commit 988a97ca8887dbde3b2d5b192e88d0203a962a0e Author: ModelHub XC Date: Fri Apr 24 07:55:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3b-Neuro-sama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f843b83 --- /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 +Llama3.2-3b-Neuro-sama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3b-Neuro-sama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3b-Neuro-sama.IQ4_XS.gguf b/Llama3.2-3b-Neuro-sama.IQ4_XS.gguf new file mode 100644 index 0000000..98bd4a0 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd8be8923a3208793885fb45c07ca7f4575823dd7474e9325afd4009ddd338e +size 1840908064 diff --git a/Llama3.2-3b-Neuro-sama.Q2_K.gguf b/Llama3.2-3b-Neuro-sama.Q2_K.gguf new file mode 100644 index 0000000..c44e971 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53cb66ac51001584d258568ce57fa7baa739f8741bed5476fea84b6fb862f3f +size 1363937056 diff --git a/Llama3.2-3b-Neuro-sama.Q3_K_L.gguf b/Llama3.2-3b-Neuro-sama.Q3_K_L.gguf new file mode 100644 index 0000000..e0790c9 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9839de8deff62326f012cc5c368bdb45cd9ae6268fb4a5f5bca48052b06d1d9a +size 1815349024 diff --git a/Llama3.2-3b-Neuro-sama.Q3_K_M.gguf b/Llama3.2-3b-Neuro-sama.Q3_K_M.gguf new file mode 100644 index 0000000..8dcec15 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0b1f15377288cb64b0194b9ed0747ce9fb2ada3fe0a36916b5e1d630781ec8 +size 1687160608 diff --git a/Llama3.2-3b-Neuro-sama.Q3_K_S.gguf b/Llama3.2-3b-Neuro-sama.Q3_K_S.gguf new file mode 100644 index 0000000..c5729f3 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab52ce045a00cb249636f448682accff53043d219664a87218989cba0c9ba092 +size 1542850336 diff --git a/Llama3.2-3b-Neuro-sama.Q4_K_M.gguf b/Llama3.2-3b-Neuro-sama.Q4_K_M.gguf new file mode 100644 index 0000000..6230c76 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9719a0cf90ba1119ce9057aa603b1bc2ae0d35c260360817519f3f408a70ce +size 2019378976 diff --git a/Llama3.2-3b-Neuro-sama.Q4_K_S.gguf b/Llama3.2-3b-Neuro-sama.Q4_K_S.gguf new file mode 100644 index 0000000..5b11d8c --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88126fa3acd4c3e82a06b1882a33ff12493984cb5338de12adac9466ea70a3dc +size 1928202016 diff --git a/Llama3.2-3b-Neuro-sama.Q5_K_M.gguf b/Llama3.2-3b-Neuro-sama.Q5_K_M.gguf new file mode 100644 index 0000000..5eb19fd --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8b38d3ab96c0e562cfb188bad673b8ce9d7acfaaf4bacd1efd0028685e23fc +size 2322155296 diff --git a/Llama3.2-3b-Neuro-sama.Q5_K_S.gguf b/Llama3.2-3b-Neuro-sama.Q5_K_S.gguf new file mode 100644 index 0000000..1ed8166 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a604e0fabf881a1b6cbcebe6464f5c80162d41c8dfbf894712e5216760db70 +size 2269513504 diff --git a/Llama3.2-3b-Neuro-sama.Q6_K.gguf b/Llama3.2-3b-Neuro-sama.Q6_K.gguf new file mode 100644 index 0000000..e748e19 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e593bebbb1fd50680fffcbbef1b1778f442eefc57a66a261b47772ca488551b3 +size 2643855136 diff --git a/Llama3.2-3b-Neuro-sama.Q8_0.gguf b/Llama3.2-3b-Neuro-sama.Q8_0.gguf new file mode 100644 index 0000000..fefc17e --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93dcb06d6d24ccb00b6cd136e5615b984d19d7d87dddc276128a3f48da37dd8 +size 3421900576 diff --git a/Llama3.2-3b-Neuro-sama.f16.gguf b/Llama3.2-3b-Neuro-sama.f16.gguf new file mode 100644 index 0000000..c9dbc59 --- /dev/null +++ b/Llama3.2-3b-Neuro-sama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c7d68db6aef02d6ece4ae601fbdd794aa3a540ee8f7f41dc63b38a14fd4718 +size 6433689376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ee072a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: SUBSECT420/Llama3.2-3b-Neuro-sama +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/SUBSECT420/Llama3.2-3b-Neuro-sama + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-3b-Neuro-sama-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/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3b-Neuro-sama-GGUF/resolve/main/Llama3.2-3b-Neuro-sama.f16.gguf) | f16 | 6.5 | 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. + +