Pythia-31M-Chat-v1/README.md

language, license, base_model, datasets, pipeline_tag, widget, inference, model-index

language	license	base_model	datasets	pipeline_tag	widget	inference	model-index
en	apache-2.0	EleutherAI/pythia-31m	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	text-generation	messages role content 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. role content user Heya! role content assistant Hi! How may I help you? role content user I am interested in developing a career in software engineering. What would you recommend me to do? messages role content system You are a helpful assistant who answers user's questions with details and curiosity. role content user What are some potential applications for quantum computing? messages role content system You are a highly knowledgeable assistant. Help the user as much as you can. role content user What are some steps I can take to become a healthier person?	parameters max_new_tokens penalty_alpha top_k repetition_penalty 250 0.5 2 1.0016	name results Pythia-31M-Chat-v1 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 22.7 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 25.6 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 23.24 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 47.99 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 0.0 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 0.0 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1 Open LLM Leaderboard

A Pythia Chat Model of 31M Parameters

• Base model: EleutherAI/pythia-31m
• Availability in other ML formats:
  • GGUF: Felladrin/gguf-Pythia-31M-Chat-v1
  • ONNX: 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

penalty_alpha: 0.5
top_k: 2
repetition_penalty: 1.0016

Datasets and parameters used for training

Dataset	License Type
totally-not-an-llm/EverythingLM-data-V3	mit
databricks/databricks-dolly-15k	cc-by-sa-3.0
THUDM/webglm-qa	apache-2.0
starfishmedical/webGPT_x_dolly	cc-by-sa-3.0
Amod/mental_health_counseling_conversations	openrail
sablo/oasst2_curated	apache-2.0
cognitivecomputations/wizard_vicuna_70k_unfiltered	apache-2.0
mlabonne/chatml_dpo_pairs	apache-2.0

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
        ),
    ],
)

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
        ),
    ],
)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.92
AI2 Reasoning Challenge (25-Shot)	22.70
HellaSwag (10-Shot)	25.60
MMLU (5-Shot)	23.24
TruthfulQA (0-shot)	0.00
Winogrande (5-shot)	47.99
GSM8k (5-shot)	0.00