Merge branch 'master' into rf-service-wiring-1c

Makefile

@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
 
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=1442677f92e45a475be7b4d056e3633d1d6f813b
+CPPLLAMA_VERSION?=7672adeec7a79ea271058c63106c142ba84f951a
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all

gallery/index.yaml

@@ -334,6 +334,19 @@
     - filename: l3-8b-stheno-v3.1.Q4_K_M.gguf
       sha256: f166fb8b7fd1de6638fcf8e3561c99292f0c37debe1132325aa583eef78f1b40
       uri: huggingface://mudler/L3-8B-Stheno-v3.1-Q4_K_M-GGUF/l3-8b-stheno-v3.1.Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "l3-8b-stheno-v3.2-iq-imatrix"
+  urls:
+    - https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2
+    - https://huggingface.co/Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix
+  icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/1rLk3xdnfD7AkdQBXWUqb.png
+  overrides:
+    parameters:
+      model: L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf
+  files:
+    - filename: L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf
+      sha256: 8607a426b0c2007716df8a9eb96754e3ccca761a3996af5d49fcd74d87ada347
+      uri: huggingface://Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix/L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf
 - !!merge <<: *llama3
   name: "llama-3-stheno-mahou-8b"
   urls:
@@ -988,6 +1001,38 @@
     - filename: Mahou-1.2-llama3-8B-Q4_K_M.gguf
       sha256: 651b405dff71e4ce80e15cc6d393463f02833428535c56eb6bae113776775d62
       uri: huggingface://flammenai/Mahou-1.2-llama3-8B-GGUF/Mahou-1.2-llama3-8B-Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "llama-3-instruct-8b-SimPO-ExPO"
+  description: |
+    The extrapolated (ExPO) model based on princeton-nlp/Llama-3-Instruct-8B-SimPO and meta-llama/Meta-Llama-3-8B-Instruct, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper.
+  urls:
+    - https://huggingface.co/bartowski/Llama-3-Instruct-8B-SimPO-ExPO-GGUF
+    - https://huggingface.co/chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
+  overrides:
+    parameters:
+      model: Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf
+  files:
+    - filename: Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf
+      sha256: a78a68851f76a376654a496d9aaac761aeac6a25fd003f0350da40afceba3f0f
+      uri: huggingface://bartowski/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "Llama-3-Yggdrasil-2.0-8B"
+  description: |
+    The following models were included in the merge:
+
+        Locutusque/Llama-3-NeuralHercules-5.0-8B
+        NousResearch/Hermes-2-Theta-Llama-3-8B
+        Locutusque/llama-3-neural-chat-v2.2-8b
+  urls:
+    - https://huggingface.co/bartowski/Llama-3-Yggdrasil-2.0-8B-GGUF
+    - https://huggingface.co/Locutusque/Llama-3-Yggdrasil-2.0-8B
+  overrides:
+    parameters:
+      model: Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf
+  files:
+    - filename: Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf
+      sha256: 75091cf3a7145373922dbeb312c689cace89ba06215ce74b6fc7055a4b35a40c
+      uri: huggingface://bartowski/Llama-3-Yggdrasil-2.0-8B-GGUF/Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf
 - &yi-chat
   ### Start Yi
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
@@ -1781,6 +1826,20 @@
     - filename: Cream-Phi-3-14B-v1-Q4_K_M.gguf
       uri: huggingface://TheDrummer/Cream-Phi-3-14B-v1-GGUF/Cream-Phi-3-14B-v1-Q4_K_M.gguf
       sha256: ec67018a86090da415517acf21ad48f28e02dff664a1dd35602f1f8fa94f6a27
+- !!merge <<: *phi-3
+  name: "phi3-4x4b-v1"
+  description: |
+    a continually pretrained phi3-mini sparse moe upcycle
+  urls:
+    - https://huggingface.co/bartowski/phi3-4x4b-v1-GGUF
+    - https://huggingface.co/Fizzarolli/phi3-4x4b-v1
+  overrides:
+    parameters:
+      model: phi3-4x4b-v1-Q4_K_M.gguf
+  files:
+    - filename: phi3-4x4b-v1-Q4_K_M.gguf
+      uri: huggingface://bartowski/phi3-4x4b-v1-GGUF/phi3-4x4b-v1-Q4_K_M.gguf
+      sha256: fd33220186b7076f4b306f27b3a8913384435a2ca90185a71c9df5a752d3a298
 - &hermes-2-pro-mistral
   ### START Hermes
   url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"