mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
zephyr-7b-alpha	38	72.24	56.06	40.57	51.72

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	20.47	±	2.54
		acc_norm	19.69	±	2.50
agieval_logiqa_en	0	acc	31.49	±	1.82

mlabonne

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
mlabonne/OmniTruthyBeagle-7B-v0 📄	57.8	45.72	77.49	76.16	50.18
mlabonne/NeuralOmniBeagle-7B-v2 📄	57.75	45.86	77.31	75.34	50.09
mlabonne/OmniBeagle-7B 📄	57.72	45.64	77.48	75.03	50.03
mlabonne/NeuralOmniBeagle-7B 📄	57.71	45.85	77.26	76.06	50.03
mlabonne/NeuralOmni-7B [📄](https://gist.github.com/mlabonne/4b5ecee86d0fd3714ba0cbd

mlabonne

base_model: codellama/CodeLlama-7b-hf
base_model_config: codellama/CodeLlama-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
hub_model_id: EvolCodeLlama-7b

load_in_8bit: false
load_in_4bit: true
strict: false

mlabonne

# Example usage:
# python merge_peft.py --base_model=meta-llama/Llama-2-7b-hf --peft_model=./qlora-out --hub_id=alpaca-qlora

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

import argparse

def get_args():

mlabonne

# Based on younesbelkada/finetune_llama_v2.py
# Install the following libraries:
# pip install accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7 scipy

from dataclasses import dataclass, field
from typing import Optional

import torch
from datasets import load_dataset
from transformers import (

mlabonne

mlabonne

import numpy as np
import matplotlib.pyplot as plt

def softmax(x, temperature=1.0):
    e_x = np.exp(x / temperature)
    return e_x / e_x.sum(axis=0)

logits = np.array([1.5, -1.8, 0.9, -3.2])
temperatures = [1.0, 0.5, 0.1]

mlabonne

import torch
import torch.nn.functional as F
from torch.nn import Linear, Sequential, BatchNorm1d, ReLU, Dropout
from torch_geometric.nn import GATConv
from torch_geometric.nn import global_add_pool


class GAT(torch.nn.Module):
    def __init__(self, dim_h):
        super(GAT, self).__init__()

mlabonne

obs = env_script.reset()
done = False

# 1. Get wood with the CNN
for i in tqdm(range(3000)):
    obs = torch.from_numpy(obs['pov'].transpose(2, 0, 1)[None].astype(np.float32) / 255).cuda()
    probabilities = torch.softmax(model(obs), dim=1)[0].detach().cpu().numpy()
    action = np.random.choice(action_list, p=probabilities)
    obs, reward, done, _ = env_script.step(action)

mlabonne

model = CNN((3, 64, 64), 7).cuda()
model.load_state_dict(torch.load('model.pth'))

env = gym.make('MineRLObtainDiamond-v0')
env1 = Recorder(env, './video', fps=60)
env = ActionShaping(env1)

action_list = np.arange(env.action_space.n)

obs = env.reset()