---
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
base_model: EleutherAI/pythia-31m
datasets:
  - totally-not-an-llm/EverythingLM-data-V3
  - databricks/databricks-dolly-15k
  - THUDM/webglm-qa
  - starfishmedical/webGPT_x_dolly
  - Amod/mental_health_counseling_conversations
  - sablo/oasst2_curated
  - cognitivecomputations/wizard_vicuna_70k_unfiltered
  - mlabonne/chatml_dpo_pairs
widget:
  - text: |-
      <|im_start|>system
      You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.<|im_end|>
      <|im_start|>user
      Heya!<|im_end|>
      <|im_start|>assistant
      Hi! How may I help you?<|im_end|>
      <|im_start|>user
      I am interested in developing a career in software engineering. What would you recommend me to do?<|im_end|>
      <|im_start|>assistant
  - text: |-
      <|im_start|>system
      You are a helpful assistant.<|im_end|>
      <|im_start|>user
      Got a question for you!<|im_end|>
      <|im_start|>assistant
      Sure! What's it?<|im_end|>
      <|im_start|>user
      Could you explain what REST API is?<|im_end|>
      <|im_start|>assistant
inference:
  parameters:
    max_new_tokens: 250
    do_sample: true
    temperature: 0.4
    top_p: 0.25
    top_k: 7
    repetition_penalty: 1.0016
---

# A Pythia Chat Model of 31M Parameters

- Base model: [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m)
- Availability in other ML formats:
  - ONNX: [Felladrin/onnx-Pythia-31M-Chat-v1](https://huggingface.co/Felladrin/onnx-Pythia-31M-Chat-v1)

## Recommended prompt format

```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
```

## Recommended inference parameters

```yml
do_sample: true
temperature: 0.4
top_p: 0.25
top_k: 7
repetition_penalty: 1.0016
```

## Datasets and parameters used for training

| Dataset | License Type |
|---------|--------------|
| [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3) | mit |
| [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) | cc-by-sa-3.0 |
| [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa) | apache-2.0 |
| [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly) | cc-by-sa-3.0 |
| [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations) | openrail |
| [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated) | apache-2.0 |
| [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered) | apache-2.0 |
| [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) | apache-2.0 |

```python
SFTTrainer(
    model,
    train_dataset=train_dataset,
    dataset_text_field="text",
    eval_dataset=eval_dataset,
    max_seq_length=2048,
    packing=True,
    args=TrainingArguments(
        learning_rate=2e-6,
        per_device_train_batch_size=1,
        per_device_eval_batch_size=1,
        gradient_accumulation_steps=16,
        lr_scheduler_type="cosine",
        num_train_epochs=1,
        logging_strategy="steps",
        save_strategy="steps",
        evaluation_strategy="steps",
        logging_steps=10,
        eval_steps=10,
        save_steps=10,
        warmup_steps=50,
        load_best_model_at_end=True,
        metric_for_best_model="eval_loss",
        greater_is_better=False,
        weight_decay=0.01,
        save_total_limit=10,
        neftune_noise_alpha=5,
    ),
    callbacks=[
        EarlyStoppingCallback(
            early_stopping_patience=3,
            early_stopping_threshold=0.005
        ),
    ],
)
```

```python
DPOTrainer(
    model,
    beta=0.1,
    train_dataset=dataset,
    tokenizer=tokenizer,
    eval_dataset=eval_dataset,
    max_length=1536,
    max_prompt_length=1024,
    args=TrainingArguments(
        learning_rate=2e-6,
        per_device_train_batch_size=1,
        per_device_eval_batch_size=1,
        gradient_accumulation_steps=1,
        lr_scheduler_type="cosine",
        num_train_epochs=1,
        logging_strategy="steps",
        save_strategy="steps",
        evaluation_strategy="steps",
        logging_steps=1,
        eval_steps=1,
        save_steps=1,
        warmup_steps=0,
        load_best_model_at_end=True,
        metric_for_best_model="eval_loss",
        greater_is_better=False,
        weight_decay=0.0,
        neftune_noise_alpha=5,
        remove_unused_columns=False,
    ),
    callbacks=[
        EarlyStoppingCallback(
            early_stopping_patience=3,
            early_stopping_threshold=0.005
        ),
    ],
)
```