tomasmcm/neural-chat-7b-v3-1 📝🔢 → 📝

▶️ 777 runs 📅 Nov 2023 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License
chatbot creative-writing joke-generation language-model poetry question-answering storytelling text-generation

About

Source: Intel/neural-chat-7b-v3-1 ✦ Quant: TheBloke/neural-chat-7B-v3-1-AWQ ✦ Fine-tuned model based on mistralai/Mistral-7B-v0.1

Example Output

Prompt:

"

System:

  • You are a helpful assistant chatbot trained by Intel.
  • 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.

User: What are the top five must-visit attractions in Shanghai?

Assistant:

"

Output

In Shanghai, there are numerous must-visit attractions that cater to various interests. Here's a list of top five attractions you simply cannot miss:

  1. The Bund: A famous waterfront promenade lined with beautiful colonial architecture.
  2. Yuyuan Garden: A historic garden filled with traditional Chinese elements, rich in history and culture.
  3. Shanghai Disney Resort: A stunning amusement park with themed areas, shows, and entertainment.
  4. Jade Buddha Temple: A renowned Buddhist temple featuring exquisite jade Buddha statues.

Performance Metrics

1.69s Prediction Time
72.64s Total Time
All Input Parameters 
{
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "### System:\n- You are a helpful assistant chatbot trained by Intel.\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.</s>\n### User: What are the top five must-visit attractions in Shanghai?\n### 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 [00:01<00:00,  1.63s/it]
Processed prompts: 100%|██████████| 1/1 [00:01<00:00,  1.63s/it]
Generated 128 tokens in 1.629446268081665 seconds.
Version Details
Version ID
acb450496b49e19a1e410b50c574a34acacd54820bc36c19cbfe05148de2ba57
Version Created
November 18, 2023
Run on Replicate →