Merge remote-tracking branch 'origin/master' into vllm-additional-config

Signed-off-by: TheDropZone <brandonbeiler@gmail.com>
2025-06-26 20:55:00 +00:00 · 2025-02-18 09:00:31 -05:00 · 2025-02-18 09:00:31 -05:00 · f498d40e43
commit f498d40e43
parent 66eae14003 28fb8e607a
4 changed files with 121 additions and 4 deletions
--- a/2
+++ b/2
@ -6,7 +6,7 @@ BINARY_NAME=local-ai
 DETECT_LIBS?=true

 # llama.cpp versions
-CPPLLAMA_VERSION?=2eea03d86a2d132c8245468c26290ce07a27a8e8
+CPPLLAMA_VERSION?=73e2ed3ce3492d3ed70193dd09ae8aa44779651d

 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp
--- a/core/http/views/chat.html
+++ b/core/http/views/chat.html
@ -44,7 +44,7 @@ SOFTWARE.

      <div class="flex items-center justify-between">

-      <h1 class="text-lg font-semibold"> <i class="fa-solid fa-comments"></i> Chat with {{.Model}} <a href="https://localai.io/features/text-generation/" target="_blank" >
+      <h1 class="text-lg font-semibold"> <i class="fa-solid fa-comments"></i> Chat with {{.Model}} <a href="browse?term={{.Model}}" ><i class="fas fa-brain pr-2"></i></a> <a href="https://localai.io/features/text-generation/" target="_blank" >
        <i class="fas fa-circle-info pr-2"></i>
      </a></h1>
      <div x-show="component === 'menu'" id="menu">
--- a/core/http/views/index.html
+++ b/core/http/views/index.html
@ -41,7 +41,7 @@
                <thead class="text-xs text-gray-400 uppercase bg-gray-700">
                    <tr>
                        <th class="px-4 py-2"></th>
-                        <th class="px-4 py-2">Model Name</th>
+                        <th class="px-4 py-2"><i class="fas fa-brain pr-2"></i>Model Name</th>
                        <th class="px-4 py-2">Backend</th>
                        <th class="px-4 py-2 float-right">Actions</th>
                    </tr>
@ -66,7 +66,7 @@
                        {{ end }}
                    </td>
                    <td class="px-4 py-3 font-bold">
-                        <p class="font-bold text-white flex items-center"><i class="fas fa-brain pr-2"></i><a href="browse?term={{.Name}}">{{.Name}}</a></p>
+                        <p class="font-bold text-white flex items-center"><a href="browse?term={{.Name}}">{{.Name}}</a> <a href="chat/{{.Name}}"><i class="fas fa-comments"></i></a></p>
                    </td>
                    <td class="px-4 py-3 font-bold">
                        {{ if .Backend }}
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@ -1550,6 +1550,23 @@
    - filename: localai-functioncall-llama3.2-3b-v0.5-q4_k_m.gguf
      sha256: edc50f6c243e6bd6912599661a15e030de03d2be53409663ac27d3ca48306ee4
      uri: huggingface://mudler/LocalAI-functioncall-llama3.2-3b-v0.5-Q4_K_M-GGUF/localai-functioncall-llama3.2-3b-v0.5-q4_k_m.gguf
+- !!merge <<: *llama32
+  name: "kubeguru-llama3.2-3b-v0.1"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/rptpRyhrcUEG3i2OPT897.png
+  urls:
+    - https://huggingface.co/Spectro-Cloud/kubeguru-llama3.2-3b-v0.1
+    - https://huggingface.co/mradermacher/kubeguru-llama3.2-3b-v0.1-GGUF
+  description: |
+    Kubeguru: Your Kubernetes & Linux Expert AI
+    Ask anything about Kubernetes, Linux, containers—and get expert answers in real-time!
+    Kubeguru is a specialized Large Language Model (LLM) developed and released by the Open Source team at Spectro Cloud. Whether you're managing cloud-native applications, deploying edge workloads, or troubleshooting containerized services, Kubeguru provides precise, actionable insights at every step.
+  overrides:
+    parameters:
+      model: kubeguru-llama3.2-3b-v0.1.Q4_K_M.gguf
+  files:
+    - filename: kubeguru-llama3.2-3b-v0.1.Q4_K_M.gguf
+      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
@ -3830,6 +3847,89 @@
    - filename: ozone-ai_0x-lite-Q4_K_M.gguf
      sha256: 7f163e72ead7522bd6774555a932e0a11f212d17cdc9442e2cfd1b017009f832
      uri: huggingface://bartowski/ozone-ai_0x-lite-GGUF/ozone-ai_0x-lite-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "nbeerbower_dumpling-qwen2.5-14b"
+  icon: https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B/resolve/main/dumpling_cover.png?download=true
+  urls:
+    - https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-14B
+    - https://huggingface.co/bartowski/nbeerbower_Dumpling-Qwen2.5-14B-GGUF
+  description: |
+    nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B finetuned on:
+
+        nbeerbower/GreatFirewall-DPO
+        nbeerbower/Schule-DPO
+        nbeerbower/Purpura-DPO
+        nbeerbower/Arkhaios-DPO
+        jondurbin/truthy-dpo-v0.1
+        antiven0m/physical-reasoning-dpo
+        flammenai/Date-DPO-NoAsterisks
+        flammenai/Prude-Phi3-DPO
+        Atsunori/HelpSteer2-DPO
+        jondurbin/gutenberg-dpo-v0.1
