝🔢 → 📝

▶️ 222 runs 📅 Dec 2023 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License

direct-preference-optimization english fine-tuning language-understanding nlp sentiment-analysis text-generation

About

Source: rwitz/go-bruins-v2 ✦ Quant: TheBloke/go-bruins-v2-AWQ ✦ Designed to push the boundaries of NLP applications, offering unparalleled performance in generating human-like text

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 photosynthesis<|im_end|>
<|im_start|>assistant

Output

During photosynthesis, green plants and certain other organisms convert sunlight into chemical energy through a process that uses water and carbon dioxide from the environment. This chemical energy is stored in the form of glucose, which can be used as a source of fuel by the plant. The overall equation for photosynthesis is:

6CO₂ + 6H₂O + light energy → C₆H₁₂O₆ + 6O₂

In this equation, 6 molecules of carbon dioxide (CO₂) combine with 6 molecules of water (

Performance Metrics

4.05s Prediction Time

31.52s 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 photosynthesis<|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 [00:03<00:00,  3.97s/it]
Processed prompts: 100%|██████████| 1/1 [00:03<00:00,  3.97s/it]
Generated 128 tokens in 3.9865102767944336 seconds.

Version Details

Version ID: a201caf3e3847babfb7ebfe8d01fe8e4a3a5bce04e044ff793cc05fceed1b198
Version Created: December 10, 2023

Run on Replicate →