CoolFace
Modelpublic

QuantFactory/Fatgirl_8B-GGUF

sourceHugging Faceupdated 2y agoView on Hugging Face
2likes384downloads
Model Card

libraryname: transformers basemodel: jeiku/Magic_8B tags:

  • —generatedfromtrainer model-index:
  • —name: outputs/out results: []

![QuantFactory Banner](https://hf.co/QuantFactory)

QuantFactory/Fatgirl_8B-GGUF

This is quantized version of jeiku/Fatgirl_8B created using llama.cpp

Original Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.1

yaml
base_model: jeiku/Magic_8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/stheno-filtered-v1.1
    type: sharegpt
    conversation: chatml
  - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: ResplendentAI/bluemoon
    type: sharegpt
    conversation: chatml
  - path: openerotica/freedom-rp
    type: sharegpt
    conversation: chatml
  - path: MinervaAI/Aesir-Preview
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.01
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 8192
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

wandb_project: New8B
wandb_entity:
wandb_watch:
wandb_name: New8B
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05

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

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

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2

debug:
deepspeed:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <pad>

</details><br>

outputs/out

This model is a fine-tuned version of jeiku/Magic_8B on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.3029

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
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 2
  • —gradientaccumulationsteps: 32
  • —totaltrainbatch_size: 64
  • —totalevalbatch_size: 2
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 32
  • —num_epochs: 2

Training results

Training LossEpochStepValidation Loss
1.4470.006211.4349
1.34370.2530411.3502
1.37340.5060821.3237
1.35430.75901231.3128
1.3191.01021641.3064
1.28861.26362051.3042
1.23871.51692461.3031
1.37461.77022871.3029

Framework versions

  • —Transformers 4.45.0.dev0
  • —Pytorch 2.4.0+cu121
  • —Datasets 2.21.0
  • —Tokenizers 0.19.1