commit fb406dc32399258eb7c7830a41e88e93400ea7de Author: ModelHub XC Date: Thu Jun 25 04:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..93cc8b0 --- /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 +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.IQ4_XS.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..bdc94b6 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11dbdf7023dec519f9a3eec6b947ce1daa3f2d5061efea6507bd056b52716eef +size 1840907520 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q2_K.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q2_K.gguf new file mode 100644 index 0000000..fca08b6 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21475e2cd9caae8393f2752e5a88aa46d5e3af426e45086090115764138ea95e +size 1363936512 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_L.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c1f7255 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a6dfabdc50e7302fbae0d4bd57fbbc34ab80e8ebd646cd3394329d7f497d2e +size 1815348480 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..2b553de --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374f2e44fbd81afb7938e1bdae12d129aceedd4124c2b7ee458a42ec02cbb2a9 +size 1687160064 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8ea0a03 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f9869bf74c8d73e74b71a57e7852b4e098c8071c484a160eb752f1acbdfd3d +size 1542849792 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..23ec821 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba0d66c1aca8c04cbea4d4c6d904410b5a19bbd733b2e3ce151a7c81dc74532 +size 2019378432 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..925b2a9 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2b136f1b0225386cd9c01c5c943f145e17240ecfb01e50f126eae94622edd7 +size 1928201472 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bdcdec3 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf59284f39661454554c8c30cf28f543111f9d1e518e578a5a7bbc1e0b7ed43 +size 2322154752 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8cc4671 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e4700b1d5f02eb52c42cc0d9168b117b2299c42628872bb61ee090891bb6fa +size 2269512960 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q6_K.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q6_K.gguf new file mode 100644 index 0000000..398f243 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c66d4f83065f22ed4a1642503e3351a0ccdb1d81af2d9aa8b5c15bd7dd98740 +size 2643854592 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q8_0.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a6fd0bb --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cf01fb14d8fbb1df16fbb7063adb27dff3faefee7daaaee4fb1e876f1bcc9b +size 3421900032 diff --git a/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.f16.gguf b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.f16.gguf new file mode 100644 index 0000000..5d36362 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bd0a43d23c7d953284144940af9660523d29c208040e37ac896780017d3166 +size 6433688832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1348788 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: hereticness/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hereticness/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-i1-GGUF +## 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/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Reasoning-Instruct.f16.gguf) | f16 | 6.5 | 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. + +