Bluckr commited on
Commit
153e259
·
1 Parent(s): fcc603f

Update README.md

Browse files

![shimeji.png](https://cdn-uploads.huggingface.co/production/uploads/64beeb8f4b4ff0d5097ddcfc/VhfWgq-Rx1PKS0JuX4wkB.png)

Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -6,7 +6,7 @@ pipeline_tag: text-generation
6
  ---
7
 
8
 
9
- Pofi is a fine-tuned version of "decapoda-research/llama-7b-hf," designed to act as an assistant capable of performing various tasks, such as:
10
 
11
  Setting alarms
12
  Connecting to the web
@@ -17,13 +17,13 @@ Opening applications
17
  Creating files
18
  Manipulating the system
19
 
20
- The training data was obtained manually through different prompts in ChatGPT, including examples created by me. It was fine-tuned using over 7,000 examples of "User" to "AI" commands. The training process was carried out in Google Colab, specifically in the "🦙🎛️ LLaMA-LoRA Tuner" notebook. The training lasted for approximately 5 hours over 10 epochs.
21
 
22
- Once LoRa was obtained, the "export_hf_checkpoint.py" script from the "tloen/alpaca-lora" repository was used to merge LoRa with the base model. This was done to quantize the model to "ggml-q4," enabling its use on a graphics card-free computer (like mine). Quantization was performed using the "ggerganov/llama.cpp" repository and the "convert.py" script.
23
 
24
- To utilize this model, you can employ "oobabooga/text-generation-webui," a user-friendly interface, or the interface I am developing for this project, "OscarMes/Pofi-Assistant."
25
 
26
- This project was created for the purpose of studying and learning about language models. All rights are reserved according to the license included in "decapoda-research/llama-7b-hf." Please refer to the included LICENSE file in that repository.
27
 
28
  ---
29
  license: other
 
6
  ---
7
 
8
 
9
+ Pofi is a fine-tuned version of ["decapoda-research/llama-7b-hf,"](https://huggingface.co/decapoda-research/llama-7b-hf) designed to act as an assistant capable of performing various tasks, such as:
10
 
11
  Setting alarms
12
  Connecting to the web
 
17
  Creating files
18
  Manipulating the system
19
 
20
+ The training data was obtained manually through different prompts in ChatGPT, including examples created by me. It was fine-tuned using over 7,000 examples of "User" to "AI" commands. The training process was carried out in Google Colab, specifically in the ["🦙🎛️ LLaMA-LoRA Tuner"](https://github.com/zetavg/LLaMA-LoRA-Tuner) notebook. The training lasted for approximately 5 hours over 10 epochs.
21
 
22
+ Once LoRa was obtained, the "export_hf_checkpoint.py" script from the ["tloen/alpaca-lora"](https://github.com/tloen/alpaca-lora) repository was used to merge LoRa with the base model. This was done to quantize the model to "ggml-q4," enabling its use on a graphics card-free computer (like mine). Quantization was performed using the ["ggerganov/llama.cpp"](https://github.com/ggerganov/llama.cpp) repository and the "convert.py" script.
23
 
24
+ To utilize this model, you can employ ["oobabooga/text-generation-webui,"](https://github.com/oobabooga/text-generation-webui) a user-friendly interface, or the interface I am developing for this project, ["OscarMes/Pofi-Assistant."](https://github.com/OscarMes/Pofi-Assistant)
25
 
26
+ This project was created for the purpose of studying and learning about language models. All rights are reserved according to the license included in "decapoda-research/llama-7b-hf." Please refer to the included [LICENSE](https://huggingface.co/decapoda-research/llama-7b-hf/blob/main/LICENSE) file in that repository.
27
 
28
  ---
29
  license: other