diff --git a/Makefile b/Makefile index 1e4de71b493a..f48eaaa0ece3 100644 --- a/Makefile +++ b/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?=61408e7fad082dc44a11c8a9f1398da4837aad44 +CPPLLAMA_VERSION?=418f5eef262cea07c2af4f45ee6a88d882221fcb # go-rwkv version RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp @@ -16,7 +16,7 @@ RWKV_VERSION?=661e7ae26d442f5cfebd2a0881b44e8c55949ec6 # whisper.cpp version WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp -WHISPER_CPP_VERSION?=19dca2bb1464326587cbeb7af00f93c4a59b01fd +WHISPER_CPP_VERSION?=0377596b77a3602e36430320cbe45f8c305ef04a # bert.cpp version BERT_REPO?=https://github.com/go-skynet/go-bert.cpp diff --git a/core/http/app_test.go b/core/http/app_test.go index 51663a0db87e..653a03d30587 100644 --- a/core/http/app_test.go +++ b/core/http/app_test.go @@ -562,7 +562,7 @@ var _ = Describe("API test", func() { Eventually(func() bool { response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid) return response["processed"].(bool) - }, "360s", "10s").Should(Equal(true)) + }, "900s", "10s").Should(Equal(true)) By("testing chat") resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: modelName, Messages: []openai.ChatCompletionMessage{ diff --git a/docs/layouts/partials/docs/top-header.html b/docs/layouts/partials/docs/top-header.html new file mode 100644 index 000000000000..375ff779ea3e --- /dev/null +++ b/docs/layouts/partials/docs/top-header.html @@ -0,0 +1,133 @@ + +
+
+
+ +
+ {{ with resources.Get "images/logos/mark.svg" }} + {{ .Content | safeHTML }} + {{ end }} +
+
+ {{ with resources.Get "images/logos/logo.svg" }} + {{ .Content | safeHTML }} + {{ end }} +
+ + + {{ if and (.Site.Params.docsearch.appID) (.Site.Params.docsearch.apiKey) -}} +
+ {{ end }} + {{ if or (not (isset .Site.Params.flexsearch "enabled")) (eq .Site.Params.flexsearch.enabled true) -}} + {{ if and (.Site.Params.docsearch.appID) (.Site.Params.docsearch.apiKey) -}} + {{ else }} + + + {{ end }} + {{ end -}} +
+
+
Star us on GitHub ! 
+ + Star +
+
+ + {{ if eq .Site.Params.docs.darkMode true -}} + + {{ end -}} + {{ if .Site.IsMultiLingual }} +
+ +
    + {{ partial (printf "%s/%s" ($.Scratch.Get "pathName") "i18nlist") . }} +
+
+ {{ end }} +
+
+ + {{ if or (not (isset .Site.Params.flexsearch "enabled")) (eq .Site.Params.flexsearch.enabled true) -}} + {{ if and (.Site.Params.docsearch.appID) (.Site.Params.docsearch.apiKey) -}} + {{ else }} +
+
+
+
  • + + + {{ i18n "search_navigate" | default "to navigate" }} +
    • +
  • + + {{ i18n "search_select" | default "to select" }} +
    • +
  • + + {{ i18n "search_close" | default "to close" }} +
    • +
    +
    +
    + + +
    +
    +
    +
    +
    + {{ end }} + {{ end }} + +
    + \ No newline at end of file diff --git a/gallery/index.yaml b/gallery/index.yaml index cee71257a40d..39bc9e520ed6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -861,6 +861,23 @@ - filename: SmolLM-1.7B-Instruct.Q4_K_M.gguf sha256: 2b07eb2293ed3fc544a9858beda5bfb03dcabda6aa6582d3c85768c95f498d28 uri: huggingface://MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF/SmolLM-1.7B-Instruct.Q4_K_M.gguf +- !!merge <<: *smollm + name: "smollm2-1.7b-instruct" + icon: https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/y45hIMNREW7w_XpHYB_0q.png + urls: + - https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct + - https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF + description: | + SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. + + The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback. + overrides: + parameters: + model: smollm2-1.7b-instruct-q4_k_m.gguf + files: + - filename: smollm2-1.7b-instruct-q4_k_m.gguf + sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33 + uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf - &llama31 ## LLama3.1 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" @@ -2002,6 +2019,20 @@ - filename: Llama-3.1-Hawkish-8B-Q4_K_M.gguf sha256: 613693936bbe641f41560151753716ba549ca052260fc5c0569e943e0bb834c3 uri: huggingface://bartowski/Llama-3.1-Hawkish-8B-GGUF/Llama-3.1-Hawkish-8B-Q4_K_M.gguf +- !!merge <<: *llama31 + name: "llama3.1-bestmix-chem-einstein-8b" + urls: + - https://huggingface.co/ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B + - https://huggingface.co/QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF + description: | + Llama3.1-BestMix-Chem-Einstein-8B is an innovative, meticulously blended model designed to excel in instruction-following, chemistry-focused tasks, and long-form conversational generation. This model fuses the best qualities of multiple Llama3-based architectures, making it highly versatile for both general and specialized tasks. 💻🧠✨ + overrides: + parameters: + model: Llama3.1-BestMix-Chem-Einstein-8B.Q4_K_M.gguf + files: + - filename: Llama3.1-BestMix-Chem-Einstein-8B.Q4_K_M.gguf + sha256: 1a53aa7124c731f33b0b616d7c66a6f78c6a133240acd9e3227f1188f743c1ee + uri: huggingface://QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF/Llama3.1-BestMix-Chem-Einstein-8B.Q4_K_M.gguf - &deepseek ## Deepseek url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" @@ -2696,6 +2727,24 @@ - filename: Darkens-8B.Q4_K_M.gguf sha256: f56a483e10fd00957460adfc16ee462cecac892a4fb44dc59e466e68a360fd42 uri: huggingface://QuantFactory/Darkens-8B-GGUF/Darkens-8B.Q4_K_M.gguf +- !!merge <<: *mistral03 + url: "github:mudler/LocalAI/gallery/chatml.yaml@master" + name: "starcannon-unleashed-12b-v1.0" + icon: https://cdn-uploads.huggingface.co/production/uploads/6720ed503a24966ac66495e8/HXc0AxPLkoIC1fy0Pb3Pb.png + urls: + - https://huggingface.co/VongolaChouko/Starcannon-Unleashed-12B-v1.0 + - https://huggingface.co/QuantFactory/Starcannon-Unleashed-12B-v1.0-GGUF + description: | + This is a merge of pre-trained language models created using mergekit. + MarinaraSpaghetti_NemoMix-Unleashed-12B + Nothingiisreal_MN-12B-Starcannon-v3 + overrides: + parameters: + model: Starcannon-Unleashed-12B-v1.0.Q4_K_M.gguf + files: + - filename: Starcannon-Unleashed-12B-v1.0.Q4_K_M.gguf + sha256: b32c6582d75d2f1d67d567badc691a1338dd1a016c71efbfaf4c91812f398f0e + uri: huggingface://QuantFactory/Starcannon-Unleashed-12B-v1.0-GGUF/Starcannon-Unleashed-12B-v1.0.Q4_K_M.gguf - &mudler ### START mudler's LocalAI specific-models url: "github:mudler/LocalAI/gallery/mudler.yaml@master"