minpeter / QLoRA-Llama-3.2-1B-alpaca

huggingface.co
Total runs: 30
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: February 05 2025

Introduction of QLoRA-Llama-3.2-1B-alpaca

Model Details of QLoRA-Llama-3.2-1B-alpaca

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: meta-llama/Llama-3.2-1B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

QLoRA-Llama-3.2-1B-Alpaca

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the yahma/alpaca-cleaned dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2517
Model description

This is an instruction-tuned model trained using the Alpaca Prompt Format with the cleaned version of the original Alpaca Dataset (yahma/alpaca-cleaned) released by Stanford.
Please note that this model is based on the Llama 3.2 1B Base (pretrained) model.

Intended uses & limitations

The following chat template provides optimal performance for inference:

# w/o train system prompt
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + eos_token + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}

# w/ train system prompt
{{ bos_token }}{{ 'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + eos_token + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}

The model was trained with the system prompt:
"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."
However, it has not been tested whether including this prompt in inference is the optimal choice. Feel free to experiment.

An example rendering with the w/ train system prompt template is as follows:

<|begin_of_text|>### Instruction:
what is  43 + 12?

### Response:
The sum of numbers 43 and 12 is 55.<|end_of_text|>

In this case, the model output is:
The sum of numbers 43 and 12 is 55.<|end_of_text|>
Be mindful of the EOS token.

Training procedure
Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB 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: 10
  • num_epochs: 1.0
Training results

https://wandb.ai/kasfiekfs-e/axolotl/runs/uzitnvvj

Training Loss Epoch Step Validation Loss
1.4939 0.0018 1 1.4682
1.3169 0.2510 138 1.2773
1.2603 0.5020 276 1.2603
1.2301 0.7531 414 1.2517
Framework versions
  • PEFT 0.14.0
  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Runs of minpeter QLoRA-Llama-3.2-1B-alpaca on huggingface.co

30
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About QLoRA-Llama-3.2-1B-alpaca huggingface.co Model

More QLoRA-Llama-3.2-1B-alpaca license Visit here:

https://choosealicense.com/licenses/llama3.2

QLoRA-Llama-3.2-1B-alpaca huggingface.co

QLoRA-Llama-3.2-1B-alpaca huggingface.co is an AI model on huggingface.co that provides QLoRA-Llama-3.2-1B-alpaca's model effect (), which can be used instantly with this minpeter QLoRA-Llama-3.2-1B-alpaca model. huggingface.co supports a free trial of the QLoRA-Llama-3.2-1B-alpaca model, and also provides paid use of the QLoRA-Llama-3.2-1B-alpaca. Support call QLoRA-Llama-3.2-1B-alpaca model through api, including Node.js, Python, http.

QLoRA-Llama-3.2-1B-alpaca huggingface.co Url

https://huggingface.co/minpeter/QLoRA-Llama-3.2-1B-alpaca

minpeter QLoRA-Llama-3.2-1B-alpaca online free

QLoRA-Llama-3.2-1B-alpaca huggingface.co is an online trial and call api platform, which integrates QLoRA-Llama-3.2-1B-alpaca's modeling effects, including api services, and provides a free online trial of QLoRA-Llama-3.2-1B-alpaca, you can try QLoRA-Llama-3.2-1B-alpaca online for free by clicking the link below.

minpeter QLoRA-Llama-3.2-1B-alpaca online free url in huggingface.co:

https://huggingface.co/minpeter/QLoRA-Llama-3.2-1B-alpaca

QLoRA-Llama-3.2-1B-alpaca install

QLoRA-Llama-3.2-1B-alpaca is an open source model from GitHub that offers a free installation service, and any user can find QLoRA-Llama-3.2-1B-alpaca on GitHub to install. At the same time, huggingface.co provides the effect of QLoRA-Llama-3.2-1B-alpaca install, users can directly use QLoRA-Llama-3.2-1B-alpaca installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

QLoRA-Llama-3.2-1B-alpaca install url in huggingface.co:

https://huggingface.co/minpeter/QLoRA-Llama-3.2-1B-alpaca

Url of QLoRA-Llama-3.2-1B-alpaca

QLoRA-Llama-3.2-1B-alpaca huggingface.co Url

Provider of QLoRA-Llama-3.2-1B-alpaca huggingface.co

minpeter
ORGANIZATIONS

Other API from minpeter

huggingface.co

Total runs: 253
Run Growth: 0
Growth Rate: 0.00%
Updated:April 07 2025
huggingface.co

Total runs: 20
Run Growth: -32
Growth Rate: -160.00%
Updated:July 31 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:September 16 2024