tomasmcm/una-cybertron-7b-v2 📝🔢 → 📝

▶️ 88 runs 📅 Dec 2023 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License
joke-generation logic mathematics mistralai poetry question-answering reasoning story-writing text-generation uniform-neural-alignment

About

Source: fblgit/una-cybertron-7b-v2-bf16 ✦ Quant: TheBloke/una-cybertron-7B-v2-AWQ ✦ A 7B MistralAI based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets

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

Photosynthesis is a remarkable natural process carried out by plants and certain organisms, which enables them to turn sunlight into energy. This life-sustaining process happens within specially designed cells called chloroplasts.

In simple terms, photosynthesis involves three main steps:

  1. Absorption: During this step, plants absorb sunlight using their leaves, which contain chlorophyll (green pigment) that acts as a light absorber. Chlorophyll takes in light energy, filtering out unwanted wavelengths.

  2. Conversion: Next,

Performance Metrics

2.94s Prediction Time
4.39s 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 [00:02<00:00,  2.84s/it]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.85s/it]
Generated 128 tokens in 2.848870038986206 seconds.
Version Details
Version ID
daeabf5ac9c1311cd6ea66ac414a56f8829cce17c429b0c7c8183aaba0b3d3d9
Version Created
December 6, 2023
Run on Replicate →