commit 3fac3d7994ce36ef67b7215eb80a267be7c1774b Author: ModelHub XC Date: Sat Jun 13 08:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neximind-llama8b-ft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..047b96f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +neximind-llama8b-ft.f16.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neximind-llama8b-ft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5c309a --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: rzr1331/neximind-llama8b-ft +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rzr1331/neximind-llama8b-ft + + +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/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/neximind-llama8b-ft-GGUF/resolve/main/neximind-llama8b-ft.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. + + diff --git a/neximind-llama8b-ft.IQ3_M.gguf b/neximind-llama8b-ft.IQ3_M.gguf new file mode 100644 index 0000000..c15f033 --- /dev/null +++ b/neximind-llama8b-ft.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ba1d7499cd84da803d1c382c2a0f11902fe42f9bd5c68afdce13f38c8eb341 +size 3784833824 diff --git a/neximind-llama8b-ft.IQ3_S.gguf b/neximind-llama8b-ft.IQ3_S.gguf new file mode 100644 index 0000000..203f237 --- /dev/null +++ b/neximind-llama8b-ft.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804c740f04b7925c9e4118c2dfc1c258ca27ebcdbcc01fe1c5fd3c175d4de61e +size 3682335520 diff --git a/neximind-llama8b-ft.IQ3_XS.gguf b/neximind-llama8b-ft.IQ3_XS.gguf new file mode 100644 index 0000000..c79b661 --- /dev/null +++ b/neximind-llama8b-ft.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc595ae20155abeba2fab404b4a1817f2d09c9330fd527952ac34762cf01d78 +size 3518757664 diff --git a/neximind-llama8b-ft.IQ4_XS.gguf b/neximind-llama8b-ft.IQ4_XS.gguf new file mode 100644 index 0000000..a4b6163 --- /dev/null +++ b/neximind-llama8b-ft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac406ba6318533939913c5bbbcc94bda274e6c2f86c7ca8f6a41481a5d5a991 +size 4484374112 diff --git a/neximind-llama8b-ft.Q2_K.gguf b/neximind-llama8b-ft.Q2_K.gguf new file mode 100644 index 0000000..33950b0 --- /dev/null +++ b/neximind-llama8b-ft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16229f3561e178a8650493948244e91295e86b4949d43e7f5cf5970b916a06f0 +size 3179141088 diff --git a/neximind-llama8b-ft.Q3_K_L.gguf b/neximind-llama8b-ft.Q3_K_L.gguf new file mode 100644 index 0000000..c049a91 --- /dev/null +++ b/neximind-llama8b-ft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e35694f99c9274d6e1c1c515d6643722bc12d32ee9efa993d01236b570fa56a +size 4321966880 diff --git a/neximind-llama8b-ft.Q3_K_M.gguf b/neximind-llama8b-ft.Q3_K_M.gguf new file mode 100644 index 0000000..e039b3f --- /dev/null +++ b/neximind-llama8b-ft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5ea11c6f7d5f027f49d97c7094df567d1003db939affe8fae558a0070be1fa +size 4018928416 diff --git a/neximind-llama8b-ft.Q3_K_S.gguf b/neximind-llama8b-ft.Q3_K_S.gguf new file mode 100644 index 0000000..3ae63bc --- /dev/null +++ b/neximind-llama8b-ft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c896ba90655de7d8c0b6b851939c572218d7ae7d07c027ef9fef8cca8155d948 +size 3664509728 diff --git a/neximind-llama8b-ft.Q4_K_M.gguf b/neximind-llama8b-ft.Q4_K_M.gguf new file mode 100644 index 0000000..8d5c95e --- /dev/null +++ b/neximind-llama8b-ft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d90bec1799bd0771f3fa773b4f009ffb159ffd953311a65dbd6b88a0d97de6b2 +size 4920745824 diff --git a/neximind-llama8b-ft.Q4_K_S.gguf b/neximind-llama8b-ft.Q4_K_S.gguf new file mode 100644 index 0000000..8e1311b --- /dev/null +++ b/neximind-llama8b-ft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9346278fb959541eb7daef93d76c4dc01550be9552f0b220ec738ee80f3ddbfc +size 4692680544 diff --git a/neximind-llama8b-ft.Q5_K_M.gguf b/neximind-llama8b-ft.Q5_K_M.gguf new file mode 100644 index 0000000..d28f609 --- /dev/null +++ b/neximind-llama8b-ft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f408e8963432032419770355a4faecb45489e857edb1c23a067bad4c707efed +size 5733000032 diff --git a/neximind-llama8b-ft.Q5_K_S.gguf b/neximind-llama8b-ft.Q5_K_S.gguf new file mode 100644 index 0000000..5cb786c --- /dev/null +++ b/neximind-llama8b-ft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba4ca0b584b6f71efe3af62e55e5dec844951c39f8eca1db7d7482868ce27fd +size 5599306592 diff --git a/neximind-llama8b-ft.Q6_K.gguf b/neximind-llama8b-ft.Q6_K.gguf new file mode 100644 index 0000000..e2d69f7 --- /dev/null +++ b/neximind-llama8b-ft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a66d37dd0e3636b21a084fccb9c245f1b082845371f5b4be899368c19304584 +size 6596020128 diff --git a/neximind-llama8b-ft.Q8_0.gguf b/neximind-llama8b-ft.Q8_0.gguf new file mode 100644 index 0000000..834c3d3 --- /dev/null +++ b/neximind-llama8b-ft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28929216e708d204627b8c5eb3024f2051efcdf93c9f15cd6760a6d1d8806f3 +size 8540788512 diff --git a/neximind-llama8b-ft.f16.gguf b/neximind-llama8b-ft.f16.gguf new file mode 100644 index 0000000..c4b2af4 --- /dev/null +++ b/neximind-llama8b-ft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d1ecbbeed2e37a62b202cd0fb1238bff1d9619ac817dcd77e6f5e846f0f7efa +size 16068924192