diff --git a/litgpt/scripts/__init__.py b/litgpt/scripts/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/scripts/convert_hf_checkpoint.py b/litgpt/scripts/convert_hf_checkpoint.py
similarity index 98%
rename from scripts/convert_hf_checkpoint.py
rename to litgpt/scripts/convert_hf_checkpoint.py
index 89a9e7291e..711df4916e 100644
--- a/scripts/convert_hf_checkpoint.py
+++ b/litgpt/scripts/convert_hf_checkpoint.py
@@ -2,9 +2,7 @@
 
 import gc
 import json
-import sys
 from collections import defaultdict
-from dataclasses import asdict
 from functools import partial
 from pathlib import Path
 from typing import Dict, List, Optional, Tuple, Union
@@ -12,10 +10,6 @@
 import torch
 from lightning.fabric.utilities.load import _NotYetLoadedTensor as NotYetLoadedTensor
 
-# support running without installing as a package
-wd = Path(__file__).parent.parent.resolve()
-sys.path.append(str(wd))
-
 from litgpt import Config
 from litgpt.utils import incremental_save, lazy_load, save_config
 
diff --git a/scripts/convert_lit_checkpoint.py b/litgpt/scripts/convert_lit_checkpoint.py
similarity index 98%
rename from scripts/convert_lit_checkpoint.py
rename to litgpt/scripts/convert_lit_checkpoint.py
index 1ff58bf9c2..67bd61fe89 100644
--- a/scripts/convert_lit_checkpoint.py
+++ b/litgpt/scripts/convert_lit_checkpoint.py
@@ -1,7 +1,6 @@
 # Copyright Lightning AI. Licensed under the Apache License 2.0, see LICENSE file.
 
 import gc
-import sys
 from functools import partial
 from pathlib import Path
 from typing import Dict, Optional, Tuple, Union
@@ -9,13 +8,9 @@
 import torch
 from lightning.fabric.utilities.load import _NotYetLoadedTensor as NotYetLoadedTensor
 
-# support running without installing as a package
-wd = Path(__file__).parent.parent.resolve()
-sys.path.append(str(wd))
-
 from litgpt import Config
+from litgpt.scripts.convert_hf_checkpoint import layer_template, load_param
 from litgpt.utils import CLI, incremental_save, lazy_load
-from scripts.convert_hf_checkpoint import layer_template, load_param
 
 
 def copy_weights_falcon(
diff --git a/scripts/convert_pretrained_checkpoint.py b/litgpt/scripts/convert_pretrained_checkpoint.py
similarity index 91%
rename from scripts/convert_pretrained_checkpoint.py
rename to litgpt/scripts/convert_pretrained_checkpoint.py
index 5aa4f2cd51..bcb0149cbf 100644
--- a/scripts/convert_pretrained_checkpoint.py
+++ b/litgpt/scripts/convert_pretrained_checkpoint.py
@@ -1,17 +1,9 @@
 # Copyright Lightning AI. Licensed under the Apache License 2.0, see LICENSE file.
 
-import json
-import shutil
-import sys
-from dataclasses import asdict
 from pathlib import Path
 
 import torch
 
-# support running without installing as a package
-wd = Path(__file__).parent.parent.resolve()
-sys.path.append(str(wd))
-
 from litgpt.utils import CLI, incremental_save, copy_config_files
 
 
diff --git a/scripts/download.py b/litgpt/scripts/download.py
similarity index 95%
rename from scripts/download.py
rename to litgpt/scripts/download.py
index c9711e448a..89614cefac 100644
--- a/scripts/download.py
+++ b/litgpt/scripts/download.py
@@ -1,7 +1,6 @@
 # Copyright Lightning AI. Licensed under the Apache License 2.0, see LICENSE file.
 
 import os
-import sys
 from contextlib import contextmanager
 from pathlib import Path
 from typing import Optional, List, Tuple
@@ -9,12 +8,8 @@
 import torch
 from lightning_utilities.core.imports import RequirementCache
 
-# support running without installing as a package
-wd = Path(__file__).parent.parent.resolve()
-sys.path.append(str(wd))
-
+from litgpt.scripts.convert_hf_checkpoint import convert_hf_checkpoint
 from litgpt.utils import CLI
-from scripts.convert_hf_checkpoint import convert_hf_checkpoint
 
 _SAFETENSORS_AVAILABLE = RequirementCache("safetensors")
 _HF_TRANSFER_AVAILABLE = RequirementCache("hf_transfer")
diff --git a/scripts/merge_lora.py b/litgpt/scripts/merge_lora.py
similarity index 94%
rename from scripts/merge_lora.py
rename to litgpt/scripts/merge_lora.py
index 46ed647485..45627cad93 100644
--- a/scripts/merge_lora.py
+++ b/litgpt/scripts/merge_lora.py
@@ -2,21 +2,15 @@
 
 """This script merges the LoRA weights with the base model"""
 import os
-import sys
 from pathlib import Path
 from typing import Optional, Tuple, Dict, Any
 
