---
license: other
tags:
  - text-generation
base_model: JackFram/llama-160m
datasets:
  - ehartford/wizard_vicuna_70k_unfiltered
  - totally-not-an-llm/EverythingLM-data-V3
  - Open-Orca/SlimOrca-Dedup
  - databricks/databricks-dolly-15k
  - THUDM/webglm-qa
widget:
  - text: |-
      <|im_start|>system
      You are a helpful assistant, who answers with empathy.<|im_end|>
      <|im_start|>user
      Got a question for you!<|im_end|>
      <|im_start|>assistant
      Sure! What's it?<|im_end|>
      <|im_start|>user
      Why do you love cats so much!? 🐈<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who answers user's questions with empathy.<|im_end|>
      <|im_start|>user
      Who is Mona Lisa?<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who provides concise responses.<|im_end|>
      <|im_start|>user
      Heya!<|im_end|>
      <|im_start|>assistant
      Hi! How may I help you today?<|im_end|>
      <|im_start|>user
      I need to build a simple website. Where should I start learning about web development?<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>user
      Invited some friends to come home today. Give me some ideas for games to play with them!<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who answers user's questions with details and curiosity.<|im_end|>
      <|im_start|>user
      What are some potential applications for quantum computing?<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who gives creative responses.<|im_end|>
      <|im_start|>user
      Write the specs of a game about mages in a fantasy world.<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who answers user's questions with details.<|im_end|>
      <|im_start|>user
      Tell me about the pros and cons of social media.<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant who answers user's questions with confidence.<|im_end|>
      <|im_start|>user
      What is a dog?<|im_end|>
      <|im_start|>assistant
      A dog is a four-legged, domesticated animal that is a member of the class Mammalia, which includes all mammals. Dogs are known for their loyalty, playfulness, and ability to be trained for various tasks. They are also used for hunting, herding, and as service animals.<|im_end|>
      <|im_start|>user
      What is the color of an apple?<|im_end|>
      <|im_start|>assistant
inference:
  parameters:
    max_new_tokens: 250
    penalty_alpha: 0.5
    top_k: 5
    repetition_penalty: 1.01
---

# A Llama Chat Model of 160M Parameters

- Base model: [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m)
- Datasets:
  - [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
  - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3)
  - [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
  - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
  - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
- Availability in other ML formats:
  - GGUF: [Felladrin/gguf-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/gguf-Llama-160M-Chat-v1)
  - ONNX: [Felladrin/onnx-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-160M-Chat-v1)
  - MLC: [Felladrin/mlc-q4f16-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/mlc-q4f16-Llama-160M-Chat-v1)

## Recommended Prompt Format

The recommended prompt format is as follows:

```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
```

## Recommended Inference Parameters

To get the best results, prefer using [contrastive search](https://huggingface.co/docs/transformers/main/en/generation_strategies#contrastive-search) for inference:

```yml
penalty_alpha: 0.5
top_k: 5
```