metadata
library_name: transformers
base_model:
- nbeerbower/llama-3-bophades-v3-8B
datasets:
- jondurbin/gutenberg-dpo-v0.1
license: other
license_name: llama3
model-index:
- name: llama-3-gutenberg-8B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: wis-k/instruction-following-eval
split: train
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 43.72
name: averaged accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: SaylorTwift/bbh
split: test
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 27.96
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: lighteval/MATH-Hard
split: test
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 7.78
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
split: train
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 6.82
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 10.05
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 31.45
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
name: Open LLM Leaderboard
llama-3-gutenberg-8B
This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT
nbeerbower/llama-3-bophades-v3-8B finetuned on jondurbin/gutenberg-dpo-v0.1.
Method
Finetuned using an A100 on Google Colab.
Fine-Tune Your Own Llama 2 Model in a Colab Notebook
Configuration
Dataset preparation, system prompt:
def chatml_format(example):
# Format instruction
prompt = "<|im_start|>user\n" + example['prompt'] + "<|im_end|>\n<|im_start|>assistant\n"
# Format chosen answer
chosen = example['chosen'] + "<|im_end|>\n"
# Format rejected answer
rejected = example['rejected'] + "<|im_end|>\n"
return {
"prompt": prompt,
"chosen": chosen,
"rejected": rejected,
}
dataset = load_dataset("jondurbin/gutenberg-dpo-v0.1")['train']
# Save columns
original_columns = dataset.column_names
# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"
# Format dataset
dataset = dataset.map(
chatml_format,
remove_columns=original_columns
)
LoRA, model, and training settings:
# LoRA configuration
peft_config = LoraConfig(
r=16,
lora_alpha=16,
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM",
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
)
# Model to fine-tune
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
load_in_4bit=True
)
model.config.use_cache = False
# Reference model
ref_model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
load_in_4bit=True
)
# Training arguments
training_args = TrainingArguments(
per_device_train_batch_size=2,
gradient_accumulation_steps=2,
gradient_checkpointing=True,
learning_rate=2e-5,
lr_scheduler_type="cosine",
max_steps=1000,
save_strategy="no",
logging_steps=1,
output_dir=new_model,
optim="paged_adamw_32bit",
warmup_steps=100,
bf16=True,
report_to="wandb",
)
# Create DPO trainer
dpo_trainer = DPOTrainer(
model,
ref_model,
args=training_args,
train_dataset=dataset,
tokenizer=tokenizer,
peft_config=peft_config,
beta=0.1,
max_prompt_length=1024,
max_length=1536,
force_use_ref_model=True
)
```# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/nbeerbower__llama-3-gutenberg-8B-details)!
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=nbeerbower%2Fllama-3-gutenberg-8B&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
| Metric |Value (%)|
|-------------------|--------:|
|**Average** | 21.30|
|IFEval (0-Shot) | 43.72|
|BBH (3-Shot) | 27.96|
|MATH Lvl 5 (4-Shot)| 7.78|
|GPQA (0-shot) | 6.82|
|MuSR (0-shot) | 10.05|
|MMLU-PRO (5-shot) | 31.45|