license: unknown
library_name: peft
tags:
- llama-2
datasets:
- ehartford/dolphin
- garage-bAInd/Open-Platypus
inference: false
pipeline_tag: text-generation
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: llama-2-7b-instruct-peft
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 51.19
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 78.92
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 46.63
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 48.5
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 74.43
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 5.99
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dfurman/llama-2-7b-instruct-peft
name: Open LLM Leaderboard
Llama-2-7B-Instruct-v0.1
This instruction model was built via parameter-efficient QLoRA finetuning of Llama-2-7b on the first 5k rows of ehartford/dolphin and the first 5k rows of garage-bAInd/Open-Platypus. Finetuning was executed on 1x A100 (40 GB SXM) for roughly 2 hours on the Lambda Labs platform.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 44.5 |
| ARC (25-shot) | 51.19 |
| HellaSwag (10-shot) | 78.92 |
| MMLU (5-shot) | 46.63 |
| TruthfulQA (0-shot) | 48.5 |
| Winogrande (5-shot) | 74.43 |
| GSM8K (5-shot) | 5.99 |
| DROP (3-shot) | 5.82 |
We use the Language Model Evaluation Harness to run the benchmark tests above, using the same version as Hugging Face's Open LLM Leaderboard.
Loss curve
The above loss curve was generated from the run's private wandb.ai log.
Limitations and biases
The following language is modified from EleutherAI's GPT-NeoX-20B
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
How to use
!pip install -q -U huggingface_hub peft transformers torch accelerate
from huggingface_hub import notebook_login
import torch
from peft import PeftModel, PeftConfig
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
pipeline,
)
notebook_login()
peft_model_id = "dfurman/Llama-2-7B-Instruct-v0.1"
config = PeftConfig.from_pretrained(peft_model_id)
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
quantization_config=bnb_config,
use_auth_token=True,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token
model = PeftModel.from_pretrained(model, peft_model_id)
format_template = "You are a helpful assistant. {query}\n"
# First, format the prompt
query = "Tell me a recipe for vegan banana bread."
prompt = format_template.format(query=query)
# Inference can be done using model.generate
print("\n\n*** Generate:")
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
with torch.autocast("cuda", dtype=torch.bfloat16):
output = model.generate(
input_ids=input_ids,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
return_dict_in_generate=True,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
repetition_penalty=1.2,
)
print(tokenizer.decode(output["sequences"][0], skip_special_tokens=True))
Runtime tests
coming
Acknowledgements
This model was finetuned by Daniel Furman on Sep 10, 2023 and is for research applications only.
Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
meta-llama/Llama-2-7b-hf citation
coming
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.6.0.dev0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 50.94 |
| AI2 Reasoning Challenge (25-Shot) | 51.19 |
| HellaSwag (10-Shot) | 78.92 |
| MMLU (5-Shot) | 46.63 |
| TruthfulQA (0-shot) | 48.50 |
| Winogrande (5-shot) | 74.43 |
| GSM8k (5-shot) | 5.99 |