camenduru/zephyr-orpo-141b-a35b-v0.1 🔢📝✓ → 📝
About
Mixtral 8x22b v0.1 Zephyr Orpo 141b A35b v0.1
Example Output
Prompt:
"What is the function of a CPU in a computer?"
Output
The central processing unit (CPU) performs most calculations which make up all processes and subprocesses that run applications on your personal computers. It can be called “the brain” because it controls everything else within an operating system, including memory management tasks as well! There are many types available but they usually have either one or more cores with each core being able to execute instructions at once- this means faster speeds when you’re doing something like gaming where there may not always enough time between frames for other things such has loading textures into video cards before rendering them onto screen again so players don't see any lag during gameplay sessions
Performance Metrics
3.33s
Prediction Time
3.36s
Total Time
All Input Parameters
{
"min_p": 0,
"top_k": 40,
"top_p": 1,
"prompt": "What is the function of a CPU in a computer?",
"template": "{prompt}",
"ignore_eos": false,
"max_tokens": 1024,
"min_tokens": 1,
"temperature": 0.6,
"system_prompt": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.",
"length_penalty": 1,
"presence_penalty": 0,
"frequency_penalty": 0,
"repetition_penalty": 2
}
Input Parameters
- min_p
- Float that represents the minimum probability for a token to be considered, relative to the probability of the most likely token. Must be in [0, 1]. Set to 0 to disable this.
- top_k
- Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.
- top_p
- 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
- template
- SYSTEM:{system_prompt} USER:{prompt}
- ignore_eos
- Whether to ignore the EOS token and continue generating tokens after the EOS token is generated.
- max_tokens
- Maximum number of tokens to generate per output sequence.
- min_tokens
- Minimum number of tokens to generate per output sequence.
- temperature
- 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.
- system_prompt
- length_penalty
- Float that penalizes sequences based on their length. Used in beam search.
- presence_penalty
- 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
- 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.
- repetition_penalty
- Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1 encourage the model to use new tokens, while values < 1 encourage the model to repeat tokens.
Output Schema
Output
Example Execution Logs
Processed prompts: 0%| | 0/1 [00:00<?, ?it/s] Processed prompts: 100%|██████████| 1/1 [00:03<00:00, 3.23s/it] Processed prompts: 100%|██████████| 1/1 [00:03<00:00, 3.23s/it] What is the function of a CPU in a computer? What is the function of a CPU in a computer?
Version Details
- Version ID
acc5b9e0f0a027e18097094beef09593098b545863392e6f72ed7652fe217a2a- Version Created
- April 15, 2024