commit 31264c8e8092646354fcd6b11ce4eab021685868 Author: ModelHub XC Date: Sun Apr 12 12:43:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..354b4fb --- /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-SFT-Capybara.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-SFT-Capybara.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-SFT-Capybara.IQ4_XS.gguf b/Qwen3-0.6B-SFT-Capybara.IQ4_XS.gguf new file mode 100644 index 0000000..5204b21 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37cf1d5e98844b194af31854b5d77c026afc94e6c19965e2efd926d3eafd6617 +size 369278400 diff --git a/Qwen3-0.6B-SFT-Capybara.Q2_K.gguf b/Qwen3-0.6B-SFT-Capybara.Q2_K.gguf new file mode 100644 index 0000000..449869c --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86593262c7e7e62248114237b10cf58f31b30018a79f23f60bb135a45d8a04fe +size 296238528 diff --git a/Qwen3-0.6B-SFT-Capybara.Q3_K_L.gguf b/Qwen3-0.6B-SFT-Capybara.Q3_K_L.gguf new file mode 100644 index 0000000..84b64b2 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d50ab16a3bd1ab65d99c739946e0d95861442686d75d2aee38bdfa47c28143b +size 368491968 diff --git a/Qwen3-0.6B-SFT-Capybara.Q3_K_M.gguf b/Qwen3-0.6B-SFT-Capybara.Q3_K_M.gguf new file mode 100644 index 0000000..dd0e5bd --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ab5cf0f99e2343eb928c3891deb12939b0ff506ae2b1a9ca9c954b41c88982 +size 347127232 diff --git a/Qwen3-0.6B-SFT-Capybara.Q3_K_S.gguf b/Qwen3-0.6B-SFT-Capybara.Q3_K_S.gguf new file mode 100644 index 0000000..7f02d87 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8afbf6f1a4b167b422e3caa7589ee5eb94fd08b4e550caffeb57a646be70ec4 +size 323075520 diff --git a/Qwen3-0.6B-SFT-Capybara.Q4_K_M.gguf b/Qwen3-0.6B-SFT-Capybara.Q4_K_M.gguf new file mode 100644 index 0000000..1bdf277 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:538a599c208b0bf93f082fd2c696d3d33dd30acb22a5073023f4aaccea676f4d +size 396705216 diff --git a/Qwen3-0.6B-SFT-Capybara.Q4_K_S.gguf b/Qwen3-0.6B-SFT-Capybara.Q4_K_S.gguf new file mode 100644 index 0000000..a99e51a --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384a36d46057d0d5564f26db0f42d9966b185b4147cbd7fbec99ae3d7496b06b +size 383270336 diff --git a/Qwen3-0.6B-SFT-Capybara.Q5_K_M.gguf b/Qwen3-0.6B-SFT-Capybara.Q5_K_M.gguf new file mode 100644 index 0000000..492b3b1 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d673c34aec11b28dea4b7c73dfcc3da5a0ebe30b1dfa2b47eea911f583cc9c0c +size 444415424 diff --git a/Qwen3-0.6B-SFT-Capybara.Q5_K_S.gguf b/Qwen3-0.6B-SFT-Capybara.Q5_K_S.gguf new file mode 100644 index 0000000..8b72db5 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd623183cd176398fbfc1ae46540e5e352c13a21077017b45037ef80e741f98 +size 436616640 diff --git a/Qwen3-0.6B-SFT-Capybara.Q6_K.gguf b/Qwen3-0.6B-SFT-Capybara.Q6_K.gguf new file mode 100644 index 0000000..0874083 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b357e2c468feb9bb87205c5b7fe74fdf355e34addb8c29eb82d3f23d2063c2 +size 495107520 diff --git a/Qwen3-0.6B-SFT-Capybara.Q8_0.gguf b/Qwen3-0.6B-SFT-Capybara.Q8_0.gguf new file mode 100644 index 0000000..c4462e3 --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e870ffc12e379c1d6e6721de9abefdce5a81fd1e201d314f2ff6ff687a01ad7 +size 639447488 diff --git a/Qwen3-0.6B-SFT-Capybara.f16.gguf b/Qwen3-0.6B-SFT-Capybara.f16.gguf new file mode 100644 index 0000000..9b2007b --- /dev/null +++ b/Qwen3-0.6B-SFT-Capybara.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0055b86c89b3702ee02b1911d1cfbc1846efa403d0eed76e774956b2e4a7a303 +size 1198182848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8df2c3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: sachin6624/Qwen3-0.6B-SFT-Capybara +language: +- en +library_name: transformers +model_name: trainer_output +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/sachin6624/Qwen3-0.6B-SFT-Capybara + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-SFT-Capybara-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-SFT-Capybara-GGUF/resolve/main/Qwen3-0.6B-SFT-Capybara.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. + +