|
--- |
|
license: mit |
|
datasets: |
|
- cong1230/Mental_illness_chatbot_training_dataset |
|
language: |
|
- ko |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
description: 'Model Purpose and Target Domain: |
|
|
|
This model is designed for text generation, specifically for the domain of mental |
|
health counseling chatbots. Its aim is to provide support for various mental health |
|
issues through conversations with users. |
|
|
|
|
|
Unique Features and Capabilities: |
|
|
|
The model specializes in mental health counseling, generating responses based on |
|
users'' text inputs, performing sentiment analysis, and providing appropriate counseling. |
|
It also incorporates knowledge about various mental health-related topics to offer |
|
more effective counseling. |
|
|
|
|
|
Performance Metrics and Benchmarks: |
|
|
|
Specific information about performance metrics and benchmarks is not currently available. |
|
The quantitative performance of the model needs to be evaluated in real-world usage |
|
scenarios. |
|
|
|
|
|
Training Procedure and Techniques: |
|
|
|
The model was fine-tuned using the Peft library with Low-Rank Adaptation (LoRA) |
|
technique. This approach allows the model to effectively learn and apply knowledge |
|
and language specific to mental health counseling in chatbot interactions.' |
|
tags: |
|
- TensorBlock |
|
- GGUF |
|
base_model: cong1230/LDCC_LoRA_full |
|
--- |
|
|
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
<div style="display: flex; justify-content: space-between; width: 100%;"> |
|
<div style="display: flex; flex-direction: column; align-items: flex-start;"> |
|
<p style="margin-top: 0.5em; margin-bottom: 0em;"> |
|
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a> |
|
</p> |
|
</div> |
|
</div> |
|
|
|
## cong1230/LDCC_LoRA_full - GGUF |
|
|
|
This repo contains GGUF format model files for [cong1230/LDCC_LoRA_full](https://huggingface.co/cong1230/LDCC_LoRA_full). |
|
|
|
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d). |
|
|
|
<div style="text-align: left; margin: 20px 0;"> |
|
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;"> |
|
Run them on the TensorBlock client using your local machine ↗ |
|
</a> |
|
</div> |
|
|
|
## Prompt template |
|
|
|
``` |
|
|
|
``` |
|
|
|
## Model file specification |
|
|
|
| Filename | Quant type | File Size | Description | |
|
| -------- | ---------- | --------- | ----------- | |
|
| [LDCC_LoRA_full-Q2_K.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q2_K.gguf) | Q2_K | 4.939 GB | smallest, significant quality loss - not recommended for most purposes | |
|
| [LDCC_LoRA_full-Q3_K_S.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q3_K_S.gguf) | Q3_K_S | 5.751 GB | very small, high quality loss | |
|
| [LDCC_LoRA_full-Q3_K_M.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q3_K_M.gguf) | Q3_K_M | 6.430 GB | very small, high quality loss | |
|
| [LDCC_LoRA_full-Q3_K_L.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q3_K_L.gguf) | Q3_K_L | 7.022 GB | small, substantial quality loss | |
|
| [LDCC_LoRA_full-Q4_0.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q4_0.gguf) | Q4_0 | 7.468 GB | legacy; small, very high quality loss - prefer using Q3_K_M | |
|
| [LDCC_LoRA_full-Q4_K_S.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q4_K_S.gguf) | Q4_K_S | 7.525 GB | small, greater quality loss | |
|
| [LDCC_LoRA_full-Q4_K_M.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q4_K_M.gguf) | Q4_K_M | 7.968 GB | medium, balanced quality - recommended | |
|
| [LDCC_LoRA_full-Q5_0.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q5_0.gguf) | Q5_0 | 9.083 GB | legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [LDCC_LoRA_full-Q5_K_S.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q5_K_S.gguf) | Q5_K_S | 9.083 GB | large, low quality loss - recommended | |
|
| [LDCC_LoRA_full-Q5_K_M.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q5_K_M.gguf) | Q5_K_M | 9.341 GB | large, very low quality loss - recommended | |
|
| [LDCC_LoRA_full-Q6_K.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q6_K.gguf) | Q6_K | 10.800 GB | very large, extremely low quality loss | |
|
| [LDCC_LoRA_full-Q8_0.gguf](https://huggingface.co/tensorblock/LDCC_LoRA_full-GGUF/blob/main/LDCC_LoRA_full-Q8_0.gguf) | Q8_0 | 13.988 GB | very large, extremely low quality loss - not recommended | |
|
|
|
|
|
## Downloading instruction |
|
|
|
### Command line |
|
|
|
Firstly, install Huggingface Client |
|
|
|
```shell |
|
pip install -U "huggingface_hub[cli]" |
|
``` |
|
|
|
Then, downoad the individual model file the a local directory |
|
|
|
```shell |
|
huggingface-cli download tensorblock/LDCC_LoRA_full-GGUF --include "LDCC_LoRA_full-Q2_K.gguf" --local-dir MY_LOCAL_DIR |
|
``` |
|
|
|
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try: |
|
|
|
```shell |
|
huggingface-cli download tensorblock/LDCC_LoRA_full-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' |
|
``` |
|
|
