Litgpt

What's Changed
* Apply prompt style for tp.py and sequentially.py by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1629
* Fix prompt docstring in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1635
* Update windows cpu-tests.yml by rasbt in https://github.com/Lightning-AI/litgpt/pull/1630
* Remove NumPy < 2.0 pin by rasbt in https://github.com/Lightning-AI/litgpt/pull/1631
* Fix kv-cache issue in Python API streaming mode by rasbt in https://github.com/Lightning-AI/litgpt/pull/1633
* Updates installation requirements to install minimal required packages for basic use by rasbt in https://github.com/Lightning-AI/litgpt/pull/1634
* Faster safetensors conversion when downloading model by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1624
* Add Sebastian as code owner by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1641
* Add missing super() call in data modules by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1639
* Update Lightning version to 2.4.0 pre by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1640
* Add tunable kvcache with error handling for nonsense inputs. by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1636
* Use Python API in serve code by rasbt in https://github.com/Lightning-AI/litgpt/pull/1644
* Fix autodownload + conversion issue by rasbt in https://github.com/Lightning-AI/litgpt/pull/1645
* Properly clear kv-cache by rasbt in https://github.com/Lightning-AI/litgpt/pull/1647
* Fix error raising where max_returned_tokens > max_seq_length_setting by rasbt in https://github.com/Lightning-AI/litgpt/pull/1648
* Add quantization support to litgpt serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1646
* Bump for 0.4.7 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1649


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.6...v0.4.7

What's Changed
* Change default top_k to 50 everywhere for consistency by rasbt in https://github.com/Lightning-AI/litgpt/pull/1592
* Fix kv-cache clearing in Python API and Serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1596
* dynamic KV Cache batching by aniketmaurya in https://github.com/Lightning-AI/litgpt/pull/1600
* Remove non-used eos_id in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1594
* Add quantization test and revert lightning version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1605
* Dynamically set kv-cache size in serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1602
* Update LitData version and restore previous LitData assertions in tests by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1609
* Gemma 2: `9b` and `27b` versions by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1545
* Update config hub table qlora sections by rasbt in https://github.com/Lightning-AI/litgpt/pull/1611
* max_returned_tokens -> max_new_tokens by rasbt in https://github.com/Lightning-AI/litgpt/pull/1612
* Add warning about pretrain preprocessing by rasbt in https://github.com/Lightning-AI/litgpt/pull/1618
* Print warning about unsupported repo_ids by rasbt in https://github.com/Lightning-AI/litgpt/pull/1617
* Restore capability to load alternative weights by rasbt in https://github.com/Lightning-AI/litgpt/pull/1620
* Enable unbalanced number of layers in sequential generation by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1623
* Llama 3.1 8B and 70B checkpoints by rasbt in https://github.com/Lightning-AI/litgpt/pull/1619
* Add Llama 3.1 405B config by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1622
* Bumb version to 0.4.6 for next release (Gemma 2 and Llama 3.1) by rasbt in https://github.com/Lightning-AI/litgpt/pull/1626


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.5...v0.4.6

What's Changed
* Update LitData to latest version 0.2.16 by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1573
* Fixed warning during model download and conversion. by bhargavyagnik in https://github.com/Lightning-AI/litgpt/pull/1574
* Bump lightning version by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1579
* chat/base.py: extend checkpoint_dir before accessing it by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1575
* Chat: dynamically set kv-cache size by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1583
* Add slow interconnect warning by rasbt in https://github.com/Lightning-AI/litgpt/pull/1577
* Mathstral checkpoints by rasbt in https://github.com/Lightning-AI/litgpt/pull/1587
* Make sure quantization is used correctly by rasbt in https://github.com/Lightning-AI/litgpt/pull/1585
* Improve mathstral tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1589
* Fixes an issue where the LitGPT Python API was consuming too much memory by rasbt in https://github.com/Lightning-AI/litgpt/pull/1590
* Increase version number for 0.4.5 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1591

New Contributors
* bhargavyagnik made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1574

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.4...v0.4.5

What's Changed
* Tokenizer: fix issue when decoding a single token at a time by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1559
* Filter out false positive PyTorch scheduler warning by rasbt in https://github.com/Lightning-AI/litgpt/pull/1562
* Add an explanation on how to evaluate on a custom test set by rasbt in https://github.com/Lightning-AI/litgpt/pull/1564
* Remove duplicated bos_token for CodeLlama by alealv in https://github.com/Lightning-AI/litgpt/pull/1566
* Fix SFTDataset sample generation by alealv in https://github.com/Lightning-AI/litgpt/pull/1568
* Add Python API section to 0 to LitGPT docs by rasbt in https://github.com/Lightning-AI/litgpt/pull/1570
* Fix multi-turn prompting error handling and extra newline by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1569
* Add automatic downloading to CLI by rasbt in https://github.com/Lightning-AI/litgpt/pull/1571
* Bumb version for 0.4.4 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1572

