README.md

---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
datasets:
- gsm8k
---

# Model Card for Model ID

Trained with [Ludwig.ai](https://ludwig.ai) and [Predibase](https://predibase.com)!

Given a grade school math question, provide the answer including reasoning steps.

Try it in [LoRAX](https://github.com/predibase/lorax):

```python
from lorax import Client

client = Client("http://<your_endpoint>")

question = "<your math question>"

prompt = f"""
Please answer the following question: {question}

Answer:
"""

adapter_id = "tgaddair/mistral-7b-gsmk8k-lora-r8"
resp = client.generate(prompt, max_new_tokens=64, adapter_id=adapter_id)
print(resp.generated_text)
```



## Model Details

### Model Description

Ludwig config (v0.9.3):

```yaml
model_type: llm
input_features:
  - name: prompt
    type: text
    preprocessing:
      max_sequence_length: null
    column: prompt
output_features:
  - name: answer
    type: text
    preprocessing:
      max_sequence_length: null
    column: answer
prompt:
  template: |-
    Please answer the following question: {question}

    Answer:
preprocessing:
  split:
    type: fixed
    column: split
  global_max_sequence_length: 2048
adapter:
  type: lora
generation:
  max_new_tokens: 64
trainer:
  type: finetune
  epochs: 3
  optimizer:
    type: paged_adam
  batch_size: 1
  eval_steps: 100
  learning_rate: 0.0002
  eval_batch_size: 2
  steps_per_checkpoint: 1000
  learning_rate_scheduler:
    decay: cosine
    warmup_fraction: 0.03
  gradient_accumulation_steps: 16
  enable_gradient_checkpointing: true
base_model: mistralai/Mistral-7B-v0.1
quantization:
  bits: 4
```