From a73eb5df15857fd47b122341ad3905f8a64d63a5 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 2 Sep 2026 03:58:17 +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: igarin/Qwen2.5-Coder-7B-20260302-GGUF Source: Original Platform --- .gitattributes | 43 +++++++++++++++++++ Modelfile | 54 ++++++++++++++++++++++++ README.md | 47 +++++++++++++++++++++ config.json | 60 +++++++++++++++++++++++++++ qwen2.5-coder-7b-instruct.F16.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q2_K.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q3_K_M.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q4_1.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q4_K_M.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q5_K_M.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q6_K.gguf | 3 ++ qwen2.5-coder-7b-instruct.Q8_0.gguf | 3 ++ 12 files changed, 228 insertions(+) create mode 100644 .gitattributes create mode 100644 Modelfile create mode 100644 README.md create mode 100644 config.json create mode 100644 qwen2.5-coder-7b-instruct.F16.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q2_K.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q3_K_M.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q4_1.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q4_K_M.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q5_K_M.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q6_K.gguf create mode 100644 qwen2.5-coder-7b-instruct.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..218d552 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,43 @@ +*.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.F16.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-7b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..c919a17 --- /dev/null +++ b/Modelfile @@ -0,0 +1,54 @@ + +FROM qwen2.5-coder-7b-instruct.Q4_K_M.gguf +TEMPLATE """{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> +{{- else if .Messages }} +{{- if or .System .Tools }}<|im_start|>system +{{- if .System }} +{{ .System }} +{{- end }} +{{- if .Tools }} + +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within : + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within with NO other text. Do not include any backticks or ```json. + +{"name": , "arguments": } + +{{- end }}<|im_end|> +{{ end }} +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 -}} +{{- 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 }}{{ if not $last }}<|im_end|> +{{ end }} +{{- else if eq .Role "tool" }}<|im_start|>user + +{{ .Content }} +<|im_end|> +{{ end }} +{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant +{{ end }} +{{- end }} +{{- else }} +{{- if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""" +SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant.""" \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..167af0f --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- swift +- python +- code +- gguf +license: cc-by-nc-4.0 +language: +- en +- ja +datasets: +- igarin/swift-python-textbook-20260302 +--- + + # Uploaded finetuned model + +- **Developed by:** igarin +- **License:** cc-by-nc-4.0 +- **Finetuned from model :** unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit + +# Qwen2.5-Coder-7B-20260302-GGUF : GGUF + +This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth). + +**Example usage**: +- For text only LLMs: `./llama.cpp/llama-cli -hf igarin/Qwen2.5-Coder-7B-20260302-GGUF --jinja` +- For multimodal models: `./llama.cpp/llama-mtmd-cli -hf igarin/Qwen2.5-Coder-7B-20260302-GGUF --jinja` + +## Available Model files: +- `qwen2.5-coder-7b-instruct.F16.gguf` +- `qwen2.5-coder-7b-instruct.Q2_K.gguf` +- `qwen2.5-coder-7b-instruct.Q3_K_M.gguf` +- `qwen2.5-coder-7b-instruct.Q4_1.gguf` +- `qwen2.5-coder-7b-instruct.Q4_K_M.gguf` +- `qwen2.5-coder-7b-instruct.Q5_K_M.gguf` +- `qwen2.5-coder-7b-instruct.Q6_K.gguf` +- `qwen2.5-coder-7b-instruct.Q8_0.gguf` + +## Ollama +An Ollama Modelfile is included for easy deployment. +This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) +[](https://github.com/unslothai/unsloth) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..ff3a660 --- /dev/null +++ b/config.json @@ -0,0 +1,60 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "torch_dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "unsloth_version": "2026.2.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/qwen2.5-coder-7b-instruct.F16.gguf b/qwen2.5-coder-7b-instruct.F16.gguf new file mode 100644 index 0000000..14f84bc --- /dev/null +++ b/qwen2.5-coder-7b-instruct.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3478e1185586aa96e098ffeffaf295eb7d17629e2a3acb299332c42a0cdec2 +size 15237853184 diff --git a/qwen2.5-coder-7b-instruct.Q2_K.gguf b/qwen2.5-coder-7b-instruct.Q2_K.gguf new file mode 100644 index 0000000..d79bb97 --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f762aeb0cf587c1ebbc33225c9cdc0990c178892a4627263cee8393b4f360b5a +size 3015940096 diff --git a/qwen2.5-coder-7b-instruct.Q3_K_M.gguf b/qwen2.5-coder-7b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b298f1d --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3c93711b84924e4ef73ff7957883b22eb1f8b96f43cf4b4971d8c9391dd5a0 +size 3808391168 diff --git a/qwen2.5-coder-7b-instruct.Q4_1.gguf b/qwen2.5-coder-7b-instruct.Q4_1.gguf new file mode 100644 index 0000000..3edffb9 --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be40748bccaa6a9ee948d065a268cad6920e6f0f88171f295cdd85491a0bd290 +size 4873283584 diff --git a/qwen2.5-coder-7b-instruct.Q4_K_M.gguf b/qwen2.5-coder-7b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f53eba5 --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ba4d5e1155c400dee7ad6eeda16c47da35568bfb3fe85900c7e634cf071bfa +size 4683073536 diff --git a/qwen2.5-coder-7b-instruct.Q5_K_M.gguf b/qwen2.5-coder-7b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..0c8d7c6 --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2a6da30a43fd616fb0e2e13a25461dd50fa7a60c96820667e66ffe5b5a05f1 +size 5444831232 diff --git a/qwen2.5-coder-7b-instruct.Q6_K.gguf b/qwen2.5-coder-7b-instruct.Q6_K.gguf new file mode 100644 index 0000000..57026fc --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c473a9788f81bb7900129484cfedef0609ce2e72ac9b548726cded7abde933af +size 6254198784 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..720510b --- /dev/null +++ b/qwen2.5-coder-7b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5961a189b1ecddddbf24fcd19c2b5111c62ff9207662f77816fb164fd91f28a2 +size 8098525184