160 lines
5.3 KiB
Markdown
160 lines
5.3 KiB
Markdown
---
|
|
base_model: Felladrin/Llama-160M-Chat-v1
|
|
datasets:
|
|
- ehartford/wizard_vicuna_70k_unfiltered
|
|
- totally-not-an-llm/EverythingLM-data-V3
|
|
- Open-Orca/SlimOrca-Dedup
|
|
- databricks/databricks-dolly-15k
|
|
- THUDM/webglm-qa
|
|
inference: false
|
|
license: other
|
|
model_creator: Felladrin
|
|
model_name: Llama-160M-Chat-v1
|
|
pipeline_tag: text-generation
|
|
quantized_by: afrideva
|
|
tags:
|
|
- text-generation
|
|
- gguf
|
|
- ggml
|
|
- quantized
|
|
- q2_k
|
|
- q3_k_m
|
|
- q4_k_m
|
|
- q5_k_m
|
|
- q6_k
|
|
- q8_0
|
|
widget:
|
|
- text: "<|im_start|>system\nYou are a helpful assistant, who answers with empathy.<|im_end|>\n<|im_start|>user\nGot
|
|
a question for you!<|im_end|>\n<|im_start|>assistant\nSure! What's it?<|im_end|>\n<|im_start|>user\nWhy
|
|
do you love cats so much!? \U0001F408<|im_end|>\n<|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'
|
|
---
|
|
# Felladrin/Llama-160M-Chat-v1-GGUF
|
|
|
|
Quantized GGUF model files for [Llama-160M-Chat-v1](https://huggingface.co/Felladrin/Llama-160M-Chat-v1) from [Felladrin](https://huggingface.co/Felladrin)
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [llama-160m-chat-v1.fp16.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.fp16.gguf) | fp16 | 326.58 MB |
|
|
| [llama-160m-chat-v1.q2_k.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q2_k.gguf) | q2_k | 77.23 MB |
|
|
| [llama-160m-chat-v1.q3_k_m.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q3_k_m.gguf) | q3_k_m | 87.54 MB |
|
|
| [llama-160m-chat-v1.q4_k_m.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q4_k_m.gguf) | q4_k_m | 104.03 MB |
|
|
| [llama-160m-chat-v1.q5_k_m.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q5_k_m.gguf) | q5_k_m | 119.04 MB |
|
|
| [llama-160m-chat-v1.q6_k.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q6_k.gguf) | q6_k | 135.00 MB |
|
|
| [llama-160m-chat-v1.q8_0.gguf](https://huggingface.co/afrideva/Llama-160M-Chat-v1-GGUF/resolve/main/llama-160m-chat-v1.q8_0.gguf) | q8_0 | 174.33 MB |
|
|
|
|
|
|
|
|
## Original Model Card:
|
|
# 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)
|
|
|
|
## 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
|
|
``` |