commit 5383a5c64ea57de1b45750266dc5eb280414a67a Author: ModelHub XC Date: Thu Jun 11 22:26:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e6035e7 --- /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-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.IQ4_XS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..66959da --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6012ea33cc9ee724cc7403b8173caa0bd3c3b24a26fb87dc9522a62414dcba67 +size 1840907456 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q2_K.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q2_K.gguf new file mode 100644 index 0000000..5723a27 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab40de20f9277a0fb85a1ea756f8e6f1f5a496bb844bb78ecfee843632ea500d +size 1363936448 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_L.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..dfb74bf --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf59994187615ff780d8815ccbbdc1f473634ee29ac865ffbba8ad5177221155 +size 1815348416 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..34f938f --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936216d67919895e882cec3de8422b7e6cac99e20577235f5e0e494be5b65778 +size 1687160000 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..543a57f --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d47d2be14850b00122608c48ecdfbf30b999764bda482da78a38f2f3dd52c1 +size 1542849728 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..74067b2 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d09ceb62ec16cc1cd334c8ad1975cfded24b1b1af0d09301e78c36dbc20542 +size 2019378368 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..65a1901 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da0d1ab85d67725066d87cc1923c2a962c232c095c9cf0b60df03dd652bfde7 +size 1928201408 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..3b2fde8 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e212b5ba55ea1c7056489188e624a76b8c48fa00172ba1baaea814ad576cef95 +size 2322154688 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..5245bd3 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2384536e6b2ac96384f05d4d2086ae5bd4044f0ea9ce70ddb180e4d25567665 +size 2269512896 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q6_K.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q6_K.gguf new file mode 100644 index 0000000..b00907f --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b15f9f9a2d5e5fe51976300c631f812f19d530a896c92af21ea698be95f74ac +size 2643854528 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.Q8_0.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ae2c33c --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966ee638fbfb18c4cdb5acc2e020f1468d2180e7c2819b4e6211cc72dafbf899 +size 3421899968 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.f16.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.f16.gguf new file mode 100644 index 0000000..9527a58 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92de2feac134b55dad229679b43f3a192f7e4ce7fd20c0f9bc244fed6522cdbf +size 6433688768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e7ef7f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: hereticness/Heretic-Llama-3.2-3B-F1-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-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-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-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-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-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. + +