-import yaml
-
 import lightning as L
 import torch
-
-# support running without installing as a package
-wd = Path(__file__).parent.parent.resolve()
-sys.path.append(str(wd))
+import yaml
 
 from litgpt.lora import GPT, Config, lora_filter, merge_lora_weights
-from litgpt.utils import CLI, check_valid_checkpoint_dir, get_default_supported_precision, lazy_load
+from litgpt.utils import CLI, check_valid_checkpoint_dir, lazy_load
 
 
 def merge_lora(
diff --git a/litgpt/utils.py b/litgpt/utils.py
index 94ec82ab7f..618775981a 100644
--- a/litgpt/utils.py
+++ b/litgpt/utils.py
@@ -72,7 +72,7 @@ def check_valid_checkpoint_dir(checkpoint_dir: Path) -> None:
     error_message = (
         f"--checkpoint_dir {str(checkpoint_dir.absolute())!r}{problem}."
         "\nFind download instructions at https://github.com/Lightning-AI/litgpt/blob/main/tutorials\n"
-        f"{extra}\nSee all download options by running:\n python scripts/download.py"
+        f"{extra}\nSee all download options by running:\n python litgpt/scripts/download.py"
     )
     print(error_message, file=sys.stderr)
     raise SystemExit(1)
diff --git a/notebooks/falcon-inference.ipynb b/notebooks/falcon-inference.ipynb
index 96bd035d4e..30dc390a92 100644
--- a/notebooks/falcon-inference.ipynb
+++ b/notebooks/falcon-inference.ipynb
@@ -60,7 +60,7 @@
    "outputs": [],
    "source": [
     "# download the weights\n",
-    "!python scripts/download.py --repo_id tiiuae/falcon-7b"
+    "!python litgpt/scripts/download.py --repo_id tiiuae/falcon-7b"
    ]
   },
   {
diff --git a/tests/test_adapter_v2.py b/tests/test_adapter_v2.py
index d7cd1aef74..8bcc0bc9b5 100644
--- a/tests/test_adapter_v2.py
+++ b/tests/test_adapter_v2.py
@@ -186,7 +186,7 @@ def test_against_hf_mixtral():
     from transformers.models.mixtral import MixtralConfig, MixtralForCausalLM
 
     from litgpt.adapter_v2 import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     device = torch.device("cpu")
     dtype = torch.float32
diff --git a/tests/test_convert_hf_checkpoint.py b/tests/test_convert_hf_checkpoint.py
index 40ea1e5837..65141e6113 100644
--- a/tests/test_convert_hf_checkpoint.py
+++ b/tests/test_convert_hf_checkpoint.py
@@ -8,7 +8,7 @@
 
 def test_llama2_70b_conversion():
     from litgpt import Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     shapes = {
         "model.embed_tokens.weight": (32000, 8192),
@@ -102,14 +102,14 @@ def test_llama2_70b_conversion():
 
 
 def test_convert_hf_checkpoint(tmp_path):
-    from scripts.convert_hf_checkpoint import convert_hf_checkpoint
+    from litgpt.scripts.convert_hf_checkpoint import convert_hf_checkpoint
 
     with pytest.raises(ValueError, match="to contain .bin"):
         convert_hf_checkpoint(checkpoint_dir=tmp_path, model_name="pythia-14m")
 
     bin_file = tmp_path / "foo.bin"
     bin_file.touch()
-    with mock.patch("scripts.convert_hf_checkpoint.lazy_load") as load:
+    with mock.patch("litgpt.scripts.convert_hf_checkpoint.lazy_load") as load:
         convert_hf_checkpoint(checkpoint_dir=tmp_path, model_name="pythia-14m")
     load.assert_called_with(bin_file)
 
diff --git a/tests/test_convert_lit_checkpoint.py b/tests/test_convert_lit_checkpoint.py
index 851bf5928d..2787f78018 100644
--- a/tests/test_convert_lit_checkpoint.py
+++ b/tests/test_convert_lit_checkpoint.py
@@ -16,7 +16,7 @@
 
 def test_convert_lit_checkpoint(tmp_path):
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import convert_lit_checkpoint
+    from litgpt.scripts.convert_lit_checkpoint import convert_lit_checkpoint
 
     ours_config = Config.from_name("Llama-2-7b-hf", block_size=8, n_layer=2, n_embd=32, n_head=2, padding_multiple=128)
     ours_model = GPT(ours_config)
@@ -43,7 +43,7 @@ def test_against_falcon_40b():
     from transformers.models.falcon.modeling_falcon import FalconForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_falcon as copy_to_theirs
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_falcon as copy_to_theirs
 
     ours_config = Config.from_name("falcon-40b", n_layer=2, n_head=8, n_query_groups=4, n_embd=32)
     theirs_config = FalconConfig(
@@ -78,7 +78,7 @@ def test_against_original_gpt_neox():
     from transformers import GPTNeoXConfig, GPTNeoXForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_gpt_neox as copy_to_theirs
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_gpt_neox as copy_to_theirs
 
     ours_config = Config(block_size=64, vocab_size=100, n_layer=4, n_head=8, n_embd=16)
     assert ours_config.padded_vocab_size == 512
@@ -123,7 +123,7 @@ def test_against_hf_llama2(ours_kwargs):
     from transformers.models.llama.modeling_llama import LlamaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_llama
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_llama
 
     ours_config = Config.from_name(
         padded_vocab_size=10000, n_layer=2, n_head=8, n_embd=32, intermediate_size=86, **ours_kwargs
@@ -161,7 +161,7 @@ def test_against_mixtral():
     from transformers.models.mixtral import MixtralConfig, MixtralForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_llama
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_llama
 
     ours_config = Config.from_name(
         "Mixtral-8x7B-Instruct-v0.1",
@@ -208,7 +208,7 @@ def test_against_original_open_llama_3b():
     from transformers.models.llama.modeling_llama import LlamaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_llama
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_llama
 
     ours_config = Config.from_name("open_llama_3b", n_layer=2, n_head=8, n_embd=32, intermediate_size=86)
     T = 5
@@ -250,7 +250,7 @@ def test_against_hf_phi_1_5():
             urlretrieve(url=url, filename=file_path)
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_phi
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_phi
     from reference_models.configuration_phi import PhiConfig
     from reference_models.original_phi_1_5 import PhiForCausalLM
 
