|
--- |
|
license: mit |
|
datasets: |
|
- avaliev/chat_doctor |
|
language: |
|
- en |
|
base_model: prithivMLmods/Llama-Doctor-3.2-3B-Instruct |
|
pipeline_tag: text-generation |
|
library_name: transformers |
|
tags: |
|
- Llama-3.2 |
|
- 3B |
|
- Llama-Doctor |
|
- Instruct |
|
- Llama-Cpp |
|
- meta |
|
- pytorch |
|
- safetensors |
|
- llama-cpp |
|
- gguf-my-repo |
|
--- |
|
|
|
# Triangle104/Llama-Doctor-3.2-3B-Instruct-Q4_K_S-GGUF |
|
This model was converted to GGUF format from [`prithivMLmods/Llama-Doctor-3.2-3B-Instruct`](https://huggingface.co/prithivMLmods/Llama-Doctor-3.2-3B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
Refer to the [original model card](https://huggingface.co/prithivMLmods/Llama-Doctor-3.2-3B-Instruct) for more details on the model. |
|
|
|
--- |
|
Model details: |
|
- |
|
The Llama-Doctor-3.2-3B-Instruct model is designed for text generation tasks, particularly in contexts where instruction-following capabilities are needed. This model is a fine-tuned version of the base Llama-3.2-3B-Instruct model and is optimized for understanding and responding to user-provided instructions or prompts. The model has been trained on a specialized dataset, avaliev/chat_doctor, to enhance its performance in providing conversational or advisory responses, especially in medical or technical fields. |
|
Key Use Cases: |
|
|
|
Conversational AI: Engage in dialogue, answering questions, or providing responses based on user instructions. |
|
Text Generation: Generate content, summaries, explanations, or solutions to problems based on given prompts. |
|
Instruction Following: Understand and execute instructions, potentially in complex or specialized domains like medical, technical, or academic fields. |
|
|
|
The model leverages a PyTorch-based architecture and comes with various files such as configuration files, tokenizer files, and special tokens maps to facilitate smooth deployment and interaction. |
|
Intended Applications: |
|
|
|
Chatbots for customer support or virtual assistants. |
|
Medical Consultation Tools for generating advice or answering medical queries (given its training on the chat_doctor dataset). |
|
Content Creation tools, helping generate text based on specific instructions. |
|
Problem-solving Assistants that offer explanations or answers to user queries, particularly in instructional contexts. |
|
|
|
--- |
|
## Use with llama.cpp |
|
Install llama.cpp through brew (works on Mac and Linux) |
|
|
|
```bash |
|
brew install llama.cpp |
|
|
|
``` |
|
Invoke the llama.cpp server or the CLI. |
|
|
|
### CLI: |
|
```bash |
|
llama-cli --hf-repo Triangle104/Llama-Doctor-3.2-3B-Instruct-Q4_K_S-GGUF --hf-file llama-doctor-3.2-3b-instruct-q4_k_s.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/Llama-Doctor-3.2-3B-Instruct-Q4_K_S-GGUF --hf-file llama-doctor-3.2-3b-instruct-q4_k_s.gguf -c 2048 |
|
``` |
|
|
|
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. |
|
|
|
Step 1: Clone llama.cpp from GitHub. |
|
``` |
|
git clone https://github.com/ggerganov/llama.cpp |
|
``` |
|
|
|
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). |
|
``` |
|
cd llama.cpp && LLAMA_CURL=1 make |
|
``` |
|
|
|
Step 3: Run inference through the main binary. |
|
``` |
|
./llama-cli --hf-repo Triangle104/Llama-Doctor-3.2-3B-Instruct-Q4_K_S-GGUF --hf-file llama-doctor-3.2-3b-instruct-q4_k_s.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/Llama-Doctor-3.2-3B-Instruct-Q4_K_S-GGUF --hf-file llama-doctor-3.2-3b-instruct-q4_k_s.gguf -c 2048 |
|
``` |
|
|
