[pull] master from mudler:master

Makefile

@@ -8,7 +8,7 @@ DETECT_LIBS?=true
 # llama.cpp versions
 GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
 GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=a813badbbdf0d38705f249df7a0c99af5cdee678
+CPPLLAMA_VERSION?=716bd6dec3e044e5c325386b5b0483392b24cefe
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

gallery/index.yaml

@@ -2490,6 +2490,40 @@
     - filename: Teleut-7b-RP-Q4_K_M.gguf
       sha256: 74d9a0974c48f16677da8891ac76ed89ed04f246275b9ca8316d25e1e86ce89f
       uri: huggingface://bartowski/Teleut-7b-RP-GGUF/Teleut-7b-RP-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "qwen2.5-32b-rp-ink"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/1_Zt_OvEW183lmrgidQw8.png
+  urls:
+    - https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink
+    - https://huggingface.co/bartowski/Qwen2.5-32b-RP-Ink-GGUF
+  description: |
+    A roleplay-focused LoRA finetune of Qwen 2.5 32b Instruct. Methodology and hyperparams inspired by SorcererLM and Slush.
+    Yet another model in the Ink series, following in the footsteps of the Nemo one
+  overrides:
+    parameters:
+      model: Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
+  files:
+    - filename: Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
+      sha256: 7a0693d50aa40ba4fd43b4988851e67443e758ae34881f448e2812e5fcc25468
+      uri: huggingface://bartowski/Qwen2.5-32b-RP-Ink-GGUF/Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "q2.5-veltha-14b-0.5"
+  urls:
+    - https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5
+    - https://huggingface.co/bartowski/Q2.5-Veltha-14B-0.5-GGUF
+  description: |
+    The following models were included in the merge:s
+        huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
+        allura-org/TQ2.5-14B-Aletheia-v1
+        EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
+        v000000/Qwen2.5-Lumen-14B
+  overrides:
+    parameters:
+      model: Q2.5-Veltha-14B-0.5-Q4_K_M.gguf
+  files:
+    - filename: Q2.5-Veltha-14B-0.5-Q4_K_M.gguf
+      sha256: f75b8cbceab555ebcab6fcb3b51d398b7ef79671aa05c21c288edd75c9f217bd
+      uri: huggingface://bartowski/Q2.5-Veltha-14B-0.5-GGUF/Q2.5-Veltha-14B-0.5-Q4_K_M.gguf
 - &smollm
   ## SmolLM
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
@@ -4349,6 +4383,21 @@
     - filename: Control-Nanuq-8B.Q4_K_M.gguf
       sha256: 5aa3b929cbcaf62709fef58d6f630c2df1185d774d0074c7e750cb03c53b744e
       uri: huggingface://QuantFactory/Control-Nanuq-8B-GGUF/Control-Nanuq-8B.Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "huatuogpt-o1-8b"
+  urls:
+    - https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-8B
+    - https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF
+  description: |
+    HuatuoGPT-o1 is a medical LLM designed for advanced medical reasoning. It generates a complex thought process, reflecting and refining its reasoning, before providing a final response.
+    For more information, visit our GitHub repository: https://github.com/FreedomIntelligence/HuatuoGPT-o1.
+  overrides:
+    parameters:
+      model: HuatuoGPT-o1-8B-Q4_K_M.gguf
+  files:
+    - filename: HuatuoGPT-o1-8B-Q4_K_M.gguf
+      sha256: 3e1ef35fc230182d96ae2d6c7436a2e8250c21a4278e798e1aa45790ba82006b
+      uri: huggingface://bartowski/HuatuoGPT-o1-8B-GGUF/HuatuoGPT-o1-8B-Q4_K_M.gguf
 - &deepseek
   ## Deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"