diff --git a/.yamllint b/.yamllint new file mode 100644 index 00000000..8b8a89eb --- /dev/null +++ b/.yamllint @@ -0,0 +1,4 @@ +extends: default + +rules: + line-length: disable \ No newline at end of file diff --git a/gallery/bert-embeddings.yaml b/gallery/bert-embeddings.yaml index 01f05f33..7ce61799 100644 --- a/gallery/bert-embeddings.yaml +++ b/gallery/bert-embeddings.yaml @@ -1,3 +1,4 @@ +--- name: "bert-embeddings" config_file: | @@ -6,6 +7,6 @@ config_file: | backend: bert-embeddings embeddings: true files: -- filename: "bert-MiniLM-L6-v2q4_0.bin" - sha256: "a5a174d8772c8a569faf9f3136c441f2c3855b5bf35ed32274294219533feaad" - uri: "https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin" \ No newline at end of file + - filename: "bert-MiniLM-L6-v2q4_0.bin" + sha256: "a5a174d8772c8a569faf9f3136c441f2c3855b5bf35ed32274294219533feaad" + uri: "https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin" diff --git a/gallery/cerbero.yaml b/gallery/cerbero.yaml index 265d4019..e3e857b9 100644 --- a/gallery/cerbero.yaml +++ b/gallery/cerbero.yaml @@ -1,3 +1,4 @@ +--- config_file: | backend: llama-cpp context_size: 8192 @@ -15,5 +16,5 @@ config_file: | stopwords: - "[|Umano|]" - trimsuffix: + trimsuffix: - "\n" diff --git a/gallery/codellama.yaml b/gallery/codellama.yaml index a4c3233f..b02ad87e 100644 --- a/gallery/codellama.yaml +++ b/gallery/codellama.yaml @@ -1,7 +1,8 @@ +--- name: "codellama" config_file: | backend: llama-cpp context_size: 4096 f16: true - mmap: true \ No newline at end of file + mmap: true diff --git a/gallery/dreamshaper.yaml b/gallery/dreamshaper.yaml index 219a1e53..03146280 100644 --- a/gallery/dreamshaper.yaml +++ b/gallery/dreamshaper.yaml @@ -1,6 +1,6 @@ +--- name: "dreamshaper" - config_file: | backend: diffusers step: 25 diff --git a/gallery/hermes-2-pro-mistral.yaml b/gallery/hermes-2-pro-mistral.yaml index b1dc0ff1..6abee631 100644 --- a/gallery/hermes-2-pro-mistral.yaml +++ b/gallery/hermes-2-pro-mistral.yaml @@ -1,6 +1,6 @@ +--- name: "hermes-2-pro-mistral" - config_file: | mmap: true template: @@ -52,4 +52,3 @@ config_file: | - - "\n" - "\n\n\n" - diff --git a/gallery/index.yaml b/gallery/index.yaml index 8edb9df1..56e434c5 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,4 @@ - +--- ### START parler-tts - &parler-tts url: "github:mudler/LocalAI/gallery/parler-tts.yaml@master" @@ -9,13 +9,13 @@ description: | Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc). It is a reproduction of work from the paper Natural language guidance of high-fidelity text-to-speech with synthetic annotations by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively. urls: - - https://github.com/huggingface/parler-tts + - https://github.com/huggingface/parler-tts tags: - - tts - - gpu - - cpu - - text-to-speech - - python + - tts + - gpu + - cpu + - text-to-speech + - python ### START rerankers - &rerankers url: "github:mudler/LocalAI/gallery/rerankers.yaml@master" @@ -26,9 +26,9 @@ description: | A cross-encoder model that can be used for reranking tags: - - reranker - - gpu - - python + - reranker + - gpu + - python ## LLMs ### START LLAMA3 - &llama3 @@ -49,43 +49,43 @@ Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. urls: - - https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct - - https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF + - https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct + - https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF tags: - - llm - - gguf - - gpu - - cpu - - llama3 + - llm + - gguf + - gpu + - cpu + - llama3 overrides: parameters: model: Meta-Llama-3-8B-Instruct-Q5_K_M.gguf files: - - filename: Meta-Llama-3-8B-Instruct.Q4_0.gguf - sha256: 19ded996fe6c60254dc7544d782276eff41046ed42aa5f2d0005dc457e5c0895 - uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q4_0.gguf + - filename: Meta-Llama-3-8B-Instruct.Q4_0.gguf + sha256: 19ded996fe6c60254dc7544d782276eff41046ed42aa5f2d0005dc457e5c0895 + uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q4_0.gguf - <<: *llama3 name: "llama3-8b-instruct:Q6_K" overrides: parameters: model: Meta-Llama-3-8B-Instruct.Q6_K.gguf files: - - filename: Meta-Llama-3-8B-Instruct.Q6_K.gguf - sha256: b7bad45618e2a76cc1e89a0fbb93a2cac9bf410e27a619c8024ed6db53aa9b4a - uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q6_K.gguf + - filename: Meta-Llama-3-8B-Instruct.Q6_K.gguf + sha256: b7bad45618e2a76cc1e89a0fbb93a2cac9bf410e27a619c8024ed6db53aa9b4a + uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q6_K.gguf - <<: *llama3 name: "llama3-70b-instruct" overrides: parameters: model: Meta-Llama-3-70B-Instruct.Q4_K_M.gguf files: - - filename: Meta-Llama-3-70B-Instruct.Q4_K_M.gguf - sha256: d559de8dd806a76dbd29f8d8bd04666f2b29e7c7872d8e8481abd07805884d72 - uri: huggingface://MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/Meta-Llama-3-70B-Instruct.Q4_K_M.gguf + - filename: Meta-Llama-3-70B-Instruct.Q4_K_M.gguf + sha256: d559de8dd806a76dbd29f8d8bd04666f2b29e7c7872d8e8481abd07805884d72 + uri: huggingface://MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/Meta-Llama-3-70B-Instruct.Q4_K_M.gguf - <<: *llama3 name: "llama-3-sauerkrautlm-8b-instruct" urls: - - https://huggingface.co/bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF + - https://huggingface.co/bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF icon: https://vago-solutions.ai/wp-content/uploads/2024/04/Llama3-Pic.png description: | SauerkrautLM-llama-3-8B-Instruct @@ -96,13 +96,13 @@ parameters: model: Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf files: - - filename: Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf - sha256: 5833d99d5596cade0d02e61cddaa6dac49170864ee56d0b602933c6f9fbae314 - uri: huggingface://bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF/Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf + - filename: Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf + sha256: 5833d99d5596cade0d02e61cddaa6dac49170864ee56d0b602933c6f9fbae314 + uri: huggingface://bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF/Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf - <<: *llama3 name: "llama-3-13b-instruct-v0.1" urls: - - https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF + - https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF icon: https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1/resolve/main/llama-3-merges.webp description: | This model is a self-merge of meta-llama/Meta-Llama-3-8B-Instruct model. @@ -110,13 +110,13 @@ parameters: model: Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf files: - - filename: Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf - sha256: 071a28043c271d259b5ffa883d19a9e0b33269b55148c4abaf5f95da4d084266 - uri: huggingface://MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf + - filename: Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf + sha256: 071a28043c271d259b5ffa883d19a9e0b33269b55148c4abaf5f95da4d084266 + uri: huggingface://MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf - <<: *llama3 name: "llama-3-smaug-8b" urls: - - https://huggingface.co/MaziyarPanahi/Llama-3-Smaug-8B-GGUF + - https://huggingface.co/MaziyarPanahi/Llama-3-Smaug-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/64c14f95cac5f9ba52bbcd7f/OrcJyTaUtD2HxJOPPwNva.png description: | This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-8B. @@ -124,13 +124,13 @@ parameters: model: Llama-3-Smaug-8B.Q4_K_M.gguf files: - - filename: Llama-3-Smaug-8B.Q4_K_M.gguf - sha256: b17c4c1144768ead9e8a96439165baf49e98c53d458b4da8827f137fbabf38c1 - uri: huggingface://MaziyarPanahi/Llama-3-Smaug-8B-GGUF/Llama-3-Smaug-8B.Q4_K_M.gguf + - filename: Llama-3-Smaug-8B.Q4_K_M.gguf + sha256: b17c4c1144768ead9e8a96439165baf49e98c53d458b4da8827f137fbabf38c1 + uri: huggingface://MaziyarPanahi/Llama-3-Smaug-8B-GGUF/Llama-3-Smaug-8B.Q4_K_M.gguf - <<: *llama3 name: "llama-3-8b-openhermes-dpo" urls: - - https://huggingface.co/mradermacher/Llama3-8B-OpenHermes-DPO-GGUF + - https://huggingface.co/mradermacher/Llama3-8B-OpenHermes-DPO-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/64fc6d81d75293f417fee1d1/QF2OsDu9DJKP4QYPBu4aK.png description: | Llama3-8B-OpenHermes-DPO is DPO-Finetuned model of Llama3-8B, on the OpenHermes-2.5 preference dataset using QLoRA. @@ -138,13 +138,13 @@ parameters: model: Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf files: - - filename: Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf - sha256: 1147e5881cb1d67796916e6cab7dab0ae0f532a4c1e626c9e92861e5f67752ca - uri: huggingface://mradermacher/Llama3-8B-OpenHermes-DPO-GGUF/Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf + - filename: Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf + sha256: 1147e5881cb1d67796916e6cab7dab0ae0f532a4c1e626c9e92861e5f67752ca + uri: huggingface://mradermacher/Llama3-8B-OpenHermes-DPO-GGUF/Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf - <<: *llama3 name: "llama-3-unholy-8b" urls: - - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF + - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png description: | Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do. @@ -156,13 +156,13 @@ parameters: model: Llama-3-Unholy-8B.q4_k_m.gguf files: - - filename: Llama-3-Unholy-8B.q4_k_m.gguf - sha256: 17b7f716bce1b34d4aa99ee730a19a834f8c77ddb36090dde5a1eda963f93602 - uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q4_k_m.gguf + - filename: Llama-3-Unholy-8B.q4_k_m.gguf + sha256: 17b7f716bce1b34d4aa99ee730a19a834f8c77ddb36090dde5a1eda963f93602 + uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q4_k_m.gguf - <<: *llama3 name: "lexi-llama-3-8b-uncensored" urls: - - https://huggingface.co/NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF + - https://huggingface.co/NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/H6axm5mlmiOWnbIFvx_em.png description: | Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. @@ -174,13 +174,13 @@ parameters: model: lexi-llama-3-8b-uncensored.Q6_K.gguf files: - - filename: lexi-llama-3-8b-uncensored.Q6_K.gguf - sha256: 5805f3856cc18a769fae0b7c5659fe6778574691c370c910dad6eeec62c62436 - uri: huggingface://NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF/lexi-llama-3-8b-uncensored.Q6_K.gguf + - filename: lexi-llama-3-8b-uncensored.Q6_K.gguf + sha256: 5805f3856cc18a769fae0b7c5659fe6778574691c370c910dad6eeec62c62436 + uri: huggingface://NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF/lexi-llama-3-8b-uncensored.Q6_K.gguf - <<: *llama3 name: "chaos-rp_l3_b-iq-imatrix" urls: - - https://huggingface.co/Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix + - https://huggingface.co/Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/u5p9kdbXT2QQA3iMU0vF1.png description: | A chaotic force beckons for you, will you heed her call? @@ -192,13 +192,13 @@ parameters: model: Chaos_RP_l3_8B-Q4_K_M-imat.gguf files: - - filename: Chaos_RP_l3_8B-Q4_K_M-imat.gguf - sha256: 4273c5a8f23d49bf6294e620a5aa1fcd78d491ea0b90d0ec63ad708eedb83893 - uri: huggingface://Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix/Chaos_RP_l3_8B-Q4_K_M-imat.gguf + - filename: Chaos_RP_l3_8B-Q4_K_M-imat.gguf + sha256: 4273c5a8f23d49bf6294e620a5aa1fcd78d491ea0b90d0ec63ad708eedb83893 + uri: huggingface://Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix/Chaos_RP_l3_8B-Q4_K_M-imat.gguf - <<: *llama3 name: "llama-3-unholy-8b:Q8_0" urls: - - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF + - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png description: | Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do. @@ -210,20 +210,20 @@ parameters: model: Llama-3-Unholy-8B.q8_0.gguf files: - - filename: Llama-3-Unholy-8B.q8_0.gguf - sha256: 8d4137018acdcd57df4beccc84d9ad3f7f08cac50588f76370afc16c85752702 - uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q8_0.gguf + - filename: Llama-3-Unholy-8B.q8_0.gguf + sha256: 8d4137018acdcd57df4beccc84d9ad3f7f08cac50588f76370afc16c85752702 + uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q8_0.gguf - <<: *llama3 name: "therapyllama-8b-v1" urls: - - https://huggingface.co/victunes/TherapyLlama-8B-v1-GGUF + - https://huggingface.co/victunes/TherapyLlama-8B-v1-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/65f07d05279d2d8f725bf0c3/A-ckcZ9H0Ee1n_ls2FM41.png description: | Trained on Llama 3 8B using a modified version of jerryjalapeno/nart-100k-synthetic. It is a Llama 3 version of https://huggingface.co/victunes/TherapyBeagle-11B-v2 - TherapyLlama is hopefully aligned to be helpful, healthy, and comforting. + TherapyLlama is hopefully aligned to be helpful, healthy, and comforting. Usage: Do not hold back on Buddy. Open up to Buddy. @@ -243,56 +243,56 @@ parameters: model: TherapyLlama-8B-v1-Q4_K_M.gguf files: - - filename: TherapyLlama-8B-v1-Q4_K_M.gguf - sha256: 3d5a16d458e074a7bc7e706a493d8e95e8a7b2cb16934c851aece0af9d1da14a - uri: huggingface://victunes/TherapyLlama-8B-v1-GGUF/TherapyLlama-8B-v1-Q4_K_M.gguf + - filename: TherapyLlama-8B-v1-Q4_K_M.gguf + sha256: 3d5a16d458e074a7bc7e706a493d8e95e8a7b2cb16934c851aece0af9d1da14a + uri: huggingface://victunes/TherapyLlama-8B-v1-GGUF/TherapyLlama-8B-v1-Q4_K_M.gguf - <<: *llama3 name: "aura-uncensored-l3-8b-iq-imatrix" urls: - - https://huggingface.co/Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix + - https://huggingface.co/Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/oiYHWIEHqmgUkY0GsVdDx.png description: | - This is another better atempt at a less censored Llama-3 with hopefully more stable formatting. + This is another better atempt at a less censored Llama-3 with hopefully more stable formatting. overrides: parameters: model: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf files: - - filename: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf - sha256: 265ded6a4f439bec160f394e3083a4a20e32ebb9d1d2d85196aaab23dab87fb2 - uri: huggingface://Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix/Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf + - filename: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf + sha256: 265ded6a4f439bec160f394e3083a4a20e32ebb9d1d2d85196aaab23dab87fb2 + uri: huggingface://Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix/Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf - &dolphin name: "dolphin-2.9-llama3-8b" url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master" urls: - - https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-gguf + - https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-gguf tags: - - llm - - gguf - - gpu - - cpu - - llama3 + - llm + - gguf + - gpu + - cpu + - llama3 license: llama3 description: | Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. - Dolphin is uncensored. + Dolphin is uncensored. Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png overrides: parameters: model: dolphin-2.9-llama3-8b-q4_K_M.gguf files: - - filename: dolphin-2.9-llama3-8b-q4_K_M.gguf - sha256: be988199ce28458e97205b11ae9d9cf4e3d8e18ff4c784e75bfc12f54407f1a1 - uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q4_K_M.gguf + - filename: dolphin-2.9-llama3-8b-q4_K_M.gguf + sha256: be988199ce28458e97205b11ae9d9cf4e3d8e18ff4c784e75bfc12f54407f1a1 + uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q4_K_M.gguf - <<: *dolphin name: "dolphin-2.9-llama3-8b:Q6_K" overrides: parameters: model: dolphin-2.9-llama3-8b-q6_K.gguf files: - - filename: dolphin-2.9-llama3-8b-q6_K.gguf - sha256: 8aac72a0bd72c075ba7be1aa29945e47b07d39cd16be9a80933935f51b57fb32 - uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q6_K.gguf + - filename: dolphin-2.9-llama3-8b-q6_K.gguf + sha256: 8aac72a0bd72c075ba7be1aa29945e47b07d39cd16be9a80933935f51b57fb32 + uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q6_K.gguf ## LLama2 and derivatives ### Start Fimbulvetr - &vicuna-chat @@ -304,20 +304,20 @@ description: | Cute girl to catch your attention. urls: - - https://huggingface.co/Sao10K/Fimbulvetr-11B-v2-GGUF + - https://huggingface.co/Sao10K/Fimbulvetr-11B-v2-GGUF tags: - - llm - - gguf - - gpu - - cpu - - llama3 + - llm + - gguf + - gpu + - cpu + - llama3 overrides: parameters: model: Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf files: - - filename: Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf - sha256: 3597dacfb0ab717d565d8a4d6067f10dcb0e26cc7f21c832af1a10a87882a8fd - uri: huggingface://Sao10K/Fimbulvetr-11B-v2-GGUF/Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf + - filename: Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf + sha256: 3597dacfb0ab717d565d8a4d6067f10dcb0e26cc7f21c832af1a10a87882a8fd + uri: huggingface://Sao10K/Fimbulvetr-11B-v2-GGUF/Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf ### Start noromaid - &noromaid url: "github:mudler/LocalAI/gallery/noromaid.yaml@master" @@ -325,48 +325,48 @@ icon: https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/VKX2Z2yjZX5J8kXzgeCYO.png license: cc-by-nc-4.0 urls: - - https://huggingface.co/NeverSleep/Noromaid-13B-0.4-DPO-GGUF + - https://huggingface.co/NeverSleep/Noromaid-13B-0.4-DPO-GGUF tags: - - llm - - llama2 - - gguf - - gpu - - cpu + - llm + - llama2 + - gguf + - gpu + - cpu overrides: parameters: model: Noromaid-13B-0.4-DPO.q4_k_m.gguf files: - - filename: Noromaid-13B-0.4-DPO.q4_k_m.gguf - sha256: cb28e878d034fae3d0b43326c5fc1cfb4ab583b17c56e41d6ce023caec03c1c1 - uri: huggingface://NeverSleep/Noromaid-13B-0.4-DPO-GGUF/Noromaid-13B-0.4-DPO.q4_k_m.gguf + - filename: Noromaid-13B-0.4-DPO.q4_k_m.gguf + sha256: cb28e878d034fae3d0b43326c5fc1cfb4ab583b17c56e41d6ce023caec03c1c1 + uri: huggingface://NeverSleep/Noromaid-13B-0.4-DPO-GGUF/Noromaid-13B-0.4-DPO.q4_k_m.gguf ### START LLaVa - &llava url: "github:mudler/LocalAI/gallery/llava.yaml@master" license: apache-2.0 description: | - LLaVA represents a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking spirits of the multimodal GPT-4 and setting a new state-of-the-art accuracy on Science QA. + LLaVA represents a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking spirits of the multimodal GPT-4 and setting a new state-of-the-art accuracy on Science QA. urls: - - https://llava-vl.github.io/ + - https://llava-vl.github.io/ tags: - - llm - - multimodal - - gguf - - gpu - - llama2 - - cpu + - llm + - multimodal + - gguf + - gpu + - llama2 + - cpu name: "llava-1.6-vicuna" overrides: mmproj: mmproj-vicuna7b-f16.gguf parameters: model: vicuna-7b-q5_k.gguf files: - - filename: vicuna-7b-q5_k.gguf - uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf - - filename: mmproj-vicuna7b-f16.gguf - uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf + - filename: vicuna-7b-q5_k.gguf + uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf + - filename: mmproj-vicuna7b-f16.gguf + uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf - <<: *llava name: "llava-1.6-mistral" overrides: @@ -374,12 +374,12 @@ parameters: model: llava-v1.6-mistral-7b.gguf files: - - filename: llava-v1.6-mistral-7b.gguf - sha256: 31826170ffa2e8080bbcd74cac718f906484fd5a59895550ef94c1baa4997595 - uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q6_K.gguf - - filename: llava-v1.6-7b-mmproj-f16.gguf - sha256: 00205ee8a0d7a381900cd031e43105f86aa0d8c07bf329851e85c71a26632d16 - uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf + - filename: llava-v1.6-mistral-7b.gguf + sha256: 31826170ffa2e8080bbcd74cac718f906484fd5a59895550ef94c1baa4997595 + uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q6_K.gguf + - filename: llava-v1.6-7b-mmproj-f16.gguf + sha256: 00205ee8a0d7a381900cd031e43105f86aa0d8c07bf329851e85c71a26632d16 + uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf - <<: *llava name: "llava-1.5" overrides: @@ -387,12 +387,12 @@ parameters: model: llava-v1.5-7b-Q4_K.gguf files: - - filename: llava-v1.5-7b-Q4_K.gguf - sha256: c91ebf0a628ceb25e374df23ad966cc1bf1514b33fecf4f0073f9619dec5b3f9 - uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-Q4_K.gguf - - filename: llava-v1.5-7b-mmproj-Q8_0.gguf - sha256: 09c230de47f6f843e4841656f7895cac52c6e7ec7392acb5e8527de8b775c45a - uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-mmproj-Q8_0.gguf + - filename: llava-v1.5-7b-Q4_K.gguf + sha256: c91ebf0a628ceb25e374df23ad966cc1bf1514b33fecf4f0073f9619dec5b3f9 + uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-Q4_K.gguf + - filename: llava-v1.5-7b-mmproj-Q8_0.gguf + sha256: 09c230de47f6f843e4841656f7895cac52c6e7ec7392acb5e8527de8b775c45a + uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-mmproj-Q8_0.gguf ### START Phi-2 - &phi-2-chat url: "github:mudler/LocalAI/gallery/phi-2-chat.yaml@master" @@ -416,32 +416,32 @@ Finetuned from model: Phi-2 urls: - - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml - - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml-gguf + - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml + - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml-gguf tags: - - llm - - gguf - - gpu - - llama2 - - cpu + - llm + - gguf + - gpu + - llama2 + - cpu name: "phi-2-chat:Q8_0" overrides: parameters: model: phi-2-layla-v1-chatml-Q8_0.gguf files: - - filename: "phi-2-layla-v1-chatml-Q8_0.gguf" - sha256: "0cf542a127c2c835066a78028009b7eddbaf773cc2a26e1cb157ce5e09c1a2e0" - uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf" + - filename: "phi-2-layla-v1-chatml-Q8_0.gguf" + sha256: "0cf542a127c2c835066a78028009b7eddbaf773cc2a26e1cb157ce5e09c1a2e0" + uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf" - <<: *phi-2-chat name: "phi-2-chat" overrides: parameters: model: phi-2-layla-v1-chatml-Q4_K.gguf files: - - filename: "phi-2-layla-v1-chatml-Q4_K.gguf" - sha256: "b071e5624b60b8911f77261398802c4b4079c6c689e38e2ce75173ed62bc8a48" - uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q4_K.gguf" + - filename: "phi-2-layla-v1-chatml-Q4_K.gguf" + sha256: "b071e5624b60b8911f77261398802c4b4079c6c689e38e2ce75173ed62bc8a48" + uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q4_K.gguf" - <<: *phi-2-chat license: mit icon: "https://huggingface.co/rhysjones/phi-2-orange/resolve/main/phi-2-orange.jpg" @@ -450,23 +450,23 @@ There is an updated model at rhysjones/phi-2-orange-v2 which has higher evals, if you wish to test. urls: - - https://huggingface.co/rhysjones/phi-2-orange - - https://huggingface.co/TheBloke/phi-2-orange-GGUF + - https://huggingface.co/rhysjones/phi-2-orange + - https://huggingface.co/TheBloke/phi-2-orange-GGUF tags: - - llm - - gguf - - llama2 - - gpu - - cpu + - llm + - gguf + - llama2 + - gpu + - cpu name: "phi-2-orange" overrides: parameters: model: phi-2-orange.Q4_0.gguf files: - - filename: "phi-2-orange.Q4_0.gguf" - sha256: "49cb710ae688e1b19b1b299087fa40765a0cd677e3afcc45e5f7ef6750975dcf" - uri: "huggingface://TheBloke/phi-2-orange-GGUF/phi-2-orange.Q4_0.gguf" + - filename: "phi-2-orange.Q4_0.gguf" + sha256: "49cb710ae688e1b19b1b299087fa40765a0cd677e3afcc45e5f7ef6750975dcf" + uri: "huggingface://TheBloke/phi-2-orange-GGUF/phi-2-orange.Q4_0.gguf" ### START Phi-3 - &phi-3 url: "github:mudler/LocalAI/gallery/phi-3-chat.yaml@master" @@ -477,30 +477,30 @@ The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Mini version in two variants 4K and 128K which is the context length (in tokens) it can support. The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3 Mini-4K-Instruct showcased a robust and state-of-the-art performance among models with less than 13 billion parameters. urls: - - https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf + - https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf tags: - - llm - - gguf - - gpu - - llama2 - - cpu + - llm + - gguf + - gpu + - llama2 + - cpu overrides: parameters: model: Phi-3-mini-4k-instruct-q4.gguf files: - - filename: "Phi-3-mini-4k-instruct-q4.gguf" - sha256: "4fed7364ee3e0c7cb4fe0880148bfdfcd1b630981efa0802a6b62ee52e7da97e" - uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-q4.gguf" + - filename: "Phi-3-mini-4k-instruct-q4.gguf" + sha256: "4fed7364ee3e0c7cb4fe0880148bfdfcd1b630981efa0802a6b62ee52e7da97e" + uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-q4.gguf" - <<: *phi-3 name: "phi-3-mini-4k-instruct:fp16" overrides: parameters: model: Phi-3-mini-4k-instruct-fp16.gguf files: - - filename: "Phi-3-mini-4k-instruct-fp16.gguf" - sha256: "ad9f8ff11cd096115adc8ff50befa22fc3da2718672ddd2ab30faccd70488605" - uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-fp16.gguf" + - filename: "Phi-3-mini-4k-instruct-fp16.gguf" + sha256: "ad9f8ff11cd096115adc8ff50befa22fc3da2718672ddd2ab30faccd70488605" + uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-fp16.gguf" ### START Hermes-2-Pro-Mistral - &hermes-2-pro-mistral url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master" @@ -520,39 +520,39 @@ Learn more about the function calling on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main urls: - - https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF + - https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF tags: - - llm - - gguf - - gpu - - llama2 - - cpu + - llm + - gguf + - gpu + - llama2 + - cpu overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q4_0.gguf files: - - filename: "Hermes-2-Pro-Mistral-7B.Q4_0.gguf" - sha256: "f446c3125026f7af6757dd097dda02280adc85e908c058bd6f1c41a118354745" - uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q4_0.gguf" + - filename: "Hermes-2-Pro-Mistral-7B.Q4_0.gguf" + sha256: "f446c3125026f7af6757dd097dda02280adc85e908c058bd6f1c41a118354745" + uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q4_0.gguf" - <<: *hermes-2-pro-mistral name: "hermes-2-pro-mistral:Q6_K" overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q6_K.gguf files: - - filename: "Hermes-2-Pro-Mistral-7B.Q6_K.gguf" - sha256: "40adc3b227bc36764de148fdda4df5df385adc06650d58d4dbe726ee0214eeff" - uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf" + - filename: "Hermes-2-Pro-Mistral-7B.Q6_K.gguf" + sha256: "40adc3b227bc36764de148fdda4df5df385adc06650d58d4dbe726ee0214eeff" + uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf" - <<: *hermes-2-pro-mistral name: "hermes-2-pro-mistral:Q8_0" overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q8_0.gguf files: - - filename: "Hermes-2-Pro-Mistral-7B.Q8_0.gguf" - sha256: "b6d95d7ec9a395b7568cc94b0447fd4f90b6f69d6e44794b1fbb84e3f732baca" - uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q8_0.gguf" + - filename: "Hermes-2-Pro-Mistral-7B.Q8_0.gguf" + sha256: "b6d95d7ec9a395b7568cc94b0447fd4f90b6f69d6e44794b1fbb84e3f732baca" + uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q8_0.gguf" ### END Hermes-2-Pro-Mistral ### START Cerbero - url: "github:mudler/LocalAI/gallery/cerbero.yaml@master" @@ -560,20 +560,20 @@ description: | cerbero-7b is specifically crafted to fill the void in Italy's AI landscape. urls: - - https://huggingface.co/galatolo/cerbero-7b + - https://huggingface.co/galatolo/cerbero-7b tags: - - llm - - gguf - - gpu - - cpu - - mistral + - llm + - gguf + - gpu + - cpu + - mistral overrides: parameters: model: galatolo-Q4_K.gguf files: - - filename: "galatolo-Q4_K.gguf" - sha256: "ca0cfd5a9ad40dc16416aa3a277015d0299b62c0803b67f5709580042202c172" - uri: "huggingface://galatolo/cerbero-7b-gguf/ggml-model-Q4_K.gguf" + - filename: "galatolo-Q4_K.gguf" + sha256: "ca0cfd5a9ad40dc16416aa3a277015d0299b62c0803b67f5709580042202c172" + uri: "huggingface://galatolo/cerbero-7b-gguf/ggml-model-Q4_K.gguf" ### START Codellama - &codellama url: "github:mudler/LocalAI/gallery/codellama.yaml@master" @@ -584,34 +584,34 @@ Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This model is designed for general code synthesis and understanding. urls: - - https://huggingface.co/TheBloke/CodeLlama-7B-GGUF - - https://huggingface.co/meta-llama/CodeLlama-7b-hf + - https://huggingface.co/TheBloke/CodeLlama-7B-GGUF + - https://huggingface.co/meta-llama/CodeLlama-7b-hf tags: - - llm - - gguf - - gpu - - llama2 - - cpu + - llm + - gguf + - gpu + - llama2 + - cpu overrides: parameters: model: codellama-7b.Q4_0.gguf files: - - filename: "codellama-7b.Q4_0.gguf" - sha256: "33052f6dd41436db2f83bd48017b6fff8ce0184e15a8a227368b4230f1da97b5" - uri: "huggingface://TheBloke/CodeLlama-7B-GGUF/codellama-7b.Q4_0.gguf" + - filename: "codellama-7b.Q4_0.gguf" + sha256: "33052f6dd41436db2f83bd48017b6fff8ce0184e15a8a227368b4230f1da97b5" + uri: "huggingface://TheBloke/CodeLlama-7B-GGUF/codellama-7b.Q4_0.gguf" ### START Embeddings - &sentencentransformers description: | This framework provides an easy method to compute dense vector representations for sentences, paragraphs, and images. The models are based on transformer networks like BERT / RoBERTa / XLM-RoBERTa etc. and achieve state-of-the-art performance in various tasks. Text is embedded in vector space such that similar text are closer and can efficiently be found using cosine similarity. urls: - - https://github.com/UKPLab/sentence-transformers + - https://github.com/UKPLab/sentence-transformers tags: - - gpu - - cpu - - embeddings - - python + - gpu + - cpu + - embeddings + - python name: "all-MiniLM-L6-v2" url: "github:mudler/LocalAI/gallery/sentencetransformers.yaml@master" overrides: @@ -628,42 +628,42 @@ A text-to-image model that uses Stable Diffusion 1.5 to generate images from text prompts. This model is DreamShaper model by Lykon. urls: - - https://civitai.com/models/4384/dreamshaper + - https://civitai.com/models/4384/dreamshaper tags: - - text-to-image - - stablediffusion - - python - - sd-1.5 - - gpu + - text-to-image + - stablediffusion + - python + - sd-1.5 + - gpu url: "github:mudler/LocalAI/gallery/dreamshaper.yaml@master" overrides: parameters: model: DreamShaper_8_pruned.safetensors files: - - filename: DreamShaper_8_pruned.safetensors - uri: huggingface://Lykon/DreamShaper/DreamShaper_8_pruned.safetensors - sha256: 879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd + - filename: DreamShaper_8_pruned.safetensors + uri: huggingface://Lykon/DreamShaper/DreamShaper_8_pruned.safetensors + sha256: 879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd ## Whisper - url: "github:mudler/LocalAI/gallery/whisper-base.yaml@master" name: "whisper-1" license: "MIT" urls: - - https://github.com/ggerganov/whisper.cpp - - https://huggingface.co/ggerganov/whisper.cpp + - https://github.com/ggerganov/whisper.cpp + - https://huggingface.co/ggerganov/whisper.cpp description: | Port of OpenAI's Whisper model in C/C++ - + ## Bert embeddings - url: "github:mudler/LocalAI/gallery/bert-embeddings.yaml@master" name: "bert-embeddings" license: "Apache 2.0" urls: - - https://huggingface.co/skeskinen/ggml + - https://huggingface.co/skeskinen/ggml tags: - - embeddings + - embeddings description: | Bert model that can be used for embeddings @@ -671,13 +671,13 @@ - url: github:mudler/LocalAI/gallery/stablediffusion.yaml@master license: "BSD-3" urls: - - https://github.com/EdVince/Stable-Diffusion-NCNN - - https://github.com/EdVince/Stable-Diffusion-NCNN/blob/main/LICENSE + - https://github.com/EdVince/Stable-Diffusion-NCNN + - https://github.com/EdVince/Stable-Diffusion-NCNN/blob/main/LICENSE description: | - Stable Diffusion in NCNN with c++, supported txt2img and img2img + Stable Diffusion in NCNN with c++, supported txt2img and img2img name: stablediffusion-cpp - + ## Tiny Dream - url: github:mudler/LocalAI/gallery/tinydream.yaml@master name: tinydream @@ -702,9 +702,9 @@ A fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. Piper is used in a variety of [projects](https://github.com/rhasspy/piper#people-using-piper). tags: - - tts - - text-to-speech - - cpu + - tts + - text-to-speech + - cpu override: parameters: @@ -786,7 +786,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-thorsten-low - + override: parameters: model: de-thorsten-low.onnx @@ -796,7 +796,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-el-gr-rapunzelina-low - + override: parameters: model: el-gr-rapunzelina-low.onnx @@ -806,7 +806,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-gb-alan-low - + override: parameters: model: en-gb-alan-low.onnx @@ -816,7 +816,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-gb-southern_english_female-low - + override: parameters: model: en-gb-southern_english @@ -826,7 +826,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-amy-low - + override: parameters: model: en-us-amy-low.onnx @@ -836,7 +836,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-danny-low - + override: parameters: model: en-us-danny-low.onnx @@ -846,7 +846,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-kathleen-low - + override: parameters: model: en-us-kathleen-low.onnx @@ -856,7 +856,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-lessac-low - + override: parameters: model: en-us-lessac-low.onnx @@ -866,7 +866,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-lessac-medium - + override: parameters: model: en-us-lessac-medium.onnx @@ -876,7 +876,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-libritts-high - + override: parameters: model: en-us-libritts-high.onnx @@ -886,7 +886,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-high - + override: parameters: model: en-us-ryan-high.onnx @@ -896,7 +896,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-low - + override: parameters: model: en-us-ryan-low.onnx @@ -907,7 +907,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-medium - + override: parameters: model: en-us-ryan-medium.onnx @@ -938,7 +938,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-es-mls_10246-low - + override: parameters: model: es-mls_10246-low.onnx @@ -949,7 +949,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-es-mls_9972-low - + override: parameters: model: es-mls_9972-low.onnx @@ -960,7 +960,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fi-harri-low - + override: parameters: model: fi-harri-low.onnx @@ -971,7 +971,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-gilles-low - + override: parameters: model: fr-gilles-low.onnx @@ -982,7 +982,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-mls_1840-low - + override: parameters: model: fr-mls_1840-low.onnx @@ -993,7 +993,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-siwis-low - + override: parameters: model: fr-siwis-low.onnx @@ -1004,7 +1004,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-siwis-medium - + override: parameters: model: fr-siwis-medium.onnx @@ -1015,7 +1015,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-bui-medium - + override: parameters: model: is-bui-medium.onnx @@ -1026,7 +1026,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-salka-medium - + override: parameters: model: is-salka-medium.onnx @@ -1037,7 +1037,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-steinn-medium - + override: parameters: model: is-steinn-medium.onnx @@ -1048,7 +1048,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-ugla-medium - + override: parameters: model: is-ugla-medium.onnx @@ -1059,7 +1059,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-it-riccardo_fasol-x-low - + override: parameters: model: it-riccardo_fasol-x-low.onnx @@ -1070,7 +1070,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-iseke-x-low - + override: parameters: model: kk-iseke-x-low.onnx @@ -1081,7 +1081,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-issai-high - + override: parameters: model: kk-issai-high.onnx @@ -1092,7 +1092,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-raya-x-low - + override: parameters: model: kk-raya-x-low.onnx @@ -1103,7 +1103,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ne-google-medium - + override: parameters: model: ne-google-medium.onnx @@ -1114,7 +1114,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ne-google-x-low - + override: parameters: model: ne-google-x-low.onnx @@ -1125,7 +1125,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-mls_5809-low - + override: parameters: model: nl-mls_5809-low.onnx @@ -1136,7 +1136,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-mls_7432-low - + override: parameters: model: nl-mls_7432-low.onnx @@ -1147,7 +1147,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-nathalie-x-low - + override: parameters: model: nl-nathalie-x-low.onnx @@ -1158,7 +1158,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-rdh-medium - + override: parameters: model: nl-rdh-medium.onnx @@ -1169,7 +1169,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-rdh-x-low - + override: parameters: model: nl-rdh-x-low.onnx @@ -1180,7 +1180,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-no-talesyntese-medium - + override: parameters: model: no-talesyntese-medium.onnx @@ -1191,7 +1191,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-pl-mls_6892-low - + override: parameters: model: pl-mls_6892-low.onnx @@ -1202,7 +1202,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-pt-br-edresson-low - + override: parameters: model: pt-br-edresson-low.onnx @@ -1213,7 +1213,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ru-irinia-medium - + override: parameters: model: ru-irinia-medium.onnx @@ -1224,7 +1224,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-sv-se-nst-medium - + override: parameters: model: sv-se-nst-medium.onnx @@ -1235,7 +1235,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-uk-lada-x-low - + override: parameters: model: uk-lada-x-low.onnx @@ -1246,7 +1246,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-vi-25hours-single-low - + override: parameters: model: vi-25hours-single-low.onnx @@ -1257,7 +1257,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-vi-vivos-x-low - + override: parameters: model: vi-vivos-x-low.onnx @@ -1268,7 +1268,7 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-zh-cn-huayan-x-low - + override: parameters: model: zh-cn-huayan-x-low.onnx @@ -1279,10 +1279,10 @@ - <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-zh_CN-huayan-medium - + override: parameters: model: zh_CN-huayan-medium.onnx files: - filename: voice-zh_CN-huayan-medium.tar.gz - uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-zh_CN-huayan-medium.tar.gz \ No newline at end of file + uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-zh_CN-huayan-medium.tar.gz diff --git a/gallery/llama3-instruct.yaml b/gallery/llama3-instruct.yaml index 96272c58..f6016cbd 100644 --- a/gallery/llama3-instruct.yaml +++ b/gallery/llama3-instruct.yaml @@ -1,6 +1,6 @@ +--- name: "llama3-instruct" - config_file: | mmap: true template: diff --git a/gallery/llava.yaml b/gallery/llava.yaml index 44c1aa97..4d07847a 100644 --- a/gallery/llava.yaml +++ b/gallery/llava.yaml @@ -1,6 +1,6 @@ +--- name: "llava" - config_file: | backend: llama-cpp context_size: 4096 diff --git a/gallery/noromaid.yaml b/gallery/noromaid.yaml index 0b9badfe..4772e4ec 100644 --- a/gallery/noromaid.yaml +++ b/gallery/noromaid.yaml @@ -1,3 +1,4 @@ +--- config_file: | mmap: true backend: llama-cpp @@ -50,4 +51,3 @@ config_file: | - - "\n" - "\n\n\n" - diff --git a/gallery/parler-tts.yaml b/gallery/parler-tts.yaml index 76252b1d..98d4614b 100644 --- a/gallery/parler-tts.yaml +++ b/gallery/parler-tts.yaml @@ -1,2 +1,3 @@ +--- config_file: | backend: parler-tts diff --git a/gallery/phi-2-chat.yaml b/gallery/phi-2-chat.yaml index 3fc84d3b..5e1fb702 100644 --- a/gallery/phi-2-chat.yaml +++ b/gallery/phi-2-chat.yaml @@ -1,6 +1,6 @@ +--- name: "phi-2-chatml" - config_file: | mmap: true template: @@ -16,4 +16,3 @@ config_file: | f16: true stopwords: - <|im_end|> - diff --git a/gallery/phi-2-orange.yaml b/gallery/phi-2-orange.yaml index 645875ad..89971b4d 100644 --- a/gallery/phi-2-orange.yaml +++ b/gallery/phi-2-orange.yaml @@ -1,3 +1,4 @@ +--- name: "phi-2-orange" config_file: | diff --git a/gallery/phi-3-chat.yaml b/gallery/phi-3-chat.yaml index b17e5bb4..ede4fd0f 100644 --- a/gallery/phi-3-chat.yaml +++ b/gallery/phi-3-chat.yaml @@ -1,3 +1,4 @@ +--- name: "phi-3-chat" config_file: | @@ -15,4 +16,3 @@ config_file: | f16: true stopwords: - <|end|> - diff --git a/gallery/piper.yaml b/gallery/piper.yaml index eb1a6ecc..c7f40f8c 100644 --- a/gallery/piper.yaml +++ b/gallery/piper.yaml @@ -1,2 +1,3 @@ +--- config_file: | backend: piper diff --git a/gallery/rerankers.yaml b/gallery/rerankers.yaml index dbbad5a0..a4ac48ca 100644 --- a/gallery/rerankers.yaml +++ b/gallery/rerankers.yaml @@ -1,2 +1,3 @@ +--- config_file: | - backend: rerankers \ No newline at end of file + backend: rerankers diff --git a/gallery/sentencetransformers.yaml b/gallery/sentencetransformers.yaml index 9ba5d29b..e8ba7aa0 100644 --- a/gallery/sentencetransformers.yaml +++ b/gallery/sentencetransformers.yaml @@ -1,4 +1,5 @@ +--- name: "sentencetransformers" config_file: | - backend: sentencetransformers \ No newline at end of file + backend: sentencetransformers diff --git a/gallery/stablediffusion.yaml b/gallery/stablediffusion.yaml index 9b1cad32..f84de7f2 100644 --- a/gallery/stablediffusion.yaml +++ b/gallery/stablediffusion.yaml @@ -1,3 +1,4 @@ +--- name: "stablediffusion-cpp" config_file: | @@ -7,42 +8,42 @@ config_file: | model: stablediffusion_assets files: -- filename: "stablediffusion_assets/AutoencoderKL-256-256-fp16-opt.param" - sha256: "18ca4b66685e21406bcf64c484b3b680b4949900415536d599cc876579c85c82" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-256-256-fp16-opt.param" -- filename: "stablediffusion_assets/AutoencoderKL-512-512-fp16-opt.param" - sha256: "cf45f63aacf3dbbab0f59ed92a6f2c14d9a1801314631cd3abe91e3c85639a20" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-512-512-fp16-opt.param" -- filename: "stablediffusion_assets/AutoencoderKL-base-fp16.param" - sha256: "0254a056dce61b0c27dc9ec1b78b53bcf55315c540f55f051eb841aa992701ba" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-base-fp16.param" -- filename: "stablediffusion_assets/AutoencoderKL-encoder-512-512-fp16.bin" - sha256: "ddcb79a9951b9f91e05e087739ed69da2c1c4ae30ba4168cce350b49d617c9fa" - uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-encoder-512-512-fp16.bin" -- filename: "stablediffusion_assets/AutoencoderKL-fp16.bin" - sha256: "f02e71f80e70252734724bbfaed5c4ddd3a8ed7e61bb2175ff5f53099f0e35dd" - uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-fp16.bin" -- filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.bin" - sha256: "1c9a12f4e1dd1b295a388045f7f28a2352a4d70c3dc96a542189a3dd7051fdd6" - uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/FrozenCLIPEmbedder-fp16.bin" -- filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.param" - sha256: "471afbe678dd1fd3fe764ef9c6eccaccb0a7d7e601f27b462aa926b20eb368c9" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/FrozenCLIPEmbedder-fp16.param" -- filename: "stablediffusion_assets/log_sigmas.bin" - sha256: "a2089f8aa4c61f9c200feaec541ab3f5c94233b28deb6d5e8bcd974fa79b68ac" - uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/raw/main/x86/linux/assets/log_sigmas.bin" -- filename: "stablediffusion_assets/UNetModel-256-256-MHA-fp16-opt.param" - sha256: "a58c380229f09491776df837b7aa7adffc0a87821dc4708b34535da2e36e3da1" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-256-256-MHA-fp16-opt.param" -- filename: "stablediffusion_assets/UNetModel-512-512-MHA-fp16-opt.param" - sha256: "f12034067062827bd7f43d1d21888d1f03905401acf6c6eea22be23c259636fa" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-512-512-MHA-fp16-opt.param" -- filename: "stablediffusion_assets/UNetModel-base-MHA-fp16.param" - sha256: "696f6975de49f4325b53ce32aff81861a6d6c07cd9ce3f0aae2cc405350af38d" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-base-MHA-fp16.param" -- filename: "stablediffusion_assets/UNetModel-MHA-fp16.bin" - sha256: "d618918d011bfc1f644c0f2a33bf84931bd53b28a98492b0a8ed6f3a818852c3" - uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/UNetModel-MHA-fp16.bin" -- filename: "stablediffusion_assets/vocab.txt" - sha256: "e30e57b6f1e47616982ef898d8922be24e535b4fa3d0110477b3a6f02ebbae7d" - uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/vocab.txt" \ No newline at end of file + - filename: "stablediffusion_assets/AutoencoderKL-256-256-fp16-opt.param" + sha256: "18ca4b66685e21406bcf64c484b3b680b4949900415536d599cc876579c85c82" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-256-256-fp16-opt.param" + - filename: "stablediffusion_assets/AutoencoderKL-512-512-fp16-opt.param" + sha256: "cf45f63aacf3dbbab0f59ed92a6f2c14d9a1801314631cd3abe91e3c85639a20" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-512-512-fp16-opt.param" + - filename: "stablediffusion_assets/AutoencoderKL-base-fp16.param" + sha256: "0254a056dce61b0c27dc9ec1b78b53bcf55315c540f55f051eb841aa992701ba" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-base-fp16.param" + - filename: "stablediffusion_assets/AutoencoderKL-encoder-512-512-fp16.bin" + sha256: "ddcb79a9951b9f91e05e087739ed69da2c1c4ae30ba4168cce350b49d617c9fa" + uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-encoder-512-512-fp16.bin" + - filename: "stablediffusion_assets/AutoencoderKL-fp16.bin" + sha256: "f02e71f80e70252734724bbfaed5c4ddd3a8ed7e61bb2175ff5f53099f0e35dd" + uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-fp16.bin" + - filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.bin" + sha256: "1c9a12f4e1dd1b295a388045f7f28a2352a4d70c3dc96a542189a3dd7051fdd6" + uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/FrozenCLIPEmbedder-fp16.bin" + - filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.param" + sha256: "471afbe678dd1fd3fe764ef9c6eccaccb0a7d7e601f27b462aa926b20eb368c9" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/FrozenCLIPEmbedder-fp16.param" + - filename: "stablediffusion_assets/log_sigmas.bin" + sha256: "a2089f8aa4c61f9c200feaec541ab3f5c94233b28deb6d5e8bcd974fa79b68ac" + uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/raw/main/x86/linux/assets/log_sigmas.bin" + - filename: "stablediffusion_assets/UNetModel-256-256-MHA-fp16-opt.param" + sha256: "a58c380229f09491776df837b7aa7adffc0a87821dc4708b34535da2e36e3da1" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-256-256-MHA-fp16-opt.param" + - filename: "stablediffusion_assets/UNetModel-512-512-MHA-fp16-opt.param" + sha256: "f12034067062827bd7f43d1d21888d1f03905401acf6c6eea22be23c259636fa" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-512-512-MHA-fp16-opt.param" + - filename: "stablediffusion_assets/UNetModel-base-MHA-fp16.param" + sha256: "696f6975de49f4325b53ce32aff81861a6d6c07cd9ce3f0aae2cc405350af38d" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-base-MHA-fp16.param" + - filename: "stablediffusion_assets/UNetModel-MHA-fp16.bin" + sha256: "d618918d011bfc1f644c0f2a33bf84931bd53b28a98492b0a8ed6f3a818852c3" + uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/UNetModel-MHA-fp16.bin" + - filename: "stablediffusion_assets/vocab.txt" + sha256: "e30e57b6f1e47616982ef898d8922be24e535b4fa3d0110477b3a6f02ebbae7d" + uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/vocab.txt" diff --git a/gallery/tinydream.yaml b/gallery/tinydream.yaml index 6e39414c..e4a79ad7 100644 --- a/gallery/tinydream.yaml +++ b/gallery/tinydream.yaml @@ -1,3 +1,4 @@ +--- name: "tinydream" config_file: | @@ -33,4 +34,4 @@ files: uri: "https://github.com/M0Rf30/tiny-dream-bins/releases/download/1.0/UNetModel-fp16.param" - filename: "tinydream_assets/vocab.txt" sha256: "e30e57b6f1e47616982ef898d8922be24e535b4fa3d0110477b3a6f02ebbae7d" - uri: "https://github.com/M0Rf30/tiny-dream-bins/releases/download/1.0/vocab.txt" \ No newline at end of file + uri: "https://github.com/M0Rf30/tiny-dream-bins/releases/download/1.0/vocab.txt" diff --git a/gallery/vicuna-chat.yaml b/gallery/vicuna-chat.yaml index 9669cce0..05600e66 100644 --- a/gallery/vicuna-chat.yaml +++ b/gallery/vicuna-chat.yaml @@ -1,3 +1,4 @@ +--- name: "vicuna-chat" description: | @@ -18,4 +19,4 @@ config_file: | Complete the following sentence: {{.Input}} chat: | {{.Input}} - ASSISTANT: \ No newline at end of file + ASSISTANT: diff --git a/gallery/virtual.yaml b/gallery/virtual.yaml index 054c3257..22e3e546 100644 --- a/gallery/virtual.yaml +++ b/gallery/virtual.yaml @@ -1,6 +1,7 @@ +--- name: "virtual" description: | A Base model definition -license: "N/A" \ No newline at end of file +license: "N/A" diff --git a/gallery/whisper-base.yaml b/gallery/whisper-base.yaml index f654a37c..2dc24d6e 100644 --- a/gallery/whisper-base.yaml +++ b/gallery/whisper-base.yaml @@ -1,12 +1,12 @@ +--- name: "whisper-base" - config_file: | backend: whisper parameters: model: ggml-whisper-base.bin files: -- filename: "ggml-whisper-base.bin" - sha256: "60ed5bc3dd14eea856493d334349b405782ddcaf0028d4b5df4088345fba2efe" - uri: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" \ No newline at end of file + - filename: "ggml-whisper-base.bin" + sha256: "60ed5bc3dd14eea856493d334349b405782ddcaf0028d4b5df4088345fba2efe" + uri: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin"