commit e238dc54b5f9c11c16c9334796fcc677af26165f Author: ModelHub XC Date: Sun Jun 28 07:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3_numina_iter2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..102c978 --- /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 +Llama3_numina_iter2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3_numina_iter2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3_numina_iter2.IQ4_XS.gguf b/Llama3_numina_iter2.IQ4_XS.gguf new file mode 100644 index 0000000..87f6c42 --- /dev/null +++ b/Llama3_numina_iter2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42234e76abf32fb7070a7a9f55027f826ba435dbd5f56f86a8fb4aed33d0d38a +size 4484363104 diff --git a/Llama3_numina_iter2.Q2_K.gguf b/Llama3_numina_iter2.Q2_K.gguf new file mode 100644 index 0000000..2a834f5 --- /dev/null +++ b/Llama3_numina_iter2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73610fd4c4507e798c636a3058c9d27aa2bd2d31576f7f517b70a9dd71f99d13 +size 3179131744 diff --git a/Llama3_numina_iter2.Q3_K_L.gguf b/Llama3_numina_iter2.Q3_K_L.gguf new file mode 100644 index 0000000..74f3296 --- /dev/null +++ b/Llama3_numina_iter2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d152f86f022bf13f296b3fc1162bc37b616ce6644aef00e235b0aa58c4873b77 +size 4321956704 diff --git a/Llama3_numina_iter2.Q3_K_M.gguf b/Llama3_numina_iter2.Q3_K_M.gguf new file mode 100644 index 0000000..b47d594 --- /dev/null +++ b/Llama3_numina_iter2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a17526c7f65421f148949b9b641ada2627c23570a1e533ed31ec2f12abffa4b +size 4018918240 diff --git a/Llama3_numina_iter2.Q3_K_S.gguf b/Llama3_numina_iter2.Q3_K_S.gguf new file mode 100644 index 0000000..51da427 --- /dev/null +++ b/Llama3_numina_iter2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936284e541425070059575355f9c8d90df3335ebf736080ddb531b1c890145e2 +size 3664499552 diff --git a/Llama3_numina_iter2.Q4_K_M.gguf b/Llama3_numina_iter2.Q4_K_M.gguf new file mode 100644 index 0000000..7193dfc --- /dev/null +++ b/Llama3_numina_iter2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:572fa70f27ca37411dfe42a25e09db9f46c977cf45175ea341307197ab1c653f +size 4920734560 diff --git a/Llama3_numina_iter2.Q4_K_S.gguf b/Llama3_numina_iter2.Q4_K_S.gguf new file mode 100644 index 0000000..5ba3eb8 --- /dev/null +++ b/Llama3_numina_iter2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3d3ab3016fa89a66666049344b8fc49210f9b4dd614c542c3b75d321f5a27d +size 4692669280 diff --git a/Llama3_numina_iter2.Q5_K_M.gguf b/Llama3_numina_iter2.Q5_K_M.gguf new file mode 100644 index 0000000..f0ac520 --- /dev/null +++ b/Llama3_numina_iter2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac76883828c22ec0f5adb80de14048453dbc546105a8d4dfa6092f2baaa5a75 +size 5732987744 diff --git a/Llama3_numina_iter2.Q5_K_S.gguf b/Llama3_numina_iter2.Q5_K_S.gguf new file mode 100644 index 0000000..dadd57d --- /dev/null +++ b/Llama3_numina_iter2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3ed4221c220bbece8995e0df230b92b7f79888a92c3e9474f2d678d626d7eb +size 5599294304 diff --git a/Llama3_numina_iter2.Q6_K.gguf b/Llama3_numina_iter2.Q6_K.gguf new file mode 100644 index 0000000..cd883ad --- /dev/null +++ b/Llama3_numina_iter2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9d1585820308ab8b9165879d5903fb7fe8d4066825788cc0c15ee1f316cb84 +size 6596006752 diff --git a/Llama3_numina_iter2.Q8_0.gguf b/Llama3_numina_iter2.Q8_0.gguf new file mode 100644 index 0000000..d2f9222 --- /dev/null +++ b/Llama3_numina_iter2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133c4fa663150630cd385c4363dd6617e02c3091bf85c353ec514ce8cd1f6d4c +size 8540771168 diff --git a/Llama3_numina_iter2.f16.gguf b/Llama3_numina_iter2.f16.gguf new file mode 100644 index 0000000..a062ca0 --- /dev/null +++ b/Llama3_numina_iter2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7542926407b3223a4e40163946b445b1d132bc7549d63be73030b65abf53fc2 +size 16068891488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be25cdb --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: HanningZhang/Llama3_numina_iter2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/HanningZhang/Llama3_numina_iter2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3_numina_iter2-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/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3_numina_iter2-GGUF/resolve/main/Llama3_numina_iter2.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. + +