@@ -300,7 +300,7 @@ def test_against_hf_phi_2():
             urlretrieve(url=url, filename=file_path)
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_phi
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_phi
     from reference_models.configuration_phi import PhiConfig
     from reference_models.original_phi_2 import PhiForCausalLM
 
@@ -341,7 +341,7 @@ def test_against_original_stablelm_zephyr_3b():
     from transformers import AutoConfig, AutoModelForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_llama
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_llama
 
     T = 5
     ours_config = Config.from_name("stablelm-zephyr-3b", n_layer=2, n_head=16, n_embd=32, intermediate_size=86)
@@ -395,7 +395,7 @@ def test_against_original_gemma(model_name, device, dtype):
     from transformers.models.gemma.modeling_gemma import GemmaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_lit_checkpoint import copy_weights_llama
+    from litgpt.scripts.convert_lit_checkpoint import copy_weights_llama
 
     torch.set_default_dtype(dtype)
 
@@ -436,7 +436,7 @@ def test_against_original_gemma(model_name, device, dtype):
 
 
 def test_check_conversion_supported_adapter():
-    from scripts.convert_lit_checkpoint import check_conversion_supported
+    from litgpt.scripts.convert_lit_checkpoint import check_conversion_supported
 
     lit_weights = {"some.key.name": ANY, "error.key.gating_factor": ANY}
     with pytest.raises(NotImplementedError, match="Converting adapter"):
@@ -448,7 +448,7 @@ def test_check_conversion_supported_adapter():
 
 
 def test_check_conversion_supported_lora():
-    from scripts.convert_lit_checkpoint import check_conversion_supported
+    from litgpt.scripts.convert_lit_checkpoint import check_conversion_supported
 
     lit_weights = {"some.key.name": ANY, "error.key.lora": ANY}
     with pytest.raises(ValueError, match=r"LoRA.*cannot be converted"):
@@ -457,7 +457,7 @@ def test_check_conversion_supported_lora():
 
 def test_qkv_split():
     from litgpt import Config
-    from scripts.convert_lit_checkpoint import qkv_split
+    from litgpt.scripts.convert_lit_checkpoint import qkv_split
 
     # MHA
     config = Config(n_embd=4, n_head=4)
diff --git a/tests/test_convert_pretrained_checkpoint.py b/tests/test_convert_pretrained_checkpoint.py
index 195d79bc52..d95260f0d6 100644
--- a/tests/test_convert_pretrained_checkpoint.py
+++ b/tests/test_convert_pretrained_checkpoint.py
@@ -6,7 +6,7 @@
 
 
 def test_convert_pretrained_checkpoint(tmp_path, fake_checkpoint_dir):
-    from scripts.convert_pretrained_checkpoint import convert_checkpoint
+    from litgpt.scripts.convert_pretrained_checkpoint import convert_checkpoint
 
     # Pretend we made a checkpoint from pretraining
     pretrained_checkpoint = {
diff --git a/tests/test_generate_sequentially.py b/tests/test_generate_sequentially.py
index da0a1507bf..32f41e01d6 100644
--- a/tests/test_generate_sequentially.py
+++ b/tests/test_generate_sequentially.py
@@ -275,7 +275,7 @@ def test_model_forward_hooks():
 @RunIf(min_cuda_gpus=2)
 def test_base_with_sequentially(tmp_path):
     from litgpt import GPT, Config
-    from scripts.download import download_from_hub
+    from litgpt.scripts.download import download_from_hub
 
     # download the tokenizer
     download_from_hub(repo_id="EleutherAI/pythia-14m", tokenizer_only=True, checkpoint_dir=tmp_path)
diff --git a/tests/test_generate_tp.py b/tests/test_generate_tp.py
index 6451f1dd10..f1da3e2f57 100644
--- a/tests/test_generate_tp.py
+++ b/tests/test_generate_tp.py
@@ -109,7 +109,7 @@ def test_tensor_parallel_llama(name, expected):
 @RunIf(min_cuda_gpus=2)
 def test_tp(tmp_path):
     from litgpt import GPT, Config
-    from scripts.download import download_from_hub
+    from litgpt.scripts.download import download_from_hub
 
