Hugging Face's logo

vpakarinen
/
qwen-3b-lora-uncensored-thinking

PEFT
Safetensors
qwen2
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
qwen-3b-lora-uncensored-thinking / README.md
vpakarinen's picture
vpakarinen
Upload 7 files
3dffe68 verified
preview code
|
raw
history blame
3.07 kB
metadata
library_name: peft
license: other
base_model: unsloth/Qwen2.5-3B-Instruct
tags:
  - generated_from_trainer
datasets:
  - ICEPVP8977/Uncensored_Small_Test_Time_Compute
model-index:
  - name: outputs/mymodel
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.8.0.dev0

adapter: lora
base_model: unsloth/Qwen2.5-3B-Instruct
bf16: auto
dataset_processes: 32
per_device_train_batch_size: 1
datasets:
- message_property_mappings:
    content: content
    role: role
  path: ICEPVP8977/Uncensored_Small_Test_Time_Compute
  type: alpaca
  trust_remote_code: false
gradient_accumulation_steps: 1
gradient_checkpointing: true
learning_rate: 0.0002
lisa_layers_attribute: model.layers
load_best_model_at_end: false
load_in_4bit: true
load_in_8bit: false
lora_alpha: 16
lora_dropout: 0.05
lora_r: 8
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
loraplus_lr_embedding: 1.0e-06
lr_scheduler: cosine
max_prompt_len: 512
mean_resizing_embeddings: false
micro_batch_size: 8
num_epochs: 1.0
optimizer: paged_adamw_8bit
output_dir: ./outputs/mymodel
pretrain_multipack_attn: true
pretrain_multipack_buffer_size: 10000
qlora_sharded_model_loading: false
ray_num_workers: 1
resources_per_worker:
  GPU: 1
sample_packing_bin_size: 200
sample_packing_group_size: 100000
save_only_model: false
save_safetensors: true
sequence_len: 4096
shuffle_merged_datasets: true
skip_prepare_dataset: false
strict: false
train_on_inputs: false
trl:
  log_completions: false
  ref_model_mixup_alpha: 0.9
  ref_model_sync_steps: 64
  sync_ref_model: false
  use_vllm: false
  vllm_device: auto
  vllm_dtype: auto
  vllm_gpu_memory_utilization: 0.9
use_ray: false
val_set_size: 0.0
weight_decay: 0.0

outputs/mymodel

This model is a fine-tuned version of unsloth/Qwen2.5-3B-Instruct on the ICEPVP8977/Uncensored_Small_Test_Time_Compute dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 17
  • num_epochs: 1.0

Training results

Framework versions

  • PEFT 0.14.0
  • Transformers 4.49.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0