Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Evaluation Results

DatasetBase AccuracyFT AccuracyBase Macro-F1FT Macro-F1
FPB in-domain0.89080.97480.87650.9725
FiQA-SA OOD0.81200.94020.67050.8335

Baseline = zero-shot Meta-Llama-3.1-8B-Instruct with the same prompt template.

Quick Start

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained(
"meta-llama/Meta-Llama-3.1-8B-Instruct",
load_in_4bit=True,
device_map="auto",
)
model = PeftModel.from_pretrained(base, "jhon53/Llama3_1_8B_Finance_QLoRA")
tokenizer = AutoTokenizer.from_pretrained("jhon53/Llama3_1_8B_Finance_QLoRA")

Training Details

ParamValue
Base modelmeta-llama/Meta-Llama-3.1-8B-Instruct
MethodQLoRA (4-bit NF4 + LoRA bf16)
LoRA rank (r)16
LoRA alpha32
LoRA dropout0.05
Target modulesq, k, v, o, gate, up, down projections
Training dataFinGPT/fingpt-sentiment-train (~76k)
OptimizerAdamW 8-bit
Learning rate2e-4 (cosine schedule)
Epochs3 (early stopping, patience=3)
LossCompletion-only cross-entropy

Related Repos

Uploaded finetuned model

  • Developed by: jhon53
  • License: apache-2.0
  • Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Model provider

jhon53

Model tree

Base

unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Fine-tuned

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today