     # download the tokenizer
     download_from_hub(repo_id="EleutherAI/pythia-14m", tokenizer_only=True, checkpoint_dir=tmp_path)
diff --git a/tests/test_lm_eval_harness.py b/tests/test_lm_eval_harness.py
index ca738253ec..9acd661e55 100644
--- a/tests/test_lm_eval_harness.py
+++ b/tests/test_lm_eval_harness.py
@@ -20,7 +20,7 @@ def test_run_eval(tmp_path, float_like):
     from eval.lm_eval_harness import EvalHarnessBase
     from litgpt.model import GPT
     from litgpt.tokenizer import Tokenizer
-    from scripts.download import download_from_hub
+    from litgpt.scripts.download import download_from_hub
 
     fabric = Fabric(devices=1)
     with fabric.init_module():
diff --git a/tests/test_lora.py b/tests/test_lora.py
index 43318c209d..37c3777c81 100644
--- a/tests/test_lora.py
+++ b/tests/test_lora.py
@@ -545,7 +545,7 @@ def test_against_hf_mixtral():
     from transformers.models.mixtral import MixtralConfig, MixtralForCausalLM
 
     from litgpt.lora import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     device = torch.device("cpu")
     dtype = torch.float32
diff --git a/tests/test_merge_lora.py b/tests/test_merge_lora.py
index eec6df0a44..fee5d02b27 100644
--- a/tests/test_merge_lora.py
+++ b/tests/test_merge_lora.py
@@ -20,7 +20,7 @@ def test_merge_lora(tmp_path, fake_checkpoint_dir):
     from litgpt.lora import GPT as LoRAGPT
     from litgpt.lora import lora_filter
     from litgpt.model import GPT
-    from scripts.merge_lora import merge_lora
+    from litgpt.scripts.merge_lora import merge_lora
 
     pretrained_checkpoint_dir = tmp_path / "pretrained"
     lora_checkpoint_dir = tmp_path / "lora"
@@ -74,7 +74,7 @@ def test_merge_lora(tmp_path, fake_checkpoint_dir):
 
 
 def test_load_lora_metadata(fake_checkpoint_dir):
-    from scripts.merge_lora import load_lora_metadata
+    from litgpt.scripts.merge_lora import load_lora_metadata
 
     assert not (fake_checkpoint_dir / "hyperparameters.yaml").is_file()
     with pytest.raises(FileNotFoundError, match="missing a `hyperparameters.yaml` file"):
diff --git a/tests/test_model.py b/tests/test_model.py
index 6a176008f5..2919e51fe2 100644
--- a/tests/test_model.py
+++ b/tests/test_model.py
@@ -44,7 +44,7 @@ def test_against_gpt_neox_model(rotary_pct, batch_size, n_embd, parallel_residua
     from transformers import GPTNeoXConfig, GPTNeoXForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_gpt_neox
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_gpt_neox
 
     torch.set_default_dtype(dtype)
 
@@ -117,7 +117,7 @@ def test_against_hf_falcon(kwargs, device, dtype):
     from transformers.models.falcon import FalconConfig, FalconForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_falcon
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_falcon
 
     torch.set_default_dtype(dtype)
 
@@ -169,7 +169,7 @@ def test_against_original_open_llama_3b(device, dtype):
     from transformers.models.llama.modeling_llama import LlamaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     torch.set_default_dtype(dtype)
 
@@ -225,7 +225,7 @@ def test_against_hf_llama2(ours_kwargs, device, dtype):
     from transformers.models.llama.modeling_llama import LlamaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     torch.set_default_dtype(dtype)
 
@@ -290,7 +290,7 @@ def test_against_hf_phi_1_5(device, dtype):
     from reference_models.original_phi_1_5 import PhiForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_phi
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_phi
 
     torch.set_default_dtype(dtype)
 
@@ -352,7 +352,7 @@ def test_against_hf_phi_2(device, dtype):
     from reference_models.original_phi_2 import PhiForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_phi
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_phi
 
     torch.set_default_dtype(dtype)
 
@@ -408,7 +408,7 @@ def test_against_hf_mistral(device, dtype):
     from transformers.models.mistral.modeling_mistral import MistralForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     torch.set_default_dtype(dtype)
 
@@ -455,7 +455,7 @@ def test_against_hf_mixtral():
     from transformers.models.mixtral import MixtralConfig, MixtralForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     device = torch.device("cpu")
     dtype = torch.float32
@@ -520,7 +520,7 @@ def test_against_original_stablelm_zephyr_3b(device, dtype):
     from transformers import AutoConfig, AutoModelForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     torch.set_default_dtype(dtype)
 
@@ -577,7 +577,7 @@ def test_against_original_gemma(model_name, device, dtype):
     from transformers.models.gemma.modeling_gemma import GemmaForCausalLM
 
     from litgpt import GPT, Config
-    from scripts.convert_hf_checkpoint import copy_weights_hf_llama
+    from litgpt.scripts.convert_hf_checkpoint import copy_weights_hf_llama
 
     torch.set_default_dtype(dtype)
 
diff --git a/tests/test_utils.py b/tests/test_utils.py
index d39f1d1162..8e4068fe72 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -43,7 +43,7 @@ def test_check_valid_checkpoint_dir(tmp_path):
 Find download instructions at https://github.com/Lightning-AI/litgpt/blob/main/tutorials
 
 See all download options by running:
- python scripts/download.py
+ python litgpt/scripts/download.py
     """.strip()
     assert out == expected
 
@@ -57,7 +57,7 @@ def test_check_valid_checkpoint_dir(tmp_path):
 Find download instructions at https://github.com/Lightning-AI/litgpt/blob/main/tutorials
 
 See all download options by running:
- python scripts/download.py
+ python litgpt/scripts/download.py
     """.strip()
     assert out == expected
 
@@ -75,7 +75,7 @@ def test_check_valid_checkpoint_dir(tmp_path):
  --checkpoint_dir '{str(checkpoint_dir.absolute())}'
 
