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

▶️ 247 runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
code-generation question-answering text-generation

About

Simple version of https://huggingface.co/teknium/OpenHermes-2-Mistral-7B

Example Output

Prompt:

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

Output

Slite is a collaborative workspace for teams that provides a centralized platform for creating, organizing, and sharing documents, notes, and files. It is designed to help teams improve their productivity, communication, and knowledge management. Slite offers features such as real-time collaboration, task management, note-taking, document organization, and search functionality, making it easy for team members to access and work on documents together.

Performance Metrics

3.64s Prediction Time
3.61s 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
}
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
Output Schema

Output

Type: arrayItems Type: string

Example Execution Logs
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:32000 for open-end generation.
Version Details
Version ID
4a459338d2bd1ba653184c49e1424bc0792432bfbe1aa4e43837528f0134cae4
Version Created
November 20, 2023
Run on Replicate →