Mawdistical / Draconic-Tease-LoRa

huggingface.co
Total runs: 6
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: April 06 2025

Introduction of Draconic-Tease-LoRa

Model Details of Draconic-Tease-LoRa

Built with Axolotl

See axolotl config

axolotl version: 0.7.0

base_model: Steelskull/L3.3-Electra-R1-70b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

model_config:
  trust_remote_code: true
  tokenizer:
    pad_token: "</s>"
    padding_side: "right"

datasets:
  - path: data/data.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content


load_in_4bit: true
adapter: qlora
lora_r: 64
lora_alpha: 32
lora_dropout: 0.1
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj

wandb_project: mawzilla
wandb_name: Purring-stats

val_set_size: 0.01
evals_per_epoch: 2
eval_sample_packing: false
eval_max_new_tokens: 128

lora_modules_to_save:
  - embed_tokens
  - lm_head

bf16: true
flash_attention: true
gradient_checkpointing: unsloth
deepspeed: deepspeed_configs/zero3_bf16.json

gradient_accumulation_steps: 4
micro_batch_size: 8
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5
warmup_ratio: 0.03

max_seq_length: 8192
pad_to_sequence_len: false
sample_packing: true

output_dir: ./output
save_steps: 100
logging_steps: 10
save_safetensors: true

special_tokens:
  pad_token: "<|finetune_right_pad_id|>"
  eos_token: "<|eot_id|>"

output

This model is a fine-tuned version of Steelskull/L3.3-Electra-R1-70b on the data/data.jsonl dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1095
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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use 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: 6
  • num_epochs: 2.0
Training results
Training Loss Epoch Step Validation Loss
No log 0.0094 1 2.7519
2.39 0.5 53 2.3200
2.1579 1.0 106 2.1615
1.9126 1.5 159 2.1168
1.9958 2.0 212 2.1095
Framework versions
  • PEFT 0.14.0
  • Transformers 4.48.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.1

Runs of Mawdistical Draconic-Tease-LoRa on huggingface.co

6
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About Draconic-Tease-LoRa huggingface.co Model

Draconic-Tease-LoRa huggingface.co

Draconic-Tease-LoRa huggingface.co is an AI model on huggingface.co that provides Draconic-Tease-LoRa's model effect (), which can be used instantly with this Mawdistical Draconic-Tease-LoRa model. huggingface.co supports a free trial of the Draconic-Tease-LoRa model, and also provides paid use of the Draconic-Tease-LoRa. Support call Draconic-Tease-LoRa model through api, including Node.js, Python, http.

Draconic-Tease-LoRa huggingface.co Url

https://huggingface.co/Mawdistical/Draconic-Tease-LoRa

Mawdistical Draconic-Tease-LoRa online free

Draconic-Tease-LoRa huggingface.co is an online trial and call api platform, which integrates Draconic-Tease-LoRa's modeling effects, including api services, and provides a free online trial of Draconic-Tease-LoRa, you can try Draconic-Tease-LoRa online for free by clicking the link below.

Mawdistical Draconic-Tease-LoRa online free url in huggingface.co:

https://huggingface.co/Mawdistical/Draconic-Tease-LoRa

Draconic-Tease-LoRa install

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

Draconic-Tease-LoRa install url in huggingface.co:

https://huggingface.co/Mawdistical/Draconic-Tease-LoRa

Url of Draconic-Tease-LoRa

Draconic-Tease-LoRa huggingface.co Url

Provider of Draconic-Tease-LoRa huggingface.co

Mawdistical
ORGANIZATIONS

Other API from Mawdistical

huggingface.co

Total runs: 41
Run Growth: -31
Growth Rate: -75.61%
Updated:November 03 2025