commit dd22f492e25a3e0474979c2716e05b3e92231f09 Author: ModelHub XC Date: Tue Aug 4 11:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Capybara-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..10f646d --- /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 +Qwen3-4B-Capybara-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Capybara-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Capybara-SFT.IQ4_XS.gguf b/Qwen3-4B-Capybara-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..53b0c5c --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9f8130c81b79bea2094f97a8263d4f90a353d4c969facec599a19805b5306f +size 2286316608 diff --git a/Qwen3-4B-Capybara-SFT.Q2_K.gguf b/Qwen3-4B-Capybara-SFT.Q2_K.gguf new file mode 100644 index 0000000..0cf3043 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09342cd3f6a8578b83ab52a63a985de1486669bc0f82ab8507f6c139215dfce6 +size 1669499968 diff --git a/Qwen3-4B-Capybara-SFT.Q3_K_L.gguf b/Qwen3-4B-Capybara-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..4bec006 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c787f90d34861571884adf1f0ff19965478d77c11eae1ee413788faace7a00f3 +size 2239786048 diff --git a/Qwen3-4B-Capybara-SFT.Q3_K_M.gguf b/Qwen3-4B-Capybara-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..3d42720 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:667d6b8294dc81e611c694e1c6871f1024e9121914bab589a31f4dfd495bc3a4 +size 2075618368 diff --git a/Qwen3-4B-Capybara-SFT.Q3_K_S.gguf b/Qwen3-4B-Capybara-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..fe63af8 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c808c1bffceea9cd7af5a673e57fda3040b3d48d74e116b0816b52bca72392 +size 1886997568 diff --git a/Qwen3-4B-Capybara-SFT.Q4_K_M.gguf b/Qwen3-4B-Capybara-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..c9a7763 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dec60e86bd3946c75de26f6d68c11cc144e365da36ff3178cbf77ce9fb1d2df +size 2497281088 diff --git a/Qwen3-4B-Capybara-SFT.Q4_K_S.gguf b/Qwen3-4B-Capybara-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..0be3199 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aabd40999f525b5714ed71362a88570ff3fb46525ca476613d187bc9d9d3b42 +size 2383309888 diff --git a/Qwen3-4B-Capybara-SFT.Q5_K_M.gguf b/Qwen3-4B-Capybara-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..73b190a --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41c851c7e2d7d43818e82baad6525543b0065be535ebdc30a12ad3d03217b27 +size 2889514048 diff --git a/Qwen3-4B-Capybara-SFT.Q5_K_S.gguf b/Qwen3-4B-Capybara-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..5da4185 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfcb5334e0f881baacaa6fa778eb996bdd885b5af9b46485f27cf5f72eef415 +size 2823711808 diff --git a/Qwen3-4B-Capybara-SFT.Q6_K.gguf b/Qwen3-4B-Capybara-SFT.Q6_K.gguf new file mode 100644 index 0000000..67693c9 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c56c27fbd1a10d5c177013239b88295728639aa2627a8ab08993c2c05441913 +size 3306261568 diff --git a/Qwen3-4B-Capybara-SFT.Q8_0.gguf b/Qwen3-4B-Capybara-SFT.Q8_0.gguf new file mode 100644 index 0000000..b73af5e --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17909c79b7895896287e11c8475e711f0065f0ff6408379548a29f752dd0a6fc +size 4280405568 diff --git a/Qwen3-4B-Capybara-SFT.f16.gguf b/Qwen3-4B-Capybara-SFT.f16.gguf new file mode 100644 index 0000000..c80a0a1 --- /dev/null +++ b/Qwen3-4B-Capybara-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da9065492e193a0a91aec29b16a7b70a1b8912daf74128114365ea4692cc129a +size 8051285568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9dca5f7 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: lewtun/Qwen3-4B-Capybara-SFT +language: +- en +library_name: transformers +model_name: Qwen3-4B-Capybara-SFT +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +- trackio:https://huggingface.co/spaces/lewtun/qwen3-4b-capybara-static-e6d3fd +- hf_jobs +- trackio +- ml-intern +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lewtun/Qwen3-4B-Capybara-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Capybara-SFT-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/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Capybara-SFT-GGUF/resolve/main/Qwen3-4B-Capybara-SFT.f16.gguf) | f16 | 8.2 | 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. + +