+        nbeerbower/gutenberg2-dpo
+        nbeerbower/gutenberg-moderne-dpo.
+  overrides:
+    parameters:
+      model: nbeerbower_Dumpling-Qwen2.5-14B-Q4_K_M.gguf
+  files:
+    - filename: nbeerbower_Dumpling-Qwen2.5-14B-Q4_K_M.gguf
+      sha256: 2d38348414b2719971a08a604313ed98b44b586490633d6e237dd096ae5bf31d
+      uri: huggingface://bartowski/nbeerbower_Dumpling-Qwen2.5-14B-GGUF/nbeerbower_Dumpling-Qwen2.5-14B-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "nbeerbower_dumpling-qwen2.5-32b-v2"
+  icon: https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B/resolve/main/dumpling_cover.png?download=true
+  urls:
+    - https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2
+    - https://huggingface.co/bartowski/nbeerbower_Dumpling-Qwen2.5-32B-v2-GGUF
+  description: |
+    nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B finetuned on:
+
+        nbeerbower/GreatFirewall-DPO
+        nbeerbower/Schule-DPO
+        nbeerbower/Purpura-DPO
+        nbeerbower/Arkhaios-DPO
+        jondurbin/truthy-dpo-v0.1
+        antiven0m/physical-reasoning-dpo
+        flammenai/Date-DPO-NoAsterisks
+        flammenai/Prude-Phi3-DPO
+        Atsunori/HelpSteer2-DPO
+        jondurbin/gutenberg-dpo-v0.1
+        nbeerbower/gutenberg2-dpo
+        nbeerbower/gutenberg-moderne-dpo.
+  overrides:
+    parameters:
+      model: nbeerbower_Dumpling-Qwen2.5-32B-v2-Q4_K_M.gguf
+  files:
+    - filename: nbeerbower_Dumpling-Qwen2.5-32B-v2-Q4_K_M.gguf
+      sha256: 02a5320d62e13b31ac6d04ccdaba7b72a524d6cc72a7082b94d8cac0a183ecb4
+      uri: huggingface://bartowski/nbeerbower_Dumpling-Qwen2.5-32B-v2-GGUF/nbeerbower_Dumpling-Qwen2.5-32B-v2-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "nbeerbower_dumpling-qwen2.5-72b"
+  icon: https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B/resolve/main/dumpling_cover.png?download=true
+  urls:
+    - https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-72B
+    - https://huggingface.co/bartowski/nbeerbower_Dumpling-Qwen2.5-72B-GGUF
+  description: |
+    nbeerbower/EVA-abliterated-TIES-Qwen2.5-72B finetuned on:
+        nbeerbower/GreatFirewall-DPO
+        nbeerbower/Schule-DPO
+        nbeerbower/Purpura-DPO
+        nbeerbower/Arkhaios-DPO
+        jondurbin/truthy-dpo-v0.1
+        antiven0m/physical-reasoning-dpo
+        flammenai/Date-DPO-NoAsterisks
+        flammenai/Prude-Phi3-DPO
+        Atsunori/HelpSteer2-DPO
+        jondurbin/gutenberg-dpo-v0.1
+        nbeerbower/gutenberg2-dpo
+        nbeerbower/gutenberg-moderne-dpo.
+  overrides:
+    parameters:
+      model: nbeerbower_Dumpling-Qwen2.5-72B-Q4_K_M.gguf
+  files:
+    - filename: nbeerbower_Dumpling-Qwen2.5-72B-Q4_K_M.gguf
+      sha256: 384de5ba5e60255846cd38e2bfad0374b059fb627ba8abb02273186f28684385
+      uri: huggingface://bartowski/nbeerbower_Dumpling-Qwen2.5-72B-GGUF/nbeerbower_Dumpling-Qwen2.5-72B-Q4_K_M.gguf
 - &llama31
  url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
  icon: https://avatars.githubusercontent.com/u/153379578
@ -5811,6 +5911,23 @@
    - filename: DavidBrowne17_LlamaThink-8B-instruct-Q4_K_M.gguf
      sha256: 6aea4e13f03347e03d6989c736a7ccab82582115eb072cacfeb7f0b645a8bec0
      uri: huggingface://bartowski/DavidBrowne17_LlamaThink-8B-instruct-GGUF/DavidBrowne17_LlamaThink-8B-instruct-Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "allenai_llama-3.1-tulu-3.1-8b"
+  icon: https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu3/Tulu3-logo.png
+  urls:
+    - https://huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B
+    - https://huggingface.co/bartowski/allenai_Llama-3.1-Tulu-3.1-8B-GGUF
+  description: |
+    Tülu 3 is a leading instruction following model family, offering a post-training package with fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern techniques. This is one step of a bigger process to training fully open-source models, like our OLMo models. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
+
+    Version 3.1 update: The new version of our Tülu model is from an improvement only in the final RL stage of training. We switched from PPO to GRPO (no reward model) and did further hyperparameter tuning to achieve substantial performance improvements across the board over the original Tülu 3 8B model.
+  overrides:
+    parameters:
+      model: allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf
+  files:
+    - filename: allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf
+      sha256: 5eae0f1a9bcdea7cad9f1d0d5ba7540bb3de3e2d72293c076a23f24db1c2c7da
+      uri: huggingface://bartowski/allenai_Llama-3.1-Tulu-3.1-8B-GGUF/allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf
 - &deepseek
  url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
  name: "deepseek-coder-v2-lite-instruct"