Uploaded finetuned model

  • Developed by: mervinpraison
  • Finetuned from model : unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit
dataset:
- name: mervinpraison/accelerometer-fall-axis-plots-alpaca
dataset_num_proc: 2
dataset_text_field: text
gradient_accumulation_steps: 4
hf_model_name: mervinpraison/llama-3.2-11B-vision-harupfall-axis
huggingface_save: 'true'
learning_rate: 0.0002
load_in_4bit: true
loftq_config: null
logging_steps: 1
lora_alpha: 16
lora_bias: none
lora_dropout: 0
lora_r: 16
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
lr_scheduler_type: linear
max_seq_length: 2048
max_steps: 4194
model_name: unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
model_parameters: 11b
num_train_epochs: 2
ollama_model: mervinpraison/llama-3.2-11b-vision-harupfall-axis
ollama_save: 'true'
optim: adamw_8bit
output_dir: outputs
packing: false
per_device_train_batch_size: 1
quantization_method:
- q4_k_m
random_state: 3407
seed: 3407
train: 'true'
use_gradient_checkpointing: unsloth
use_rslora: false
warmup_steps: 5
weight_decay: 0.01

# Vision-specific parameters
finetune_vision_layers: false
finetune_language_layers: true
finetune_attention_modules: true
finetune_mlp_modules: true
vision_instruction: "Determine whether the following accelerometer data indicates a fall or not."
Downloads last month
3
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.