commit 41c20f0fc2704592285315f2339d7ca8540a84bc Author: ModelHub XC Date: Sat Jun 13 06:18:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/InfiReasoner-Preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f04a573 --- /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 +InfiReasoner-Preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.f16.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiReasoner-Preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InfiReasoner-Preview.IQ4_XS.gguf b/InfiReasoner-Preview.IQ4_XS.gguf new file mode 100644 index 0000000..823f294 --- /dev/null +++ b/InfiReasoner-Preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc736df41cfd3399bbea2ef38f4c1190c85607c02b2e4ec3e02a42d58c4f58b +size 4250298528 diff --git a/InfiReasoner-Preview.Q2_K.gguf b/InfiReasoner-Preview.Q2_K.gguf new file mode 100644 index 0000000..40172d3 --- /dev/null +++ b/InfiReasoner-Preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a6e95eaa8c05eba7d30a18b06328907b2873dd7ff28edeb520e98764103a82 +size 3015940256 diff --git a/InfiReasoner-Preview.Q3_K_L.gguf b/InfiReasoner-Preview.Q3_K_L.gguf new file mode 100644 index 0000000..8e36d80 --- /dev/null +++ b/InfiReasoner-Preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cec3e482474bf256bb73c8763bc3a42eb09f4db7a1d173f36c910b3de2f9fec +size 4088459424 diff --git a/InfiReasoner-Preview.Q3_K_M.gguf b/InfiReasoner-Preview.Q3_K_M.gguf new file mode 100644 index 0000000..3805111 --- /dev/null +++ b/InfiReasoner-Preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01a24f27aea34e541803a03db713f8bf536377c1a99ef3e0e3d279f4641feb8 +size 3808391328 diff --git a/InfiReasoner-Preview.Q3_K_S.gguf b/InfiReasoner-Preview.Q3_K_S.gguf new file mode 100644 index 0000000..5ee7c40 --- /dev/null +++ b/InfiReasoner-Preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35e3698c690b2766bad81d8b954ae8a8ae98599ff14fc2723ebefaa25a1d885 +size 3492368544 diff --git a/InfiReasoner-Preview.Q4_K_M.gguf b/InfiReasoner-Preview.Q4_K_M.gguf new file mode 100644 index 0000000..6f28faf --- /dev/null +++ b/InfiReasoner-Preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97e85b213a5e9ed881267888a12f5fd4eaaa11a66177412d75f47f2972a851e +size 4683073696 diff --git a/InfiReasoner-Preview.Q4_K_S.gguf b/InfiReasoner-Preview.Q4_K_S.gguf new file mode 100644 index 0000000..1f9581e --- /dev/null +++ b/InfiReasoner-Preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7ae014aaa96e06baaac65aae5b94883a85ba3c3a03f3fcaee02a16e26374cf +size 4457769120 diff --git a/InfiReasoner-Preview.Q5_K_M.gguf b/InfiReasoner-Preview.Q5_K_M.gguf new file mode 100644 index 0000000..531fb01 --- /dev/null +++ b/InfiReasoner-Preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473029ce07fcb2d4b5bbc2b74e716c2505985a8a784f283b87c92d18a45a2e30 +size 5444831392 diff --git a/InfiReasoner-Preview.Q5_K_S.gguf b/InfiReasoner-Preview.Q5_K_S.gguf new file mode 100644 index 0000000..f7739ab --- /dev/null +++ b/InfiReasoner-Preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c9df2a6892804c1192c4defefa0230e54e1f62242e12d99d6a70542162ff99 +size 5315176608 diff --git a/InfiReasoner-Preview.Q6_K.gguf b/InfiReasoner-Preview.Q6_K.gguf new file mode 100644 index 0000000..69f5615 --- /dev/null +++ b/InfiReasoner-Preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3071515f5fd226978dcd0cead53e838b531ce4f74720113e6a7231c5e0c48ff +size 6254198944 diff --git a/InfiReasoner-Preview.Q8_0.gguf b/InfiReasoner-Preview.Q8_0.gguf new file mode 100644 index 0000000..1996c26 --- /dev/null +++ b/InfiReasoner-Preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2015b6763a54ea82a7297a87d38064e9e85bebdaede66ba2eff9f7180a22cd7e +size 8098525344 diff --git a/InfiReasoner-Preview.f16.gguf b/InfiReasoner-Preview.f16.gguf new file mode 100644 index 0000000..dbc5f87 --- /dev/null +++ b/InfiReasoner-Preview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24c669a2efe2d193796309cadd1d602f0e1ef50984874e5cc5286c3a7002c0a +size 15237853344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..51a45c4 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: InfiX-ai/InfiAlign-Coder +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/InfiX-ai/InfiAlign-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InfiReasoner-Preview-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/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InfiReasoner-Preview-GGUF/resolve/main/InfiReasoner-Preview.f16.gguf) | f16 | 15.3 | 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. + +