commit 1a1fa260f6a065300ef8766003347a7781752b41 Author: ModelHub XC Date: Mon Jul 20 04:33:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53e1fb3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-Full-Finetuning-No-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-No-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.IQ4_XS.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..693939a --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf402842b31092db4030ed25b4705ef59a3b931ef95a1d4baf685666cf17986 +size 369279072 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q2_K.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q2_K.gguf new file mode 100644 index 0000000..c8b9560 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf40464a4836208f70b918e9e3053ea03c4fe4f5e30571b4b6ce1e5586c231e +size 296239200 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_L.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..a4d8325 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbe8fdfce04dcc2be6e20b4438f406a52ae52885dc06747cf45759cadb4407d +size 368492640 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..5d89ab4 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9ea853f74f037e4d89b1dc4d5986fccac97f280cb6620bb486826ea7b9f7af +size 347127904 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..573a997 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe58322508ae50c81ce9a0623148c79df7d52abbf17b68b7081fb4ec3d3e50c +size 323076192 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..5dd88f3 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccb8140b4db27b954cb885f2e11ea51cc02ab4fd3f3126511c9884a9e947472 +size 396705888 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..e2ce50b --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0b2533125a2db1c340dbe3a9e9238da0d61598d7d3b534716ba0d20ab2de81 +size 383271008 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..373c194 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f756c41a00daa401a931a634dd27f2bd393cc9d70edede722e4dc9b206980a41 +size 444416096 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..744286b --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619be5796b7e0dc8be8b74a2cb4d41200f734723ad1b6f038b29ef27b2e1c6c6 +size 436617312 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q6_K.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q6_K.gguf new file mode 100644 index 0000000..434a9c0 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50df71eea98dc1d3eae0df8626299f264fb6750410105912b9cb90dcc132df61 +size 495108192 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q8_0.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q8_0.gguf new file mode 100644 index 0000000..f5814fe --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48850a939a117871e6a0b1f8ac2f3a3383a3796c5dd19a9ff6518e80cce9607c +size 639448160 diff --git a/Qwen3-0.6B-Full-Finetuning-No-Thinking.f16.gguf b/Qwen3-0.6B-Full-Finetuning-No-Thinking.f16.gguf new file mode 100644 index 0000000..d197dd7 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-No-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf55e1aefbf055789642d11f185f46ed00892128b5f9c5898d5f3602178860f +size 1198183520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6fb97db --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: theneuralmaze/Qwen3-0.6B-Full-Finetuning-No-Thinking +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theneuralmaze/Qwen3-0.6B-Full-Finetuning-No-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-No-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-No-Thinking.f16.gguf) | f16 | 1.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +