---
base_model: mistralai/Mistral-Nemo-Base-2407
library_name: peft
---

# Model Card for Model ID


This is a [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) model fine-tuned on [Reddit-Dad-Jokes dataset](https://huggingface.co/datasets/shuttie/dadjokes). It can generate cringe and toxic jokes on any short prompt:

```
[INST] What horse says when she sees an old lady? [/INST] Move over grandma, I'm going to trot!
[INST] What is a lawyer's favorite drink? [/INST] Whine.
[INST] My obese pet parrot died over the weekend. [/INST] Now I just have a big fat birdcage.
[INST] My wife asked why there was a blanket on top of me and my laptop. [/INST] I told her that I was just covering all my bases.
[INST] My girlfriend changed after she became a vegetarian. [/INST] She finally lost her meat.
```

## Demo

The model is running on HF Spaces: [https://huggingface.co/spaces/shuttie/dadjokes](https://huggingface.co/spaces/shuttie/dadjokes)

## Used data

We use a [Kaggle Reddit Dad Jokes dataset](https://huggingface.co/datasets/shuttie/reddit-dadjokes) formatted in a base+punchline tuples. The model task was to predict the punchline given the base. Prompt format is the same as for original Mistral model:

`[INST] base [/INST] punchline`

## Training process

The model was trained with [Axolotl](TODO) with the following config:

```yaml
base_model: mistralai/Mistral-Nemo-Base-2407
model_type: MistralForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false
val_set_size: 0.01
datasets:
  - path: shuttie/reddit-dadjokes
    split: train
    type: 
      field_system: system
      field_instruction: instruction
      field_output: output
      field_input: input
      format: "[INST] {input} [/INST]"

dataset_prepared_path: last_run_prepared
output_dir: ./outputs/dadjoke-mistral-nemo-qlora-r128

adapter: qlora
lora_model_dir:

sequence_len: 256
sample_packing: false
pad_to_sequence_len: true

lora_r: 128
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: "dad jokes"
wandb_entity:
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001

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

gradient_checkpointing: false
gradient_checkpointing_kwargs:
  use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
xformers_attention:
flash_attention: true

logging_steps: 10
warmup_steps: 10
evals_per_epoch: 10
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: false
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: false
  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  activation_checkpointing: true
special_tokens:
  pad_token: <pad>
flash_attention: true
```

# License

Apache 2.0