From 4e2a5719e744909c83b5602728cee9c6f2d101d8 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 12 Nov 2024 12:03:14 +0100 Subject: [PATCH] models(gallery): add qwen2.5-coder-32b-instruct (#4127) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 87 +++++++++++++++++++++++++++------------------- 1 file changed, 51 insertions(+), 36 deletions(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index 50da10d1..bf49a3bc 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,55 @@ --- +- &qwen25coder + name: "qwen2.5-coder-14b" + url: "github:mudler/LocalAI/gallery/chatml.yaml@master" + license: apache-2.0 + tags: + - llm + - gguf + - gpu + - qwen + - qwen2.5 + - cpu + urls: + - https://huggingface.co/Qwen/Qwen2.5-Coder-14B + - https://huggingface.co/mradermacher/Qwen2.5-Coder-14B-GGUF + description: | + Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: + + Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. + A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. + Long-context Support up to 128K tokens. + overrides: + parameters: + model: Qwen2.5-Coder-14B.Q4_K_M.gguf + files: + - filename: Qwen2.5-Coder-14B.Q4_K_M.gguf + sha256: 94f277a9ac7caf117140b2fff4e1ccf4bc9f35395b0112f0d0d7c82c6f8d860e + uri: huggingface://mradermacher/Qwen2.5-Coder-14B-GGUF/Qwen2.5-Coder-14B.Q4_K_M.gguf +- !!merge <<: *qwen25coder + name: "qwen2.5-coder-3b-instruct" + urls: + - https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct + - https://huggingface.co/bartowski/Qwen2.5-Coder-3B-Instruct-GGUF + overrides: + parameters: + model: Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf + files: + - filename: Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf + sha256: 3da3afe6cf5c674ac195803ea0dd6fee7e1c228c2105c1ce8c66890d1d4ab460 + uri: huggingface://bartowski/Qwen2.5-Coder-3B-Instruct-GGUF/Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf +- !!merge <<: *qwen25coder + name: "qwen2.5-coder-32b-instruct" + urls: + - https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct + - https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-GGUF + overrides: + parameters: + model: Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf + files: + - filename: Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf + sha256: 8e2fd78ff55e7cdf577fda257bac2776feb7d73d922613caf35468073807e815 + uri: huggingface://bartowski/Qwen2.5-Coder-32B-Instruct-GGUF/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf - &opencoder name: "opencoder-8b-base" icon: https://github.com/OpenCoder-llm/opencoder-llm.github.io/blob/main/static/images/opencoder_icon.jpg?raw=true @@ -1118,42 +1169,6 @@ - filename: calme-3.1-qwenloi-3b.Q5_K_M.gguf sha256: 8962a8d1704979039063b5c69fafdb38b545c26143419ec4c574f37f2d6dd7b2 uri: huggingface://MaziyarPanahi/calme-3.1-qwenloi-3b-GGUF/calme-3.1-qwenloi-3b.Q5_K_M.gguf -- !!merge <<: *qwen25 - name: "qwen2.5-coder-14b" - urls: - - https://huggingface.co/Qwen/Qwen2.5-Coder-14B - - https://huggingface.co/mradermacher/Qwen2.5-Coder-14B-GGUF - description: | - Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - - Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. - A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. - Long-context Support up to 128K tokens. - overrides: - parameters: - model: Qwen2.5-Coder-14B.Q4_K_M.gguf - files: - - filename: Qwen2.5-Coder-14B.Q4_K_M.gguf - sha256: 94f277a9ac7caf117140b2fff4e1ccf4bc9f35395b0112f0d0d7c82c6f8d860e - uri: huggingface://mradermacher/Qwen2.5-Coder-14B-GGUF/Qwen2.5-Coder-14B.Q4_K_M.gguf -- !!merge <<: *qwen25 - name: "qwen2.5-coder-3b-instruct" - urls: - - https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct - - https://huggingface.co/bartowski/Qwen2.5-Coder-3B-Instruct-GGUF - description: | - Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - - Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o. - A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. - Long-context Support up to 128K tokens. - overrides: - parameters: - model: Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf - files: - - filename: Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf - sha256: 3da3afe6cf5c674ac195803ea0dd6fee7e1c228c2105c1ce8c66890d1d4ab460 - uri: huggingface://bartowski/Qwen2.5-Coder-3B-Instruct-GGUF/Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf - &archfunct license: apache-2.0 tags: