antoinelyset/openhermes-2.5-mistral-7b-awq 🔢📝✓ → 📝
About
Example Output
Prompt:
"[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is Slite?"
}
]"
Output
Slite is a collaborative knowledge management platform designed for teams. It allows users to create, organize, and share documents, notes, and knowledge bases within a team or organization. Slite's features include real-time collaboration, version control, search functionality, and integration with other tools like Google Drive, Dropbox, and Microsoft Teams. The platform is accessible through a web browser or mobile app, making it easy for teams to access and contribute to shared knowledge wherever they are.
Performance Metrics
1.41s
Prediction Time
141.21s
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
- When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
- top_p
- When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
- prompt (required)
- The JSON stringified of the messages (array of objects with role/content like OpenAI) to predict on
- temperature
- Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
- max_new_tokens
- Max new tokens
- use_beam_search
- Whether to use beam search instead of sampling
Output Schema
Output
Example Execution Logs
Processed prompts: 0%| | 0/1 [00:00<?, ?it/s] Processed prompts: 100%|██████████| 1/1 [00:01<00:00, 1.21s/it] Processed prompts: 100%|██████████| 1/1 [00:01<00:00, 1.21s/it]
Version Details
- Version ID
f2e768e7dd9ce5479ccb63700380ce50fdd9efef5f0c77c3052adb69afde28b7
- Version Created
- November 9, 2023