antoinelyset/openhermes-2-mistral-7b-awq 🔢📝✓ → 📝

▶️ 199.6K runs 📅 Nov 2023 ⚙️ Cog 0.8.6

About

Example Output

Prompt:

"[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is Slite?"
}
]"

Output

Slite is a knowledge management tool that helps teams to collaborate, share, and organize their knowledge effectively. It provides a centralized platform for teams to create, store, and find information, making it easier for them to work together and make informed decisions. Slite offers features such as note-taking, document management, task management, and real-time collaboration, making it an essential tool for teams that need to keep their knowledge organized and easily accessible.

Performance Metrics

1.18s Prediction Time

74.62s Total Time

All Input Parameters

{
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "[\n      {\n        \"role\": \"system\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"What is Slite?\"\n      }\n    ]",
  "temperature": 0.75,
  "max_new_tokens": 512,
  "use_beam_search": false
}

Input Parameters

top_k Type: integerDefault: 50Range: 0 - ∞: When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
top_p Type: numberDefault: 0.9Range: 0 - 1: When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string: The JSON stringified of the messages (array of objects with role/content like OpenAI) to predict on
temperature Type: numberDefault: 0.75Range: 0.01 - 5: Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
max_new_tokens Type: integerDefault: 512Range: 1 - ∞: Max new tokens
use_beam_search Type: booleanDefault: false: Whether to use beam search instead of sampling

Output Schema

Output

Type: array • Items Type: string

Example Execution Logs

Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:01<00:00,  1.13s/it]
Processed prompts: 100%|██████████| 1/1 [00:01<00:00,  1.13s/it]

Version Details

Version ID: f48e0a295349761472cd9bf25f6e1ad6249e41dc702a928e149097cc8eca18c9
Version Created: November 9, 2023

Run on Replicate →