commit d19ec33d7a77c241b410e09f7cc880abc02cf10a Author: ModelHub XC Date: Sat Jul 18 05:23:09 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-Herald-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b20f9ef --- /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 +Qwen3-8B-Herald-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Herald-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-Herald-SFT.IQ4_XS.gguf b/Qwen3-8B-Herald-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..254be04 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e2e8cf666d20bf0e477432e9d6ee25735c86c661df970fac8994ca3b749e95 +size 4593297536 diff --git a/Qwen3-8B-Herald-SFT.Q2_K.gguf b/Qwen3-8B-Herald-SFT.Q2_K.gguf new file mode 100644 index 0000000..68327ac --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7061407fab862be563c2c26308f051f7ab926a66ec6cff4eec49c55c93d2e54a +size 3281733760 diff --git a/Qwen3-8B-Herald-SFT.Q3_K_L.gguf b/Qwen3-8B-Herald-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..3b3e542 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6bc3a0b508ff1a578d53a238217917defc4dc861cbd5ccdf5abefd351c94e6 +size 4431394944 diff --git a/Qwen3-8B-Herald-SFT.Q3_K_M.gguf b/Qwen3-8B-Herald-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..4e7c59c --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06252a238a468ca734fe690f3957cf736443dcf4aee9f138fffd153d909cfba6 +size 4124162176 diff --git a/Qwen3-8B-Herald-SFT.Q3_K_S.gguf b/Qwen3-8B-Herald-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..a7e0cea --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a324b29050d2927611a8b37f373c080535803af4b684da09aaf9d43c74383f5a +size 3769612416 diff --git a/Qwen3-8B-Herald-SFT.Q4_K_M.gguf b/Qwen3-8B-Herald-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..5e7b77d --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b280af3fcc51860b48a2c2a8bcc260ab5a50ee65b4c6981c8875da8a96e2c2 +size 5027784832 diff --git a/Qwen3-8B-Herald-SFT.Q4_K_S.gguf b/Qwen3-8B-Herald-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..755eeff --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7864d9e891f7c5ee6ba06242e2ca74693321355bd230f9d05c42afb937ba5c73 +size 4802013312 diff --git a/Qwen3-8B-Herald-SFT.Q5_K_M.gguf b/Qwen3-8B-Herald-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..fed31bb --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a07d97047dd5d23b3784d7006f764c66a7ba909cb0a18ab9036e8b2b2f9919 +size 5851113600 diff --git a/Qwen3-8B-Herald-SFT.Q5_K_S.gguf b/Qwen3-8B-Herald-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..55c2e69 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87a5a656c56bc118f4f79aef1b27fadd4c10eab6bd703c8ff9a157215540dc4 +size 5720762496 diff --git a/Qwen3-8B-Herald-SFT.Q6_K.gguf b/Qwen3-8B-Herald-SFT.Q6_K.gguf new file mode 100644 index 0000000..52e08b9 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fe043119f323226a0eefa01c3bae44a3504176b097451ec8300f642780a06d +size 6725900416 diff --git a/Qwen3-8B-Herald-SFT.Q8_0.gguf b/Qwen3-8B-Herald-SFT.Q8_0.gguf new file mode 100644 index 0000000..0327067 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4007cbc8c6d966aeedfa014624174aaa2ad535b9a140f63d1164c5d61d2fa9 +size 8709519488 diff --git a/Qwen3-8B-Herald-SFT.f16.gguf b/Qwen3-8B-Herald-SFT.f16.gguf new file mode 100644 index 0000000..c8bde52 --- /dev/null +++ b/Qwen3-8B-Herald-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1639c04333d2403baf446ab889f7740b0978a8cdbc8a41f386d79732027962 +size 16388044928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad0f9ed --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: xiaolesu/Qwen3-8B-Herald-SFT +datasets: +- FrenzyMath/Herald_statements +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- lean4 +- mathlib +- autoformalization +- formal-verification +- math +- peft +- lora +- qlora +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xiaolesu/Qwen3-8B-Herald-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-8B-Herald-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/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Herald-SFT-GGUF/resolve/main/Qwen3-8B-Herald-SFT.f16.gguf) | f16 | 16.5 | 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. + +