commit 674b011185d3f21b89ecb4f06d407c869c21ee02 Author: ModelHub XC Date: Fri Jul 10 18:58:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniChat-2-3B-pruned2.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e95224c --- /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 +MiniChat-2-3B-pruned2.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniChat-2-3B-pruned2.4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniChat-2-3B-pruned2.4.IQ4_XS.gguf b/MiniChat-2-3B-pruned2.4.IQ4_XS.gguf new file mode 100644 index 0000000..a84cb25 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85bf15ca65efe718ff106676d9e9c0c2318e602daf266fdc5b2295daa76aeff7 +size 1661740224 diff --git a/MiniChat-2-3B-pruned2.4.Q2_K.gguf b/MiniChat-2-3B-pruned2.4.Q2_K.gguf new file mode 100644 index 0000000..567453a --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e84a3f887d861fdb42fc23c8aadef9148fb3673691ce1dda091cd7da5f8c65 +size 1174505664 diff --git a/MiniChat-2-3B-pruned2.4.Q3_K_L.gguf b/MiniChat-2-3B-pruned2.4.Q3_K_L.gguf new file mode 100644 index 0000000..f24c478 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a7b83b0556739a17072ec477d7c678bf4fd5ff056b58152619efad3d2aed40 +size 1631049408 diff --git a/MiniChat-2-3B-pruned2.4.Q3_K_M.gguf b/MiniChat-2-3B-pruned2.4.Q3_K_M.gguf new file mode 100644 index 0000000..867531d --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617e03e852783b7761103b54a7206ab66301bd2735a28ed28d79de8a13d2c3db +size 1504433856 diff --git a/MiniChat-2-3B-pruned2.4.Q3_K_S.gguf b/MiniChat-2-3B-pruned2.4.Q3_K_S.gguf new file mode 100644 index 0000000..899f001 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4f5dbddefd90e2b7adf101272edd6a22d54efafdf5aa012baff1958a7f712f +size 1358550720 diff --git a/MiniChat-2-3B-pruned2.4.Q4_K_M.gguf b/MiniChat-2-3B-pruned2.4.Q4_K_M.gguf new file mode 100644 index 0000000..07b4e28 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60ed2166c800492e69d22749ab145a5fe5e254365e057f78a1996be667210a1 +size 1846656192 diff --git a/MiniChat-2-3B-pruned2.4.Q4_K_S.gguf b/MiniChat-2-3B-pruned2.4.Q4_K_S.gguf new file mode 100644 index 0000000..a72cc42 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60bd6bab6fdee21a753f05bb0f39a70e1c7ac07bc456d93bb3bb452ccf6d34e +size 1753758912 diff --git a/MiniChat-2-3B-pruned2.4.Q5_K_M.gguf b/MiniChat-2-3B-pruned2.4.Q5_K_M.gguf new file mode 100644 index 0000000..0f978c7 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092116f6e56c6483e104c97f3371d7c2e61e9880abf3624f926d6938309b426c +size 2153389248 diff --git a/MiniChat-2-3B-pruned2.4.Q5_K_S.gguf b/MiniChat-2-3B-pruned2.4.Q5_K_S.gguf new file mode 100644 index 0000000..328675c --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2491e51df24b6c14ded9598c6ab7611edafbf1179cab29227d7394f20cb461 +size 2098240704 diff --git a/MiniChat-2-3B-pruned2.4.Q6_K.gguf b/MiniChat-2-3B-pruned2.4.Q6_K.gguf new file mode 100644 index 0000000..5eb7992 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f7b9904c157397b607cc8e5359922f8c956cd99764b45b9f6e32495c8d604b +size 2479293120 diff --git a/MiniChat-2-3B-pruned2.4.Q8_0.gguf b/MiniChat-2-3B-pruned2.4.Q8_0.gguf new file mode 100644 index 0000000..f85e7b4 --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc22092637753b37281a1f95bac634e4e4b31d46df9647bf09602dfe4e2de6ef +size 3210770112 diff --git a/MiniChat-2-3B-pruned2.4.f16.gguf b/MiniChat-2-3B-pruned2.4.f16.gguf new file mode 100644 index 0000000..fb1fc0b --- /dev/null +++ b/MiniChat-2-3B-pruned2.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31a5da74c6253535ba4d5541204d12e3673b49aaa4e8d71303ac82e9d229550 +size 6042293952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82a4070 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: RedHatAI/MiniChat-2-3B-pruned2.4 +language: +- en +library_name: transformers +model_type: Llama +quantized_by: mradermacher +tags: +- nm-vllm +- sparse +--- +## About + + + + + + +static quants of https://huggingface.co/RedHatAI/MiniChat-2-3B-pruned2.4 + + +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/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.IQ4_XS.gguf) | IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q5_K_S.gguf) | Q5_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.Q8_0.gguf) | Q8_0 | 3.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiniChat-2-3B-pruned2.4-GGUF/resolve/main/MiniChat-2-3B-pruned2.4.f16.gguf) | f16 | 6.1 | 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. + +