Transformers
GGUF
English
llama
text-generation-inference
torch
trl
unsloth
How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
# Run inference directly in the terminal:
llama cli -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
# Run inference directly in the terminal:
llama cli -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
# Run inference directly in the terminal:
./llama-cli -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
Use Docker
docker model run hf.co/student-abdullah/Llama3.2_Trial-7_32-bit_gguf:F32
Quick Links

Uploaded model

  • Developed by: student-abdullah
  • License: apache-2.0
  • Finetuned from model: meta-llama/Llama-3.2-1B
  • Created on: 7th October, 2024

Acknowledgement


Model Description

This model is fine-tuned from the meta-llama/Llama-3.2-1B base model to enhance its capabilities in generating relevant and accurate responses related to generic medications under the PMBJP scheme. The fine-tuning process included the following hyperparameters:

  • Fine Tuning Template: Llama Q&A
  • Max Tokens: 1024
  • LoRA Alpha: 5
  • LoRA Rank (r): 132
  • Learning rate: 5e-5
  • Gradient Accumulation Steps: 1
  • Batch Size: 6
  • Quantization: None

Model Quantitative Performace

  • Training Quantitative Loss: 0.1403 (at final 3rd epoch 4505th Step)

Limitations

  • Token Limitations: With a max token limit of 512, the model might not handle very long queries or contexts effectively.
  • Training Data Limitations: The model’s performance is contingent on the quality and coverage of the fine-tuning dataset, which may affect its generalizability to different contexts or medications not covered in the dataset.
  • Potential Biases: As with any model fine-tuned on specific data, there may be biases based on the dataset used for training.

Model Performace Evaluation:

  • Evaluation on 1000 Questions based on dataset (to evaluate the finetuned knowledge base)
  • At temperature 0.3
  • Correct Responses: 83.69%
  • Incorrect Responses: 16.31%

Downloads last month
23
GGUF
Model size
1B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for student-abdullah/Llama3.2_Trial-7_32-bit_gguf

Quantized
(259)
this model

Dataset used to train student-abdullah/Llama3.2_Trial-7_32-bit_gguf