From cd878aa65d37360978ced488430b977ba4b5fd6c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 17 Sep 2026 09:42:16 +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: Losa10/Qwen3-0.6b-test-kimi-GGUF Source: Original Platform --- .gitattributes | 40 +++++++++++++++++++++++++++ Modelfile | 59 ++++++++++++++++++++++++++++++++++++++++ README.md | 24 +++++++++++++++++ config.json | 61 ++++++++++++++++++++++++++++++++++++++++++ qwen3-0.6b.Q4_0.gguf | 3 +++ qwen3-0.6b.Q4_K_M.gguf | 3 +++ qwen3-0.6b.Q5_0.gguf | 3 +++ qwen3-0.6b.Q5_K_M.gguf | 3 +++ qwen3-0.6b.Q8_0.gguf | 3 +++ 9 files changed, 199 insertions(+) create mode 100644 .gitattributes create mode 100644 Modelfile create mode 100644 README.md create mode 100644 config.json create mode 100644 qwen3-0.6b.Q4_0.gguf create mode 100644 qwen3-0.6b.Q4_K_M.gguf create mode 100644 qwen3-0.6b.Q5_0.gguf create mode 100644 qwen3-0.6b.Q5_K_M.gguf create mode 100644 qwen3-0.6b.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..efcec37 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +qwen3-0.6b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-0.6b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-0.6b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-0.6b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-0.6b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..122a0cd --- /dev/null +++ b/Modelfile @@ -0,0 +1,59 @@ + +FROM qwen3-0.6b.Q4_0.gguf +TEMPLATE """{{- 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 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 }} +{{- 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 }}""" +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|im_start|>" +PARAMETER temperature 0.6 +PARAMETER min_p 0.0 +PARAMETER top_k 20 +PARAMETER top_p 0.95 +PARAMETER repeat_penalty 1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c8b071 --- /dev/null +++ b/README.md @@ -0,0 +1,24 @@ +--- +tags: +- gguf +- llama.cpp +- unsloth +base_model: +- Losa10/Qwen3-0.6b-test-kimi +--- + +# Qwen3-0.6b-test-kimi-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-cli -hf Losa10/Qwen3-0.6b-test-kimi-GGUF --jinja` +- For multimodal models: `llama-mtmd-cli -hf Losa10/Qwen3-0.6b-test-kimi-GGUF --jinja` + +## Available Model files: +- `qwen3-0.6b.Q4_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..5b4dd70 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "torch_dtype": "float16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151654, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "unsloth_version": "2026.3.17", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/qwen3-0.6b.Q4_0.gguf b/qwen3-0.6b.Q4_0.gguf new file mode 100644 index 0000000..d3e2dcb --- /dev/null +++ b/qwen3-0.6b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5acf142b30bd98c6dfb64a1ec3a232c7f97bf100392f913eb2b3c373bf11fee2 +size 381566464 diff --git a/qwen3-0.6b.Q4_K_M.gguf b/qwen3-0.6b.Q4_K_M.gguf new file mode 100644 index 0000000..73379ee --- /dev/null +++ b/qwen3-0.6b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049441f92ecde5258e12d7a7b6ef0b3ad378cdf033acbac10fdc32aa0d908c8a +size 396705280 diff --git a/qwen3-0.6b.Q5_0.gguf b/qwen3-0.6b.Q5_0.gguf new file mode 100644 index 0000000..b45f35d --- /dev/null +++ b/qwen3-0.6b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2314738f4812288b187120167aa70af567d523ac7146dcf308f1fc3fb9e448eb +size 436616704 diff --git a/qwen3-0.6b.Q5_K_M.gguf b/qwen3-0.6b.Q5_K_M.gguf new file mode 100644 index 0000000..7ca8898 --- /dev/null +++ b/qwen3-0.6b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f500be5bf5ed0123ed2c63747858a340a28336a92c49acf24da5cc3b33bac55 +size 444415488 diff --git a/qwen3-0.6b.Q8_0.gguf b/qwen3-0.6b.Q8_0.gguf new file mode 100644 index 0000000..f9aa644 --- /dev/null +++ b/qwen3-0.6b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9050800ff08cc11a293bcbb97ac15a262b82eb29e9e581e7d4dafc3f2a21150 +size 639447552