[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?=e52522b8694ae73abf12feb18d29168674aa1c1b
+CPPLLAMA_VERSION?=dafae66cc242eb766797194d3c85c5e502625623
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

gallery/index.yaml

@@ -1,4 +1,29 @@
 ---
+- &intellect1
+  name: "intellect-1-instruct"
+  url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
+  icon: https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct/resolve/main/intellect-1-map.png
+  urls:
+    - https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct
+    - https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+    - intellect
+  license: apache-2.0
+  description: |
+    INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
+    This is an instruct model. The base model associated with it is INTELLECT-1.
+    INTELLECT-1 was trained on up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent community contributors providing compute. The training code utilizes the prime framework, a scalable distributed training framework designed for fault-tolerant, dynamically scaling, high-perfomance training on unreliable, globally distributed workers. The key abstraction that allows dynamic scaling is the ElasticDeviceMesh which manages dynamic global process groups for fault-tolerant communication across the internet and local process groups for communication within a node. The model was trained using the DiLoCo algorithms with 100 inner steps. The global all-reduce was done with custom int8 all-reduce kernels to reduce the communication payload required, greatly reducing the communication overhead by a factor 400x.
+  overrides:
+    parameters:
+      model: INTELLECT-1-Instruct-Q4_K_M.gguf
+  files:
+    - filename: INTELLECT-1-Instruct-Q4_K_M.gguf
+      sha256: 5df236fe570e5998d07fb3207788eac811ef3b77dd2a0ad04a2ef5c6361f3030
+      uri: huggingface://bartowski/INTELLECT-1-Instruct-GGUF/INTELLECT-1-Instruct-Q4_K_M.gguf
 - &llama33
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
   icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png
@@ -1866,6 +1891,21 @@
     - filename: Qwen2.5-7B-HomerAnvita-NerdMix.Q4_K_M.gguf
       sha256: 73db2ca3ab50e8627352078988cd173e7447c5e8199a7db9e554602da1362e5f
       uri: huggingface://QuantFactory/Qwen2.5-7B-HomerAnvita-NerdMix-GGUF/Qwen2.5-7B-HomerAnvita-NerdMix.Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "qwen2.5-math-14b-instruct"
+  urls:
+    - https://huggingface.co/qingy2024/Qwen2.5-Math-14B-Instruct-Preview
+    - https://huggingface.co/QuantFactory/Qwen2.5-Math-14B-Instruct-GGUF
+  description: |
+    This Qwen 2.5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
+    Fine-tuned it for 400 steps on garage-bAInd/Open-Platypus with a batch size of 3.
+  overrides:
+    parameters:
+      model: Qwen2.5-Math-14B-Instruct.Q4_K_M.gguf
+  files:
+    - filename: Qwen2.5-Math-14B-Instruct.Q4_K_M.gguf
+      sha256: 14e672394738a7d9f14a6cb16fd9a649b113a19a8b4934f9c18299fc4e286ab6
+      uri: huggingface://QuantFactory/Qwen2.5-Math-14B-Instruct-GGUF/Qwen2.5-Math-14B-Instruct.Q4_K_M.gguf
 - &archfunct
   license: apache-2.0
   tags:
@@ -3661,6 +3701,20 @@
     - filename: Tulu-3.1-8B-SuperNova-Smart.Q4_K_M.gguf
       sha256: 4b8ba9e64f0667199eee2dcc769f1a90aa9c7730165d42f440fdf107c7585c63
       uri: huggingface://QuantFactory/Tulu-3.1-8B-SuperNova-Smart-GGUF/Tulu-3.1-8B-SuperNova-Smart.Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "b-nimita-l3-8b-v0.02"
+  urls:
+    - https://huggingface.co/Arkana08/B-NIMITA-L3-8B-v0.02
+    - https://huggingface.co/QuantFactory/B-NIMITA-L3-8B-v0.02-GGUF
+  description: |
+    B-NIMITA is an AI model designed to bring role-playing scenarios to life with emotional depth and rich storytelling. At its core is NIHAPPY, providing a solid narrative foundation and contextual consistency. This is enhanced by Mythorica, which adds vivid emotional arcs and expressive dialogue, and V-Blackroot, ensuring character consistency and subtle adaptability. This combination allows B-NIMITA to deliver dynamic, engaging interactions that feel natural and immersive.
+  overrides:
+    parameters:
+      model: B-NIMITA-L3-8B-v0.02.Q4_K_M.gguf
+  files:
+    - filename: B-NIMITA-L3-8B-v0.02.Q4_K_M.gguf
+      sha256: 625a54848dcd3f23bc06b639a7dfecae14142b5d177dd45acfe7724816bab4cd
+      uri: huggingface://QuantFactory/B-NIMITA-L3-8B-v0.02-GGUF/B-NIMITA-L3-8B-v0.02.Q4_K_M.gguf
 - &deepseek
   ## Deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"