Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Bump llama-cpp-python from 0.2.27 to 0.2.32 (#305)
Bumps [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) from 0.2.27 to 0.2.32. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/abetlen/llama-cpp-python/blob/main/CHANGELOG.md">llama-cpp-python's changelog</a>.</em></p> <blockquote> <h2>[0.2.32]</h2> <ul> <li>feat: Update llama.cpp to ggerganov/llama.cpp@504dc37</li> <li>fix: from_json_schema oneof/anyof bug by <a href="https://github.com/jndiogo"><code>@jndiogo</code></a> in d3f5528ca8bcb9d69d4f27e21631e911f1fb9bfe</li> <li>fix: pass chat handler not chat formatter for huggingface autotokenizer and tokenizer_config formats by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 24f39454e91cf5dddbc4b6041aead4accc7c7a2d</li> <li>feat: Add add_generation_prompt option for jinja2chatformatter by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 7f3209b1eb4ad3260ba063801fab80a8c25a2f4c</li> <li>feat: Add Jinja2ChatFormatter by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in be09318c26add8674ce494ae7cc480cce72a4146</li> <li>feat: Expose gguf model metadata in metadata property by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 5a34c57e5479e50c99aba9b38218cc48e6560b81</li> </ul> <h2>[0.2.31]</h2> <ul> <li>feat: Update llama.cpp to ggerganov/llama.cpp@a5cacb2</li> <li>fix: Mirostat sampling now passes correct type to ctypes and tracks state during generation by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 3babe3512cb95743108f2b595210c38ed6f1b904</li> <li>fix: Python3.8 support in server by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 141293a75b564a8699e0acba1da24d9aa1cf0ab1</li> </ul> <h2>[0.2.30]</h2> <ul> <li>feat: Update llama.cpp to ggerganov/llama.cpp@57e2a7a</li> <li>feat(server): Add ability to load chat format from huggingface autotokenizer or tokenizer_config.json files by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in b8fc1c7d83ad4a9207c707ba1d954fe580286a01</li> <li>feat: Integration of Jinja2 Templating for chat formats by <a href="https://github.com/teleprint-me"><code>@teleprint-me</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/875">#875</a></li> <li>fix: Offload KQV by default by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 48c3b77e6f558a9899de0e1155c7dc0c7958d8e8</li> <li>fix: Support Accept text/event-stream in chat and completion endpoints, resolves <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1083">#1083</a> by <a href="https://github.com/aniljava"><code>@aniljava</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1088">#1088</a></li> <li>fix(cli): allow passing n_ctx=0 to openAI API server args to use model n_ctx_train field per <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1015">#1015</a> by <a href="https://github.com/K-Mistele"><code>@K-Mistele</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1093">#1093</a></li> </ul> <h2>[0.2.29]</h2> <ul> <li>feat: Update llama.cpp to ggerganov/llama.cpp@4483396</li> <li>feat: Add split_mode option by <a href="https://github.com/abetlen"><code>@abetlen</code></a> in 84615adbc6855c8384807c42f0130f9a1763f99d</li> <li>feat: Implement GGUF metadata KV overrides by <a href="https://github.com/phiharri"><code>@phiharri</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1011">#1011</a></li> <li>fix: Avoid "LookupError: unknown encoding: ascii" when open() called in a destructor by <a href="https://github.com/yieldthought"><code>@yieldthought</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1012">#1012</a></li> <li>fix: Fix low_level_api_chat_cpp example to match current API by <a href="https://github.com/aniljava"><code>@aniljava</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1086">#1086</a></li> <li>fix: Fix Pydantic model parsing by <a href="https://github.com/DeNeutoy"><code>@DeNeutoy</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1087">#1087</a></li> </ul> <h2>[0.2.28]</h2> <ul> <li>feat: Update llama.cpp to ggerganov/llama.cpp@6efb8eb</li> <li>feat: Add ability to pass in penalize_nl param by <a href="https://github.com/shankinson"><code>@shankinson</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1068">#1068</a></li> <li>fix: print_grammar to stderr by <a href="https://github.com/turian"><code>@turian</code></a> in <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1052">#1052</a></li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/2ce0b8aa2c2f81d999bbb2a7246a9f221f9d52d0"><code>2ce0b8a</code></a> Bump version</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/d3f5528ca8bcb9d69d4f27e21631e911f1fb9bfe"><code>d3f5528</code></a> fix: from_json_schema oneof/anyof bug. Closes <a href="https://redirect.github.com/abetlen/llama-cpp-python/issues/1097">#1097</a></li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/8eefdbca03d005095f6645d4e5b42b982af9daf0"><code>8eefdbc</code></a> Update llama.cpp</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/88fbccaaa3416f38552d80d84c71fdb40c7c477a"><code>88fbcca</code></a> docs: Add macosx wrong arch fix to README</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/24f39454e91cf5dddbc4b6041aead4accc7c7a2d"><code>24f3945</code></a> fix: pass chat handler not chat formatter for huggingface autotokenizer and t...</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/7f3209b1eb4ad3260ba063801fab80a8c25a2f4c"><code>7f3209b</code></a> feat: Add add_generation_prompt option for jinja2chatformatter.</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/ac2e96d4b4610cb9cd9b0c978c76ece6567f5c02"><code>ac2e96d</code></a> Update llama.cpp</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/be09318c26add8674ce494ae7cc480cce72a4146"><code>be09318</code></a> feat: Add Jinja2ChatFormatter</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/5a34c57e5479e50c99aba9b38218cc48e6560b81"><code>5a34c57</code></a> feat: Expose gguf model metadata in metadata property</li> <li><a href="https://github.com/abetlen/llama-cpp-python/commit/833a7f1a86f2136df5f75c1bd62d2e4d5adaa439"><code>833a7f1</code></a> Bump version</li> <li>Additional commits viewable in <a href="https://github.com/abetlen/llama-cpp-python/compare/v0.2.27...v0.2.32">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=llama-cpp-python&package-manager=pip&previous-version=0.2.27&new-version=0.2.32)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
- Loading branch information