From 604cb95b7f7a8d82a13da3609646ac5c22470d8c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 7 Oct 2026 04:47:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++ AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf | 3 ++ AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf | 3 ++ README.md | 71 ++++++++++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf create mode 100644 AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d01c45 --- /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 +AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf new file mode 100644 index 0000000..fc7b802 --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d2f18aee06fc89c317bdf150fc66931e8401d58b33cf2059e71dca23a5493a +size 4484363168 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf new file mode 100644 index 0000000..d325cde --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490810d7036e29833a51de3015e0708f3b9685ee5785b2d45899ac13239cd070 +size 3179131808 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf new file mode 100644 index 0000000..cfce72e --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98725ccb7b3d91092992511c6d8370f8d1077dc59dc90a2b8a2ae113c70877f9 +size 4321956768 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf new file mode 100644 index 0000000..5f6d1ff --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9666649b2b009b043e9fcc4c72ef415a1fb6ed7a8ef72ef9a237f08ee766f431 +size 4018918304 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf new file mode 100644 index 0000000..b2043ab --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2ab8587803640c7c27d98f9a109c3e2d1b01aa5a30fcc1e5a459ec1abdf327 +size 3664499616 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf new file mode 100644 index 0000000..5d6f471 --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccdc14802652a5435a3f5e34a585264c225e968debe201e93045fc3ac7ee533 +size 4920734624 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf new file mode 100644 index 0000000..4d8aea7 --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b414728bd5ccc90ba556b15108e964414f3cf10858e6b43c84fc8dff389851d +size 4692669344 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf new file mode 100644 index 0000000..9f9c05c --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42055d9f276a542b30d83a1b71e97f575679b8b4c9c9f6d436d0dcf5bd99ec7 +size 5732987808 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf new file mode 100644 index 0000000..f1b0eb8 --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de683f1692eeda239d94d827946993490048349ec4fc65457a1e1614683d1696 +size 5599294368 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf new file mode 100644 index 0000000..239cb16 --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df024b5a676728d6c40b9f339a687e2d44320aa2336787258d76433f76e646f2 +size 6596006816 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf new file mode 100644 index 0000000..ef8ddfd --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d444a1df0955065b3e9738e5f956c14725615e3dc0403e3f398ec77453b05e01 +size 8540771232 diff --git a/AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf b/AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf new file mode 100644 index 0000000..4b939ac --- /dev/null +++ b/AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129147af10a7bd2cb5f5329cd535603a25e6674c7665fa1cff8beacb9755a14a +size 16068891552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c28479 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: yujunzhou/AIME-TTT-Llama-3.1-8B-TTRL +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yujunzhou/AIME-TTT-Llama-3.1-8B-TTRL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AIME-TTT-Llama-3.1-8B-TTRL-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/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AIME-TTT-Llama-3.1-8B-TTRL-GGUF/resolve/main/AIME-TTT-Llama-3.1-8B-TTRL.f16.gguf) | f16 | 16.2 | 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. + +