commit 814d4dc25d6993892c3a0a92849ae142d6f8e57f Author: ModelHub XC Date: Tue Jun 2 14:56:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f524f66 --- /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 +Ichigo-llama3.2-3B-s-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ichigo-llama3.2-3B-s-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ichigo-llama3.2-3B-s-instruct.IQ3_M.gguf b/Ichigo-llama3.2-3B-s-instruct.IQ3_M.gguf new file mode 100644 index 0000000..38a13c1 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623943aacdb9ef4d4a3de37c0f0e08a3dc2ff58b099dc7c21785dcacd51f4a43 +size 1600979904 diff --git a/Ichigo-llama3.2-3B-s-instruct.IQ3_S.gguf b/Ichigo-llama3.2-3B-s-instruct.IQ3_S.gguf new file mode 100644 index 0000000..b8ddbc4 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7911f93739989c62eee77954aa7012dc61b0c53c64f5c6f4c4640a32fd98ff +size 1544160192 diff --git a/Ichigo-llama3.2-3B-s-instruct.IQ3_XS.gguf b/Ichigo-llama3.2-3B-s-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..aaac9e1 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6ac44769325e18a422a2f09887207e5eed14263c6bc598b873c6aa3293d04c +size 1478099904 diff --git a/Ichigo-llama3.2-3B-s-instruct.IQ4_XS.gguf b/Ichigo-llama3.2-3B-s-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4b9785d --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0125846538194b86ada9aea3f9aec55cdc186c0a1f6f0b0711970fc5a1e282f8 +size 1842217920 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q2_K.gguf b/Ichigo-llama3.2-3B-s-instruct.Q2_K.gguf new file mode 100644 index 0000000..84bf0ea --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb9ef8999087bbfbcc835758c0694fd8edcfa3286e056cb64395ac02e406f79 +size 1365246912 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q3_K_L.gguf b/Ichigo-llama3.2-3B-s-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1d64c0a --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eae46aa44178f21c2f942b3578b4c81e3b282c2afec78c4b8c187ad1afedb66 +size 1816658880 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q3_K_M.gguf b/Ichigo-llama3.2-3B-s-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..70a693d --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85d2b77530d6d828d3abef3a9915b755f2fbc8cc9d0f584cb5ced2e20fb0350 +size 1688470464 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q3_K_S.gguf b/Ichigo-llama3.2-3B-s-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5898765 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf3b1f7d41f6db14f713299f05901c5875c9648b8d5777797298588bd272e9a +size 1544160192 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q4_K_M.gguf b/Ichigo-llama3.2-3B-s-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5bc161f --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a764892ca936cefd1c2650060ef3188ece902cff2ab5bd9fc7531e2921536704 +size 2020688832 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q4_K_S.gguf b/Ichigo-llama3.2-3B-s-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4772e68 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0c0f18c11324de7094815bd6c7312ad1c5ed00eb83dabbfa351792e682f46c +size 1929511872 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q5_K_M.gguf b/Ichigo-llama3.2-3B-s-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..43d7473 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a65f270d8cb5e2348ce3ef4f2e3ee588a54deb26e82d1ff5d311b3310d962c4 +size 2323465152 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q5_K_S.gguf b/Ichigo-llama3.2-3B-s-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..a128869 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8c8d76f217120322b86ebcf449668bf109f95d1cbaee6602fd46a21001d8e1 +size 2270823360 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q6_K.gguf b/Ichigo-llama3.2-3B-s-instruct.Q6_K.gguf new file mode 100644 index 0000000..86c299f --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46d7ee770c954e6bd3fad83ae0ba55c69af2cd7ab40c6b531d57d1d8b659b2a6 +size 2645164992 diff --git a/Ichigo-llama3.2-3B-s-instruct.Q8_0.gguf b/Ichigo-llama3.2-3B-s-instruct.Q8_0.gguf new file mode 100644 index 0000000..ceb3b29 --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c4b3d75aa4902427e92306676f3728093548db6be83d8a38e75dfa71be60c9 +size 3423593568 diff --git a/Ichigo-llama3.2-3B-s-instruct.f16.gguf b/Ichigo-llama3.2-3B-s-instruct.f16.gguf new file mode 100644 index 0000000..4a056bb --- /dev/null +++ b/Ichigo-llama3.2-3B-s-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9a265d3c4a8e59709fa339d75c8020fc2fba2c9bd0b82905e60ddd66db3993 +size 6436865568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a716384 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Menlo/mini-Ichigo-llama3.2-3B-s-instruct +datasets: +- homebrewltd/instruction-speech-whispervq-v2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- sound language model +--- +## About + + + + + + +static quants of https://huggingface.co/Menlo/mini-Ichigo-llama3.2-3B-s-instruct + + +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/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.2-3B-s-instruct-GGUF/resolve/main/Ichigo-llama3.2-3B-s-instruct.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. + +