From 2557921219a51d979a8fc911a49a2f6abc148a26 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 21 Apr 2026 23:54:57 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF Source: Original Platform --- .gitattributes | 36 +++++++ README.md | 158 ++++++++++++++++++++++++++++ qwen2.5-coder-7b-instruct-q8_0.gguf | 3 + 3 files changed, 197 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 qwen2.5-coder-7b-instruct-q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1286c81 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b1d545 --- /dev/null +++ b/README.md @@ -0,0 +1,158 @@ +--- +base_model: Qwen/Qwen2.5-Coder-7B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE +pipeline_tag: text-generation +tags: +- code +- codeqwen +- chat +- qwen +- qwen-coder +- llama-cpp +- gguf-my-repo +--- + +# smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF +This model was converted to GGUF format from [`Qwen/Qwen2.5-Coder-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. +Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) for more details on the model. + + +## Ollama Modelfile (draft/beta!) + +``` + +# ollama create qwen2.5-coder-7b-instruct:q8_0 -f modelfiles/Modelfile-qwen2.5-coder + +FROM ../qwen2.5-coder-7b-instruct-q8_0.gguf + +# This is Sam's hacked up template 2024-09-19 +TEMPLATE """ +{{- $fim_prefix := .FIMPrefix -}} +{{- $fim_suffix := .FIMSuffix -}} +{{- $repo_name := .RepoName -}} +{{- $files := .Files -}} +{{- $has_tools := gt (len .Tools) 0 -}} +{{- if $fim_prefix -}} +<|fim_prefix|>{{ $fim_prefix }}<|fim_suffix|>{{ $fim_suffix }}<|fim_middle|> +{{- else if $repo_name -}} +<|repo_name|>{{ $repo_name }} +{{- range $files }} +<|file_sep|>{{ .Path }} +{{ .Content }} +{{- end }} +{{- else -}} +{{- if or .System $has_tools -}} +<|im_start|>system +{{- if .System }} +{{ .System }} +{{- end }} +{{- if $has_tools }} + +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within XML tags: + +{"name": , "arguments": } + +{{- end }} +<|im_end|> +{{- end }} +{{- if .Messages }} +{{- range $i, $message := .Messages }} +{{- if eq .Role "user" }}<|im_start|>user +{{ .Content }}<|im_end|> +{{- else if eq .Role "assistant" }}<|im_start|>assistant +{{- if .Content }}{{ .Content }} +{{- else if .ToolCalls }} +{{- range .ToolCalls }} +{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} +{{- end }} + +{{- end }}<|im_end|> +{{- else if eq .Role "tool" }}<|im_start|>user + +{{ .Content }} +<|im_end|> +{{- end }} +{{- end }} +{{- else if .Prompt -}} +<|im_start|>user +{{ .Prompt }}<|im_end|> +{{- end -}} +<|im_start|>assistant +{{ .Response }} +{{- end -}} +""" + +PARAMETER stop "<|im_start|>" +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|fim_prefix|>" +PARAMETER stop "<|fim_suffix|>" +PARAMETER stop "<|fim_middle|>" +PARAMETER stop "<|repo_name|>" +PARAMETER stop "<|file_sep|>" + +### Tuning ## +PARAMETER num_ctx 16384 +PARAMETER temperature 0.3 +PARAMETER top_p 0.8 + +# PARAMETER num_batch 1024 +# PARAMETER num_keep 512 +# PARAMETER presence_penalty 0.2 +# PARAMETER frequency_penalty 0.2 +# PARAMETER repeat_last_n 50 +``` + +## Use with llama.cpp +Install llama.cpp through brew (works on Mac and Linux) + +```bash +brew install llama.cpp + +``` +Invoke the llama.cpp server or the CLI. + +### CLI: +```bash +llama-cli --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is" +``` + +### Server: +```bash +llama-server --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -c 2048 +``` + +Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. + +Step 1: Clone llama.cpp from GitHub. +``` +git clone https://github.com/ggerganov/llama.cpp +``` + +Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). +``` +cd llama.cpp && LLAMA_CURL=1 make +``` + +Step 3: Run inference through the main binary. +``` +./llama-cli --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is" +``` +or +``` +./llama-server --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -c 2048 +``` diff --git a/qwen2.5-coder-7b-instruct-q8_0.gguf b/qwen2.5-coder-7b-instruct-q8_0.gguf new file mode 100644 index 0000000..8523a62 --- /dev/null +++ b/qwen2.5-coder-7b-instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc646852b6cf37ca45fbf5232f0ccf5ad9cea1d30348cc373fdf21fa04cd5e1 +size 8098525696