commit c9688c88d242ae8f9c2d99c9943fed710a475429 Author: ModelHub XC Date: Sat Jun 20 13:50:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Heretic-InfiR-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..80bc3d3 --- /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-InfiR-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-InfiR-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-InfiR-1B-Instruct.IQ4_XS.gguf b/Heretic-InfiR-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..fcdecfb --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b2775d6d1b55073194626faf73196655fca116c29ac8a20950d57bed84c095 +size 748381632 diff --git a/Heretic-InfiR-1B-Instruct.Q2_K.gguf b/Heretic-InfiR-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..f936d54 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437a0a6122e371ab7cee9b543aa13a2ea37a24470bcc6f8bb7048280a24eae5b +size 580871616 diff --git a/Heretic-InfiR-1B-Instruct.Q3_K_L.gguf b/Heretic-InfiR-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..5aeb34d --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27984e99f805c28d54f1d8fa3952befb0321921c56ae1c59b67520b6ab127e3 +size 732521920 diff --git a/Heretic-InfiR-1B-Instruct.Q3_K_M.gguf b/Heretic-InfiR-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ad304fd --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8dd557845d62c7bd27668d219bdd8b31080846823e102ec72c5da4560e7a25 +size 690841024 diff --git a/Heretic-InfiR-1B-Instruct.Q3_K_S.gguf b/Heretic-InfiR-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..782d678 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3500575bd0c5530f661b3c948b1ea2092091647ff3203f6d07b999cd7506e1f +size 641689024 diff --git a/Heretic-InfiR-1B-Instruct.Q4_K_M.gguf b/Heretic-InfiR-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..b29eae2 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e93134b1660ff250ffdbf86bdaa9a73faf262737fb597c7c64b08ac48ca6995 +size 807691712 diff --git a/Heretic-InfiR-1B-Instruct.Q4_K_S.gguf b/Heretic-InfiR-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..29602c1 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40497b2c6fd83ce24824bf4e29558d035af8fb1890f22f084f0c1e81760ce69f +size 775644608 diff --git a/Heretic-InfiR-1B-Instruct.Q5_K_M.gguf b/Heretic-InfiR-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..187e3cb --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486e934819fefb568dc5686e1a0b941afe1ac4dcae3587dd6a52110f3592d350 +size 911500736 diff --git a/Heretic-InfiR-1B-Instruct.Q5_K_S.gguf b/Heretic-InfiR-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d371845 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1348544e3a3d276aff23fdc7d4667b0d331787f29a5dc6749c20ef6232ebf83 +size 892560832 diff --git a/Heretic-InfiR-1B-Instruct.Q6_K.gguf b/Heretic-InfiR-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..b727c3b --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f80253a9258708a6985005c89958802dd493ef8156fe5abd2b535f1bfcec1dd +size 1021797824 diff --git a/Heretic-InfiR-1B-Instruct.Q8_0.gguf b/Heretic-InfiR-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..97bd271 --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7ec9022edebc656d33a79982dda59ee28ba582d2ee67d9c2cfac9e8659a3a2 +size 1321080256 diff --git a/Heretic-InfiR-1B-Instruct.f16.gguf b/Heretic-InfiR-1B-Instruct.f16.gguf new file mode 100644 index 0000000..90c876f --- /dev/null +++ b/Heretic-InfiR-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e231da00d3c365da334b4d25935463fe6350f5107c49b1251eb92b939c617365 +size 2479592896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8825c9c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: hereticness/Heretic-InfiR-1B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hereticness/Heretic-InfiR-1B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Heretic-InfiR-1B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Heretic-InfiR-1B-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-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-InfiR-1B-Instruct-GGUF/resolve/main/Heretic-InfiR-1B-Instruct.f16.gguf) | f16 | 2.6 | 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. + +