chore(model gallery): add granite embeddings models

gallery/index.yaml

@@ -1169,6 +1169,40 @@
     - filename: ibm-granite_granite-3.2-2b-instruct-Q4_K_M.gguf
       sha256: e1b915b0849becf4fdda188dee7b09cbebbfabd71c6f3f2b75dd3eca0a8fded1
       uri: huggingface://bartowski/ibm-granite_granite-3.2-2b-instruct-GGUF/ibm-granite_granite-3.2-2b-instruct-Q4_K_M.gguf
+- name: "granite-embedding-107m-multilingual"
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual
+    - https://huggingface.co/bartowski/granite-embedding-107m-multilingual-GGUF
+  description: |
+      Granite-Embedding-107M-Multilingual is a 107M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. This model is developed using contrastive finetuning, knowledge distillation and model merging for improved performance.
+  tags:
+    - embeddings
+  overrides:
+    embeddings: true
+    parameters:
+      model: granite-embedding-107m-multilingual-f16.gguf
+  files:
+    - filename: granite-embedding-107m-multilingual-f16.gguf
+      uri: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
+      sha256: 3fc99928632fcecad589c401ec33bbba86b51c457e9813e3a1cb801ff4106e21
+- name: "granite-embedding-125m-english"
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/ibm-granite/granite-embedding-125m-english
+    - https://huggingface.co/bartowski/granite-embedding-125m-english-GGUF
+  description: |
+    Granite-Embedding-125m-English is a 125M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 768. Compared to most other open-source models, this model was only trained using open-source relevance-pair datasets with permissive, enterprise-friendly license, plus IBM collected and generated datasets. While maintaining competitive scores on academic benchmarks such as BEIR, this model also performs well on many enterprise use cases. This model is developed using retrieval oriented pretraining, contrastive finetuning and knowledge distillation.
+  tags:
+    - embeddings
+  overrides:
+    embeddings: true
+    parameters:
+      model: granite-embedding-125m-english-f16.gguf
+  files:
+    - filename: granite-embedding-125m-english-f16.gguf
+      uri: huggingface://bartowski/granite-embedding-125m-english-GGUF/granite-embedding-125m-english-f16.gguf
+      sha256: e2950cf0228514e0e81c6f0701a62a9e4763990ce660b4a3c0329cd6a4acd4b9
 - name: "moe-girl-1ba-7bt-i1"
   icon: https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/kTXXSSSqpb21rfyOX7FUa.jpeg
   # chatml
@@ -1804,7 +1838,7 @@
       sha256: 770900ba9594f64f31b35fe444d31263712cabe167efaf4201d79fdc29de9533
       uri: huggingface://mradermacher/kubeguru-llama3.2-3b-v0.1-GGUF/kubeguru-llama3.2-3b-v0.1.Q4_K_M.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -3765,7 +3799,7 @@
       sha256: 0fec82625f74a9a340837de7af287b1d9042e5aeb70cda2621426db99958b0af
       uri: huggingface://bartowski/Chuluun-Qwen2.5-72B-v0.08-GGUF/Chuluun-Qwen2.5-72B-v0.08-Q4_K_M.gguf
 - &smollm
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## SmolLM
   name: "smollm-1.7b-instruct"
   icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
   tags:
@@ -4404,7 +4438,7 @@
       sha256: ee0b5027c686f3c37938f33b62788e27211852268f9e5c32e00058f0cf1688c7
       uri: huggingface://bartowski/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-GGUF/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-Q4_K_M.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578
   name: "meta-llama-3.1-8b-instruct"
   license: llama3.1
@@ -6501,7 +6535,7 @@
       sha256: 25db6d4ae5649e6d2084036d8f05ec1aca459126e2d4734d6c18f1e16147a4d3
       uri: huggingface://mradermacher/Llama-3.3-MagicalGirl-2.5-i1-GGUF/Llama-3.3-MagicalGirl-2.5.i1-Q4_K_M.gguf
 - &deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
   name: "deepseek-coder-v2-lite-instruct"
   icon: "https://avatars.githubusercontent.com/u/148330874"
   license: deepseek
@@ -6566,7 +6600,7 @@
       sha256: a47782c55ef2b39b19644213720a599d9849511a73c9ebb0c1de749383c0a0f8
       uri: huggingface://RichardErkhov/ContextualAI_-_archangel_sft_pythia2-8b-gguf/archangel_sft_pythia2-8b.Q4_K_M.gguf
 - &deepseek-r1
   url: "github:mudler/LocalAI/gallery/deepseek-r1.yaml@master" ## Start DeepSeek-R1
   name: "deepseek-r1-distill-qwen-1.5b"
   icon: "https://avatars.githubusercontent.com/u/148330874"
   urls:
@@ -6898,7 +6932,7 @@
       sha256: 889455f0c747f2c444818c68169384d3da4830156d2a19906d7d6adf48b243df
       uri: huggingface://bartowski/TheDrummer_Fallen-Llama-3.3-R1-70B-v1-GGUF/TheDrummer_Fallen-Llama-3.3-R1-70B-v1-Q4_K_M.gguf
 - &qwen2
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2
   name: "qwen2-7b-instruct"
   icon: https://avatars.githubusercontent.com/u/141221163
   license: apache-2.0
@@ -7299,7 +7333,7 @@
       sha256: dbffc989d12d42ef8e4a2994e102d7ec7a02c49ec08ea2e35426372ad07b4cd8
       uri: huggingface://bartowski/TAID-LLM-1.5B-GGUF/TAID-LLM-1.5B-Q4_K_M.gguf
 - &mistral03
   url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master" ## START Mistral
   name: "mistral-7b-instruct-v0.3"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/62dac1c7a8ead43d20e3e17a/wrLf5yaGC6ng4XME70w6Z.png
   license: apache-2.0
@@ -8068,7 +8102,7 @@
       sha256: 6358033ea52dbde158dbcdb44bd68b2b8959cc77514c86a9ccc64ba1a452f287
       uri: huggingface://bartowski/PocketDoc_Dans-PersonalityEngine-V1.2.0-24b-GGUF/PocketDoc_Dans-PersonalityEngine-V1.2.0-24b-Q4_K_M.gguf
 - &mudler
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models
   name: "LocalAI-llama3-8b-function-call-v0.2"
   icon: "https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/us5JKi9z046p8K-cn_M0w.webp"
   license: llama3
@@ -8113,7 +8147,7 @@
       sha256: 579cbb229f9c11d0330759ff4733102d2491615a4c61289e26c09d1b3a583fec
       uri: huggingface://mudler/Mirai-Nova-Llama3-LocalAI-8B-v0.1-GGUF/Mirai-Nova-Llama3-LocalAI-8B-v0.1-q4_k_m.bin
 - &parler-tts
   url: "github:mudler/LocalAI/gallery/parler-tts.yaml@master" ### START parler-tts
   name: parler-tts-mini-v0.1
   overrides:
     parameters:
@@ -8130,7 +8164,7 @@
     - text-to-speech
     - python
 - &rerankers
   url: "github:mudler/LocalAI/gallery/rerankers.yaml@master" ### START rerankers
   name: cross-encoder
   parameters:
     model: cross-encoder