tomasmcm/neuronovo-7b-v0.3 📝🔢 → 📝

▶️ 42 runs 📅 Jan 2024 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License
dialogue interactive-scenarios language-model natural-language-processing text-generation

About

Source: Neuronovo/neuronovo-7B-v0.3 ✦ Quant: TheBloke/neuronovo-7B-v0.3-AWQ ✦ Neuronovo/neuronovo-7B-v0.3 model represents an advanced and fine-tuned version of a large language model, initially based on CultriX/MistralTrix-v1.

Example Output

Prompt:

"<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Give me a tasty recipe for some noodle dish.<|im_end|>
<|im_start|>assistant"

Output

Here is a delicious and easy-to-make recipe for Chicken Pad Thai, which is a popular Thai noodle dish. It's perfect for lunch or dinner and serves around 4 people.

Ingredients:

  • 8 oz (225g) rice noodles
  • 2 tablespoons vegetable oil
  • 1 large egg, beaten
  • 1 lb (450g) boneless chicken breasts or thighs, thinly sliced
  • 2 tablespoons fish sauce
  • 2 tablespoons soy sauce
  • 1 tablespoon rice vinegar
  • 1 tablespoon sugar (or to taste)
  • 1 tablespoon sriracha sauce (or to taste)
  • 1 bell pepper (any color), sliced into thin strips
  • 1 small carrot, julienned or cut into thin strips
  • 1 cup (100g) bean sprouts
  • 3 scallions, cut into 2-inch (5cm) pieces
  • 1/4 cup (20g) chopped roasted peanuts
  • 1/4 cup (1

Performance Metrics

5.93s Prediction Time
5.97s Total Time
All Input Parameters 
{
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nGive me a tasty recipe for some noodle dish.<|im_end|>\n<|im_start|>assistant\n",
  "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 [00:05<00:00,  5.87s/it]
Processed prompts: 100%|██████████| 1/1 [00:05<00:00,  5.87s/it]
Generated 256 tokens in 5.86732029914856 seconds.
Version Details
Version ID
2447da54222e6a4bb51657960962f643dd24f55e11004d4dd908e1efab027cd3
Version Created
January 12, 2024
Run on Replicate →