 See all download options by running:
- python scripts/download.py
+ python litgpt/scripts/download.py
     """.strip()
     assert out == expected
 
diff --git a/tutorials/convert_hf_checkpoint.md b/tutorials/convert_hf_checkpoint.md
index 6c1e45e36c..cc26a46587 100644
--- a/tutorials/convert_hf_checkpoint.md
+++ b/tutorials/convert_hf_checkpoint.md
@@ -1,9 +1,9 @@
 # Converting Hugging Face Transformers to LitGPT weights
 
-By default, the `scripts/download.py` script converts the downloaded HF checkpoint files into a LitGPT compatible format after downloading. For example,
+By default, the `litgpt/scripts/download.py` script converts the downloaded HF checkpoint files into a LitGPT compatible format after downloading. For example,
 
 ```bash
-python scripts/download.py --repo_id EleutherAI/pythia-14m
+python litgpt/scripts/download.py --repo_id EleutherAI/pythia-14m
 ```
 
 creates the following files:
@@ -23,12 +23,12 @@ checkpoints/
 
 
 
-To disable the automatic conversion, which is useful for development and debugging purposes, you can run the `scripts/download.py` with the `--convert_checkpoint false` flag. This will only download the checkpoint files but do not convert them for use in LitGPT:
+To disable the automatic conversion, which is useful for development and debugging purposes, you can run the `litgpt/scripts/download.py` with the `--convert_checkpoint false` flag. This will only download the checkpoint files but do not convert them for use in LitGPT:
 
 ```bash
 rm -rf checkpoints/EleutherAI/pythia-14m 
 
-python scripts/download.py \
+python litgpt/scripts/download.py \
   --repo_id EleutherAI/pythia-14m \
   --convert_checkpoint false
   
@@ -46,10 +46,10 @@ ls checkpoints/EleutherAI/pythia-14m
         └── tokenizer_config.json
 ```
 
-The required files `lit_config.json` and `lit_model.pth` files can then be manually generated via the `scripts/convert_hf_checkpoint.py` script:
+The required files `lit_config.json` and `lit_model.pth` files can then be manually generated via the `litgpt/scripts/convert_hf_checkpoint.py` script:
 
 ```bash
-python scripts/convert_hf_checkpoint.py \
+python litgpt/scripts/convert_hf_checkpoint.py \
   --checkpoint_dir checkpoints/EleutherAI/pythia-14m
 ```
 
diff --git a/tutorials/convert_lit_models.md b/tutorials/convert_lit_models.md
index 53ba412798..d4b88cf6fd 100644
--- a/tutorials/convert_lit_models.md
+++ b/tutorials/convert_lit_models.md
@@ -1,11 +1,11 @@
 ## Converting LitGPT weights to Hugging Face Transformers
 
-LitGPT weights need to be converted to a format that Hugging Face understands with a [conversion script](../scripts/convert_lit_checkpoint.py) before our scripts can run.
+LitGPT weights need to be converted to a format that Hugging Face understands with a [conversion script](../litgpt/scripts/convert_lit_checkpoint.py) before our scripts can run.
 
 We provide a helpful script to convert models LitGPT models back to their equivalent Hugging Face Transformers format:
 
 ```sh
-python scripts/convert_lit_checkpoint.py \
+python litgpt/scripts/convert_lit_checkpoint.py \
     --checkpoint_path checkpoints/repo_id/lit_model.pth \
     --output_path output_path/converted.pth \
     --config_path checkpoints/repo_id/config.json
@@ -46,7 +46,7 @@ model = AutoModel.from_pretrained("online_repo_id", state_dict=state_dict)
 
 ### Merging LoRA weights
 
-Please note that if you want to convert a model that has been fine-tuned using an adapter like LoRA, these weights should be [merged](../scripts/merge_lora.py) to the checkpoint prior to converting.
+Please note that if you want to convert a model that has been fine-tuned using an adapter like LoRA, these weights should be [merged](../litgpt/scripts/merge_lora.py) to the checkpoint prior to converting.
 
 ```sh
 python scripts/merge_lora.py \
@@ -70,12 +70,12 @@ export repo_id=TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 
 Instead of using TinyLlama, you can replace the `repo_id` target with any other model repository 
 specifier that is currently supported by LitGPT. You can get a list of supported repository specifier
-by running `scripts/download.py` without any additional arguments.
+by running `litgpt/scripts/download.py` without any additional arguments.
 
 Then, we download the model we specified via `$repo_id` above:
 
 ```bash
-python scripts/download.py --repo_id $repo_id
+python litgpt/scripts/download.py --repo_id $repo_id
 ```
 
 2. Finetune the model:
@@ -104,7 +104,7 @@ python scripts/merge_lora.py \
 4. Convert the finetuning model back into a HF format:
 
 ```bash
-python scripts/convert_lit_checkpoint.py \
+python litgpt/scripts/convert_lit_checkpoint.py \
    --checkpoint_path $finetuned_dir/final/lit_model.pth \
    --output_path out/hf-tinyllama/converted_model.pth \
    --config_path checkpoints/$repo_id/lit_config.json 
diff --git a/tutorials/download_code_llama.md b/tutorials/download_code_llama.md
index a5075a1086..fb467557cb 100644
--- a/tutorials/download_code_llama.md
+++ b/tutorials/download_code_llama.md
@@ -13,7 +13,7 @@ All models were  trained on 16,000 token contexts and support generations with u
 To see all the available checkpoints, run:
 
