README.md

---
base_model: LemiSt/SmolLM-135M-de
library_name: peft
license: apache-2.0
tags:
- axolotl
- generated_from_trainer
model-index:
- name: SmolLM-135M-instruct-de
  results: []
---

<!-- 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"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.1`
```yaml
base_model: LemiSt/SmolLM-135M-de
model_type: LlamaForCausalLM
tokenizer_type: GPT2Tokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
push_dataset_to_hub:
datasets:
  - path: smollm_dataset.json
    type: sharegpt
    conversation: chatml
chat_template: chatml
default_system_prompt: "Du bist ein hilfreicher KI-Assistent."
dataset_prepared_path:
val_set_size: 0.05
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: smollm-135m-de-sft-qlora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./outputs/smollm-135m-sft-qlora-out
hub_model_id: LemiSt/SmolLM-135M-instruct-de
hub_strategy: end
gradient_accumulation_steps: 16
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.003
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 4
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|endoftext|>"
  eos_token: "<|endoftext|>"
  unk_token: "<|endoftext|>"

```

</details><br>

# SmolLM-135M-instruct-de-merged

This model is a fine-tuned version of [LemiSt/SmolLM-135M-de](https://huggingface.co/LemiSt/SmolLM-135M-de) on an internal testing dataset with general chat examples.
It achieves the following results on the evaluation set:
- Loss: 0.7453

## Model description

For more information, see the model card of the [base model](https://huggingface.co/LemiSt/SmolLM-135M-de). This adapter was trained using qlora at rank 32 with alpha 16, applying a dataset of around 200k german chat samples for two epochs.

## Intended uses & limitations

Mainly playing around with tiny chat models - while the output is generally intact German and the model somewhat follows instructions, it makes too many mistakes to be deployed in a real world setting.

### Usage example
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
checkpoint = "LemiSt/SmolLM-135M-instruct-de-merged"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map=device, torch_dtype=torch.bfloat16)
messages = [
  {"role": "system", "content": "Du bist ein hilfreicher Assistent."},
  {"role": "user", "content": "Wie viele Hände hat ein normaler Mensch?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt", add_generation_prompt=True).to(device)
outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.4, top_p=0.9, repetition_penalty=1.1, top_k=512)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
```
## Training and evaluation data

Internal dataset which was compiled for another experiment.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.003
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6406        | 0.0005 | 1    | 1.6172          |
| 0.8219        | 0.2497 | 501  | 0.8901          |
| 0.8646        | 0.4995 | 1002 | 0.8370          |
| 0.8651        | 0.7492 | 1503 | 0.8052          |
| 0.7231        | 0.9989 | 2004 | 0.7827          |
| 0.7632        | 1.2468 | 2505 | 0.7673          |
| 0.7543        | 1.4967 | 3006 | 0.7536          |
| 0.7782        | 1.7466 | 3507 | 0.7469          |
| 0.6724        | 1.9966 | 4008 | 0.7453          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1