commit 7a8648cdcc670e00ef5fbd9f6e84f794b34113a2 Author: ModelHub XC Date: Fri Aug 7 05:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f86e9c8 --- /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 +Qwen2.5-HA-0.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-HA-0.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-HA-0.5B-Instruct.IQ4_XS.gguf b/Qwen2.5-HA-0.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..f9bce34 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16200e24d57cc024992eb91d53770fdfd18736fd6c6f81ee8c782f328cd376f3 +size 351445408 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q2_K.gguf b/Qwen2.5-HA-0.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..e369281 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35c5816071c430aad1f7d0853e95c67825a0319552d44a426a539b573b17a33 +size 338607520 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q3_K_L.gguf b/Qwen2.5-HA-0.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..8d9a379 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cab0963787dba0102b70fb86297118f486eb683ff5c4052615da99c785aff16 +size 369358240 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q3_K_M.gguf b/Qwen2.5-HA-0.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e5e5fa2 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5ea76d68cbe4e59d4b49a18c8ef6b68d5f609d1ce2a3b6bf952008a8c8f890 +size 355466656 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q3_K_S.gguf b/Qwen2.5-HA-0.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..63a489f --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91525d1abdef9fcc4f071483c7a7a4a4144ce2cdf1aaeaa1686412042ffe282b +size 338263456 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q4_K_M.gguf b/Qwen2.5-HA-0.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..3717aa4 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe91ea2f566734627c21f0af13e669f77b94018061d4d8aa2541e54dc9d9dcb +size 397808032 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q4_K_S.gguf b/Qwen2.5-HA-0.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..981cf1b --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac91275f86d27125889db07a655bc64b9e7a1f3f5f818b9fcbca7e03b0dd022f +size 385471904 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q5_K_M.gguf b/Qwen2.5-HA-0.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..f365c49 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb01dfc0689b927c8d3ac8e2aa3e779e8687b3cb1fa790c4268a4db5e786160 +size 420086176 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q5_K_S.gguf b/Qwen2.5-HA-0.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d189a88 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d97db577b817c3eb48478167500f8c37bdc0fdae50b6ae3431085f592204643b +size 412710304 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q6_K.gguf b/Qwen2.5-HA-0.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..281b190 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54db200176e511ce85f0933b689987ee27545ec422b7ebdbae4e30b8fb67c344 +size 505736608 diff --git a/Qwen2.5-HA-0.5B-Instruct.Q8_0.gguf b/Qwen2.5-HA-0.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..3db14b0 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9041f9b372a4802736531ad1494131e20793855b5ed2047af5abd68f00b48c +size 531068320 diff --git a/Qwen2.5-HA-0.5B-Instruct.f16.gguf b/Qwen2.5-HA-0.5B-Instruct.f16.gguf new file mode 100644 index 0000000..d1bd6e3 --- /dev/null +++ b/Qwen2.5-HA-0.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25e43d90f665df5330b1988e635d02d63f5b3a73ffc517675d544fdf1ed371c +size 994156960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..550b4cb --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: M5Stack/Qwen2.5-HA-0.5B-Instruct +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/M5Stack/Qwen2.5-HA-0.5B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-HA-0.5B-Instruct-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/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-HA-0.5B-Instruct-GGUF/resolve/main/Qwen2.5-HA-0.5B-Instruct.f16.gguf) | f16 | 1.1 | 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. + +