"content": "Sure! Here's What I'd Say Given That It's a Test:\n\n---\n\n**Test Scenario: Validation of a Given Statement**\n\n**Scenario Outline:** \n- **Scenario Name:** \"Test Scenario\"\n- **Description:** \"This is a test!\"\n\n**1. Pre-Test Preparations:**\n\nBefore starting the test, the following preparations must be made: \n\n- **Test Environment:** Ensure that the test environment is setup correctly. This may include ensuring that all necessary software"
}
}
],
"usage": {
"prompt_tokens": 16,
"completion_tokens": 100,
"total_tokens": 116
}
}
```
### Request Fields
-`messages`: An array of message objects representing the conversation
history. Each message object should have a role (e.g. user, assistant) and
content (the message text).
-`role_mapping`: (Optional) A dictionary to customize the role prefixes in
the generated prompt. If not provided, the default mappings are used.
-`stop`: (Optional) An array of strings or a single string. Thesse are
sequences of tokens on which the generation should stop.
-`max_tokens`: (Optional) An integer specifying the maximum number of tokens
to generate. Defaults to `100`.
-`stream`: (Optional) A boolean indicating if the response should be
streamed. If true, responses are sent as they are generated. Defaults to
false.
-`temperature`: (Optional) A float specifying the sampling temperature.
Defaults to `1.0`.
-`top_p`: (Optional) A float specifying the nucleus sampling parameter.
Defaults to `1.0`.
-`repetition_penalty`: (Optional) Applies a penalty to repeated tokens.
Defaults to `1.0`.
-`repetition_context_size`: (Optional) The size of the context window for
applying repetition penalty. Defaults to `20`.
-`logit_bias`: (Optional) A dictionary mapping token IDs to their bias
values. Defaults to `None`.
-`logprobs`: (Optional) An integer specifying the number of top tokens and
corresponding log probabilities to return for each output in the generated
sequence. If set, this can be any value between 1 and 10, inclusive.
### Text Models
- [MLX LM](llms/README.md) a package for LLM text generation, fine-tuning, and more.
- [Transformer language model](transformer_lm) training.
- Minimal examples of large scale text generation with [LLaMA](llms/llama),
[Mistral](llms/mistral), and more in the [LLMs](llms) directory.
- A mixture-of-experts (MoE) language model with [Mixtral 8x7B](llms/mixtral).
- Parameter efficient fine-tuning with [LoRA or QLoRA](lora).
- Text-to-text multi-task Transformers with [T5](t5).
- Bidirectional language understanding with [BERT](bert).
### Image Models
- Image classification using [ResNets on CIFAR-10](cifar).
- Generating images with [Stable Diffusion or SDXL](stable_diffusion).
- Convolutional variational autoencoder [(CVAE) on MNIST](cvae).
### Audio Models
- Speech recognition with [OpenAI's Whisper](whisper).
### Multimodal models
- Joint text and image embeddings with [CLIP](clip).
- Text generation from image and text inputs with [LLaVA](llava).
### Other Models
- Semi-supervised learning on graph-structured data with [GCN](gcn).
- Real NVP [normalizing flow](normalizing_flow) for density estimation and
sampling.
### Hugging Face
Note: You can now directly download a few converted checkpoints from the [MLX
Community](https://huggingface.co/mlx-community) organization on Hugging Face.
We encourage you to join the community and [contribute new