 ```bash
-python scripts/download.py | grep CodeLlama
+python litgpt/scripts/download.py | grep CodeLlama
 ```
 
 which will print
@@ -38,7 +38,7 @@ In order to use a specific checkpoint, for instance [CodeLlama-7b-Python-hf](htt
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id codellama/CodeLlama-7b-Python-hf
+python litgpt/scripts/download.py --repo_id codellama/CodeLlama-7b-Python-hf
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_dolly.md b/tutorials/download_dolly.md
index 1a17dd5d31..103d322f0c 100644
--- a/tutorials/download_dolly.md
+++ b/tutorials/download_dolly.md
@@ -12,7 +12,7 @@ For detailed info on the models, their training, and their behavior, please see
 To see all the available checkpoints for Dolly, run:
 
 ```bash
-python scripts/download.py | grep dolly
+python litgpt/scripts/download.py | grep dolly
 ```
 
 which will print
@@ -28,7 +28,7 @@ In order to use a specific Dolly checkpoint, for instance [dolly-v2-3b](https://
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id databricks/dolly-v2-3b
+python litgpt/scripts/download.py --repo_id databricks/dolly-v2-3b
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_falcon.md b/tutorials/download_falcon.md
index 18c28b4d26..4346ff1ea5 100644
--- a/tutorials/download_falcon.md
+++ b/tutorials/download_falcon.md
@@ -9,7 +9,7 @@ The first Falcon release includes a base model and an instruction tuned model of
 To see all the available checkpoints for Falcon, run:
 
 ```bash
-python scripts/download.py | grep falcon
+python litgpt/scripts/download.py | grep falcon
 ```
 
 which will print
@@ -28,7 +28,7 @@ In order to use a specific Falcon checkpoint, for instance [falcon-7b](https://h
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id tiiuae/falcon-7b
+python litgpt/scripts/download.py --repo_id tiiuae/falcon-7b
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_freewilly_2.md b/tutorials/download_freewilly_2.md
index f228533ec6..50fd020941 100644
--- a/tutorials/download_freewilly_2.md
+++ b/tutorials/download_freewilly_2.md
@@ -7,7 +7,7 @@ FreeWilly2 leverages the Llama 2 70B foundation model to reach a performance tha
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id stabilityai/FreeWilly2
+python litgpt/scripts/download.py --repo_id stabilityai/FreeWilly2
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_function_calling_llama_2.md b/tutorials/download_function_calling_llama_2.md
index a275205bd4..c084f1b815 100644
--- a/tutorials/download_function_calling_llama_2.md
+++ b/tutorials/download_function_calling_llama_2.md
@@ -10,7 +10,7 @@ In order to use the checkpoint, download the weights and convert the checkpoint
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id Trelis/Llama-2-7b-chat-hf-function-calling-v2
+python litgpt/scripts/download.py --repo_id Trelis/Llama-2-7b-chat-hf-function-calling-v2
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_gemma.md b/tutorials/download_gemma.md
index d929c4662d..b7089e8c5b 100644
--- a/tutorials/download_gemma.md
+++ b/tutorials/download_gemma.md
@@ -8,7 +8,7 @@ For more information, please see the [technical report](https://storage.googleap
 To see all the available checkpoints, run:
 
 ```bash
-python scripts/download.py | grep gemma
+python litgpt/scripts/download.py | grep gemma
 ```
 
 which will print
@@ -30,7 +30,7 @@ After access is granted, you can find your HF hub token in <https://huggingface.
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id google/gemma-2b --access_token your_hf_token
+python litgpt/scripts/download.py --repo_id google/gemma-2b --access_token your_hf_token
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_llama_2.md b/tutorials/download_llama_2.md
index adddbde72f..15b0cb08a1 100644
--- a/tutorials/download_llama_2.md
+++ b/tutorials/download_llama_2.md
@@ -13,7 +13,7 @@ Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as
 To see all the available checkpoints, run:
 
 ```bash
-python scripts/download.py | grep Llama-2
+python litgpt/scripts/download.py | grep Llama-2
 ```
 
 which will print
@@ -35,7 +35,7 @@ After access is granted, you can find your HF hub token in <https://huggingface.
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id meta-llama/Llama-2-7b-chat-hf --access_token your_hf_token
+python litgpt/scripts/download.py --repo_id meta-llama/Llama-2-7b-chat-hf --access_token your_hf_token
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_longchat.md b/tutorials/download_longchat.md
index 79f921fa23..465708414c 100644
--- a/tutorials/download_longchat.md
+++ b/tutorials/download_longchat.md
@@ -6,7 +6,7 @@ The technique used to extend the context length is described in [this blogpost](
 To see all the available checkpoints, run:
 
 ```bash
-python scripts/download.py | grep longchat
+python litgpt/scripts/download.py | grep longchat
 ```
 
 which will print
@@ -21,7 +21,7 @@ In order to use a specific checkpoint, for instance [longchat-7b-16k](https://hu
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id lmsys/longchat-7b-16k
+python litgpt/scripts/download.py --repo_id lmsys/longchat-7b-16k
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_mistral.md b/tutorials/download_mistral.md
index 57a6ba4ecd..aab867a78a 100644
--- a/tutorials/download_mistral.md
+++ b/tutorials/download_mistral.md
@@ -16,7 +16,7 @@ Details about the data used to train the model or training procedure have not be
 To see all the available checkpoints, run:
 