New Contributors
* alealv made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1566
* apaz-cli made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1569

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.3...v0.4.4

What's Changed
* Fix Twine Build Issue by rasbt in https://github.com/Lightning-AI/litgpt/pull/1530
* Fix Mixtral prompt style by janEbert in https://github.com/Lightning-AI/litgpt/pull/1531
* Raise warning when loading a large model on a CPU device by rasbt in https://github.com/Lightning-AI/litgpt/pull/1532
* Tutorial `convert_from_litgpt` doc fix to remove `output_dir` command argument by jentfoo in https://github.com/Lightning-AI/litgpt/pull/1533
* Test against eager attention on GPTNeoX by rasbt in https://github.com/Lightning-AI/litgpt/pull/1537
* Bump to 0.4.3.dev0 version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1536
* Fix for LM Eval harness 0.4.3 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1542
* Add `Phi-3-mini-4k-instruct` checkpoint by rasbt in https://github.com/Lightning-AI/litgpt/pull/1341
* Update phi-3 prompt template by rasbt in https://github.com/Lightning-AI/litgpt/pull/1544
* Add progress bar for weight loading by rasbt in https://github.com/Lightning-AI/litgpt/pull/1534
* Remove redundant code in checkpoint conversion script by rasbt in https://github.com/Lightning-AI/litgpt/pull/1547
* Update how evaluate tasks are listed by rasbt in https://github.com/Lightning-AI/litgpt/pull/1550
* Fix generate issue in finetuning script when finetuning with small datasets by rasbt in https://github.com/Lightning-AI/litgpt/pull/1551
* Tokenizer: check that `bos` and `eos` tokens are applied w.r.t. to a provided config/args by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1527
* Add num_nodes argument by janEbert in https://github.com/Lightning-AI/litgpt/pull/1546
* Add Phi-3 Configs by rasbt in https://github.com/Lightning-AI/litgpt/pull/1553
* Update to version 0.4.3 for new release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1554

New Contributors
* janEbert made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1531
* jentfoo made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1533

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.2...v0.4.3

What's Changed
* Disable "validating ..." comment if initial_validation is False by rasbt in https://github.com/Lightning-AI/litgpt/pull/1499
* Add simple issue templates by rasbt in https://github.com/Lightning-AI/litgpt/pull/1501
* Add note about dependencies by rasbt in https://github.com/Lightning-AI/litgpt/pull/1502
* Update test_readme.py by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1505
* Print message when unnecessary can't be deleted by rasbt in https://github.com/Lightning-AI/litgpt/pull/1507
* Bumb version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1509
* LitGPT Python API v1 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1463
* Fix pip upgrade command on windows by rasbt in https://github.com/Lightning-AI/litgpt/pull/1513
* add `LLM.generate` with streaming by aniketmaurya in https://github.com/Lightning-AI/litgpt/pull/1511
* Fix and update Python API docs by rasbt in https://github.com/Lightning-AI/litgpt/pull/1514
* Update LLM import and make stream/non-stream option consistent by rasbt in https://github.com/Lightning-AI/litgpt/pull/1515
* Extend Python API to initialize model with random weights by rasbt in https://github.com/Lightning-AI/litgpt/pull/1512
* Add Python API download option by rasbt in https://github.com/Lightning-AI/litgpt/pull/1516
* Add Rope group size as constexpr to fix thunder tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1520
* Explain how to access pretraining dataset options by rasbt in https://github.com/Lightning-AI/litgpt/pull/1510
* Bump thunder by rasbt in https://github.com/Lightning-AI/litgpt/pull/1519
* Add automatic checkpoint downloading in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1521
* Tokenizer: prefer HF Tokenizer by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1518
* iterate response from streaming server by aniketmaurya in https://github.com/Lightning-AI/litgpt/pull/1523
* Add new python API to readme by williamFalcon in https://github.com/Lightning-AI/litgpt/pull/1525
* Remove `init="local"` option by rasbt in https://github.com/Lightning-AI/litgpt/pull/1524
* Readme improvements by rasbt in https://github.com/Lightning-AI/litgpt/pull/1526
* Add `evaluate` to Readme by rasbt in https://github.com/Lightning-AI/litgpt/pull/1528


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.1...v0.4.2