release 0.5.7 (#1924)

Author: t-vi

README.md

@@ -103,7 +103,7 @@ Every model is written from scratch to maximize performance and remove layers of
 | Phi 4 | 14B | Microsoft Research | [Abdin et al. 2024](https://arxiv.org/abs/2412.08905)                                                                            |
 | Qwen2.5 | 0.5B, 1.5B, 3B, 7B, 14B, 32B, 72B | Alibaba Group | [Qwen Team 2024](https://qwenlm.github.io/blog/qwen2.5/)                                               |
 | Qwen2.5 Coder | 0.5B, 1.5B, 3B, 7B, 14B, 32B | Alibaba Group | [Hui, Binyuan et al. 2024](https://arxiv.org/abs/2409.12186)                                          |
-| R1 Distll Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                                 |
+| R1 Distill Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                                 |
 | ... | ... | ... | ...   |
 
 <details>
@@ -143,7 +143,7 @@ Every model is written from scratch to maximize performance and remove layers of
 | Qwen2.5 Coder | 0.5B, 1.5B, 3B, 7B, 14B, 32B | Alibaba Group | [Hui, Binyuan et al. 2024](https://arxiv.org/abs/2409.12186)                                          |
 | Qwen2.5 Math | 1.5B, 7B, 72B | Alibaba Group | [An, Yang et al. 2024](https://arxiv.org/abs/2409.12122)                                          |
 | QwQ | 32B | Alibaba Group | [Qwen Team 2024](https://qwenlm.github.io/blog/qwq-32b-preview/)                                                                         |
-| R1 Distll Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                                 |
+| R1 Distill Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                                 |
 | SmolLM2 | 135M, 360M, 1.7B | Hugging Face | [Hugging Face 2024](https://github.com/huggingface/smollm)                                                               |
 | Salamandra | 2B, 7B | Barcelona Supercomputing Centre | [BSC-LTC 2024](https://github.com/BSC-LTC/salamandra)                                                                         |
 | StableCode | 3B | Stability AI | [Stability AI 2023](https://stability.ai/blog/stablecode-llm-generative-ai-coding)                                                  |

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "litgpt"
-version = "0.5.7.dev1"
+version = "0.5.7"
 description = "Hackable implementation of state-of-the-art open-source LLMs"
 authors = [
     { name = "Lightning AI", email = "contact@lightning.ai" },