 ```bash
-python scripts/download.py | grep -E 'Mistral|Mixtral'
+python litgpt/scripts/download.py | grep -E 'Mistral|Mixtral'
 ```
 
 which will print
@@ -34,7 +34,7 @@ In order to use the Mistral 7B model checkpoint, which requires about 14 GB of d
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id mistralai/Mistral-7B-Instruct-v0.2
+python litgpt/scripts/download.py --repo_id mistralai/Mistral-7B-Instruct-v0.2
 ```
 
 You're done! To execute the model just run:
@@ -57,7 +57,7 @@ In order to use the Mixtral 7B model checkpoint, which requires about 94 GB of d
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id mistralai/Mixtral-8x7B-Instruct-v0.1
+python litgpt/scripts/download.py --repo_id mistralai/Mixtral-8x7B-Instruct-v0.1
 ```
 
 Due to the size of the model, currently only the multi-device sequential generation script can handle it.
diff --git a/tutorials/download_openllama.md b/tutorials/download_openllama.md
index 3cf6c4064e..6dbaba95a1 100644
--- a/tutorials/download_openllama.md
+++ b/tutorials/download_openllama.md
@@ -7,7 +7,7 @@ The weights can serve as the drop in replacement of LLaMA in existing implementa
 To see all the available checkpoints for Open LLaMA, run:
 
 ```bash
-python scripts/download.py | grep open_llama
+python litgpt/scripts/download.py | grep open_llama
 ```
 
 which will print
@@ -23,9 +23,7 @@ In order to use a specific OpenLLaMA checkpoint, for instance [open_llama_3b](ht
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id openlm-research/open_llama_3b
-
-python scripts/convert_hf_checkpoint.py --checkpoint_dir checkpoints/openlm-research/open_llama_3b
+python litgpt/scripts/download.py --repo_id openlm-research/open_llama_3b
 ```
 
 By default, the convert_hf_checkpoint step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_phi.md b/tutorials/download_phi.md
index 8dd0850218..c2c6f98523 100644
--- a/tutorials/download_phi.md
+++ b/tutorials/download_phi.md
@@ -10,7 +10,7 @@ To download the model weights and convert them to the litgpt format, run
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id microsoft/phi-2
+python litgpt/scripts/download.py --repo_id microsoft/phi-2
 ```
 
 > [!WARNING]
@@ -61,7 +61,7 @@ In order to use the phi-1.5 model checkpoint, which requires about 3 Gb of disk
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id microsoft/phi-1_5
+python litgpt/scripts/download.py --repo_id microsoft/phi-1_5
 ```
 
 You're done! To execute the model just run:
diff --git a/tutorials/download_pythia.md b/tutorials/download_pythia.md
index 653b16c980..b5c158b575 100644
--- a/tutorials/download_pythia.md
+++ b/tutorials/download_pythia.md
@@ -8,7 +8,7 @@ It includes a suite of 8 checkpoints (weights) on 2 different datasets: [The Pil
 To see all the available checkpoints for Pythia, run:
 
 ```bash
-python scripts/download.py | grep pythia
+python litgpt/scripts/download.py | grep pythia
 ```
 
 which will print
@@ -39,7 +39,7 @@ In order to use a specific Pythia checkpoint, for instance [pythia-1b](https://h
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id EleutherAI/pythia-1b
+python litgpt/scripts/download.py --repo_id EleutherAI/pythia-1b
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_redpajama_incite.md b/tutorials/download_redpajama_incite.md
index 456d704024..c7648e5f45 100644
--- a/tutorials/download_redpajama_incite.md
+++ b/tutorials/download_redpajama_incite.md
@@ -7,7 +7,7 @@ The release includes a base model, a chat fine-tuned model, and an instruction t
 To see all the available checkpoints for RedPajama-INCITE, run:
 
 ```bash
-python scripts/download.py | grep RedPajama
+python litgpt/scripts/download.py | grep RedPajama
 ```
 
 which will print
@@ -29,7 +29,7 @@ In order to use a specific RedPajama-INCITE checkpoint, for instance [RedPajama-
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id togethercomputer/RedPajama-INCITE-Base-3B-v1
+python litgpt/scripts/download.py --repo_id togethercomputer/RedPajama-INCITE-Base-3B-v1
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_stablecode.md b/tutorials/download_stablecode.md
index 734c30d0c5..1e6a9b7b4b 100644
--- a/tutorials/download_stablecode.md
+++ b/tutorials/download_stablecode.md
@@ -11,7 +11,7 @@ For more info on the models, please visit the [StableCode repository](https://hu
 To see all the available checkpoints for StableCode, run:
 
 ```bash
-python scripts/download.py | grep -E "stable-?code"
+python litgpt/scripts/download.py | grep -E "stable-?code"
 ```
 
 which will print:
@@ -29,7 +29,7 @@ In order to use a specific StableCode checkpoint, for instance [stable-code-3b](
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
 export repo_id=stabilityai/stable-code-3b
-python scripts/download.py --repo_id $repo_id
+python litgpt/scripts/download.py --repo_id $repo_id
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_stablelm.md b/tutorials/download_stablelm.md
index 5f8d922eca..5aef6fe93f 100644
--- a/tutorials/download_stablelm.md
+++ b/tutorials/download_stablelm.md
@@ -5,7 +5,7 @@ StableLM is a family of generative language models trained by StabilityAI.
 To see all the available checkpoints for StableLM, run:
 
 ```bash
-python scripts/download.py | grep stablelm
+python litgpt/scripts/download.py | grep stablelm
 ```
 
