@@ -7,12 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77
88## [ Unreleased]
99
10+ ## [ 0.2.50]
11+
12+ - docs: Update Functionary OpenAI Server Readme by @jeffrey-fong in #1193
13+ - fix: LlamaHFTokenizer now receives pre_tokens by @abetlen in 47bad30dd716443652275099fa3851811168ff4a
14+
1015## [ 0.2.49]
1116
1217- fix: module 'llama_cpp.llama_cpp' has no attribute 'c_uint8' in Llama.save_state by @abetlen in db776a885cd4c20811f22f8bd1a27ecc71dba927
1318- feat: Auto detect Mixtral's slightly different format by @lukestanley in #1214
1419
15-
1620## [ 0.2.48]
1721
1822- feat: Update llama.cpp to ggerganov/llama.cpp@15499eb94227401bdc8875da6eb85c15d37068f7
@@ -151,7 +155,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
151155- feat: Update llama.cpp to ggerganov/llama.cpp@b3a7c20b5c035250257d2b62851c379b159c899a
152156- feat: Add ` saiga ` chat format by @femoiseev in #1050
153157- feat: Added ` chatglm3 ` chat format by @xaviviro in #1059
154- - fix: Correct typo in README.md by @qeleb in (#1058 )
158+ - fix: Correct typo in README.md by @qeleb in (#1058 )
155159
156160## [ 0.2.26]
157161
@@ -284,7 +288,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
284288
285289## [ 0.2.11]
286290
287- - Fix bug in ` llama_model_params ` object has no attribute ` logits_all ` by @abetlen in d696251fbe40015e8616ea7a7d7ad5257fd1b896
291+ - Fix bug in ` llama_model_params ` object has no attribute ` logits_all ` by @abetlen in d696251fbe40015e8616ea7a7d7ad5257fd1b896
288292
289293## [ 0.2.10]
290294
@@ -472,7 +476,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
472476
473477## [ 0.1.60]
474478
475- NOTE: This release was deleted due to a bug with the packaging system that caused pip installations to fail.
479+ NOTE: This release was deleted due to a bug with the packaging system that caused pip installations to fail.
476480
477481- Truncate max_tokens in create_completion so requested tokens doesn't exceed context size.
478482- Temporarily disable cache for completion requests
@@ -496,4 +500,4 @@ NOTE: This release was deleted due to a bug with the packaging system that caus
496500- (misc) Added first version of the changelog
497501- (server) Use async routes
498502- (python-api) Use numpy for internal buffers to reduce memory usage and improve performance.
499- - (python-api) Performance bug in stop sequence check slowing down streaming.
503+ - (python-api) Performance bug in stop sequence check slowing down streaming.
0 commit comments