commit e3724bb5f3fbf131641cfd1f517a6e6c2ec82834 Author: ModelHub XC Date: Thu Oct 1 10:19:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llamaphi-3-128k-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3e55b29 --- /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 +llamaphi-3-128k-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llamaphi-3-128k-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..105ef24 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: mrfakename/llamaphi-3-128k-instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/mrfakename/llamaphi-3-128k-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/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llamaphi-3-128k-instruct-GGUF/resolve/main/llamaphi-3-128k-instruct.f16.gguf) | f16 | 7.7 | 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/llamaphi-3-128k-instruct.IQ4_XS.gguf b/llamaphi-3-128k-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cbcf2a7 --- /dev/null +++ b/llamaphi-3-128k-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6034f3584845326213d974b10401aea4345f61c50bb5134843bbfb0d8c508a2f +size 2075586656 diff --git a/llamaphi-3-128k-instruct.Q2_K.gguf b/llamaphi-3-128k-instruct.Q2_K.gguf new file mode 100644 index 0000000..056f726 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d9a65beda3f89851298d3037e73512818f3b47786853cb0e132100b3a08883 +size 1446880352 diff --git a/llamaphi-3-128k-instruct.Q3_K_L.gguf b/llamaphi-3-128k-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e68e205 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccc2324db90a9dd571afbd3e3b69dc8401fddc05ad4fa37055ee9c6b347dcc0 +size 2045135456 diff --git a/llamaphi-3-128k-instruct.Q3_K_M.gguf b/llamaphi-3-128k-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ee4bc9f --- /dev/null +++ b/llamaphi-3-128k-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9def6abb631fa383db4c9e1fa00358951db079b9e1345e9e1aca4bd05e85d54e +size 1877625440 diff --git a/llamaphi-3-128k-instruct.Q3_K_S.gguf b/llamaphi-3-128k-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..556d056 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3fe4545c6164ca50b34b02648b430d72b3104c50a8b340f78840edbfaf0fe8 +size 1681803872 diff --git a/llamaphi-3-128k-instruct.Q4_K_M.gguf b/llamaphi-3-128k-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..b037e84 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff2adc07ca876851c5567ff19b76727331c72c8e248a700f8511134afc6aa6f +size 2318919776 diff --git a/llamaphi-3-128k-instruct.Q4_K_S.gguf b/llamaphi-3-128k-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..806777d --- /dev/null +++ b/llamaphi-3-128k-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd71f2f2c6be9360929aa1d799fd8158cf6bda3d8be7910a3192d0bb8bf26f6 +size 2193483872 diff --git a/llamaphi-3-128k-instruct.Q5_K_M.gguf b/llamaphi-3-128k-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..5b9acdb --- /dev/null +++ b/llamaphi-3-128k-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48976357f78db77315bf713a110db1286b993a3094744b5bd28b31742160c7f +size 2715011168 diff --git a/llamaphi-3-128k-instruct.Q5_K_S.gguf b/llamaphi-3-128k-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..9b97212 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3dee0da220c5c15bfcee03eadefde4fe3a9bcc279739592909043dffac0f1b +size 2641479776 diff --git a/llamaphi-3-128k-instruct.Q6_K.gguf b/llamaphi-3-128k-instruct.Q6_K.gguf new file mode 100644 index 0000000..598c275 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514ea3805f555a52f031a99c9d00ccca0bd43672a48c885e5ff26edc57dd3bc0 +size 3135858272 diff --git a/llamaphi-3-128k-instruct.Q8_0.gguf b/llamaphi-3-128k-instruct.Q8_0.gguf new file mode 100644 index 0000000..9b50481 --- /dev/null +++ b/llamaphi-3-128k-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f565e1be67563c595466b2d274c5c29a2d9ba3cbf0021d7796b2ace9476031b7 +size 4061227616 diff --git a/llamaphi-3-128k-instruct.f16.gguf b/llamaphi-3-128k-instruct.f16.gguf new file mode 100644 index 0000000..4dfcf85 --- /dev/null +++ b/llamaphi-3-128k-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca2e0c808427361023a5ad2a89b2a82b7a6ff7ffbb8824e699408fe3652731a +size 7643302496