 which will print:
@@ -24,7 +24,7 @@ In order to use a specific StableLM checkpoint, for instance [stablelm-base-alph
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id stabilityai/stablelm-base-alpha-3b
+python litgpt/scripts/download.py --repo_id stabilityai/stablelm-base-alpha-3b
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
@@ -56,8 +56,7 @@ In order to use a specific StableLM checkpoint, for instance [StableLM Zephyr 3B
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
 export repo_id=stabilityai/stablelm-zephyr-3b
-python scripts/download.py --repo_id $repo_id
-python scripts/convert_hf_checkpoint.py --checkpoint_dir checkpoints/$repo_id
+python litgpt/scripts/download.py --repo_id $repo_id
 ```
 
 By default, the `convert_hf_checkpoint` step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/download_tinyllama.md b/tutorials/download_tinyllama.md
index 5723d4d6e1..681b8c99cf 100644
--- a/tutorials/download_tinyllama.md
+++ b/tutorials/download_tinyllama.md
@@ -8,7 +8,7 @@ There are two version of TinyLlama available: a base one and a fine-tuned "Chat"
 To see all available versions, run:
 
 ```bash
-python scripts/download.py | grep TinyLlama
+python litgpt/scripts/download.py | grep TinyLlama
 ```
 
 which will print
@@ -23,7 +23,7 @@ In order to use a specific checkpoint, for instance [TinyLlama 1.1B base model](
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+python litgpt/scripts/download.py --repo_id TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 ```
 
 -----
@@ -32,13 +32,13 @@ With the `Chat` version of the model, the download and conversion procedures are
 As this version of the model is stored in `safetensor` format, to download it an additional flag is required:
 
 ```bash
-python scripts/download.py --repo_id TinyLlama/TinyLlama-1.1B-Chat-v1.0
+python litgpt/scripts/download.py --repo_id TinyLlama/TinyLlama-1.1B-Chat-v1.0
 ```
 
 The model is shipped in `bfloat16` format, so if your hardware doesn't support it, you can provide `--dtype` argument during model conversion. For example we can convert the weights into `float32` format:
 
 ```bash
-python scripts/download.py \
+python litgpt/scripts/download.py \
     --repo_id checkpoints/TinyLlama/TinyLlama-1.1B-Chat-v1.0 --dtype=float32
 ```
 
diff --git a/tutorials/download_vicuna.md b/tutorials/download_vicuna.md
index 97e73091e4..11d24a33eb 100644
--- a/tutorials/download_vicuna.md
+++ b/tutorials/download_vicuna.md
@@ -5,7 +5,7 @@ Vicuna is an open-source family of chatbots trained by fine-tuning LLaMA on user
 To see all the available checkpoints for Vicuna, run:
 
 ```bash
-python scripts/download.py | grep vicuna
+python litgpt/scripts/download.py | grep vicuna
 ```
 
 which will print
@@ -25,7 +25,7 @@ In order to use a specific Vicuna checkpoint, for instance [vicuna-7b-v1.5](http
 ```bash
 pip install 'huggingface_hub[hf_transfer] @ git+https://github.com/huggingface/huggingface_hub'
 
-python scripts/download.py --repo_id lmsys/vicuna-7b-v1.5
+python litgpt/scripts/download.py --repo_id lmsys/vicuna-7b-v1.5
 ```
 
 By default, the checkpoint conversion step will use the data type of the HF checkpoint's parameters. In cases where RAM
diff --git a/tutorials/pretrain_tinyllama.md b/tutorials/pretrain_tinyllama.md
index 8438fe3a64..8fb6c2a7fd 100644
--- a/tutorials/pretrain_tinyllama.md
+++ b/tutorials/pretrain_tinyllama.md
@@ -55,7 +55,7 @@ pip install 'lightning[data]' torchmetrics tensorboard sentencepiece zstandard p
 You will need to have the tokenizer config available:
 
 ```bash
-python scripts/download.py \
+python litgpt/scripts/download.py \
    --repo_id meta-llama/Llama-2-7b-hf \
    --access_token your_hf_token \
    --tokenizer_only true
@@ -118,7 +118,7 @@ The currently supported model names are contained in the [config.py](https://git
 You can
 
 1) either search this file for lines containing "name =",
-2) or run `python scripts/download.py` without additional command line arguments
+2) or run `python litgpt/scripts/download.py` without additional command line arguments
 
 Keep in mind that training with a single machine will take weeks. To speed up the process, you'll need access to a cluster.
 Once you're in a cluster, you can follow [these instructions](https://lightning.ai/docs/fabric/stable/fundamentals/launch.html#launch-on-a-cluster)
@@ -156,7 +156,7 @@ python litgpt/pretrain.py \
 After training is completed, you can convert the checkpoint to a format that can be loaded for evaluation, inference, finetuning etc.
 
 ```bash
-python scripts/convert_pretrained_checkpoint.py \
+python litgpt/scripts/convert_pretrained_checkpoint.py \
   --checkpoint_dir out/pretrain/tiny-llama/step-00060500 \
   --output_dir checkpoints/tiny-llama/final
 ```