commit 2804ebb4a703d10ff2ca318261f45c66f703ab2b Author: ModelHub XC Date: Mon May 4 19:59:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f735ee7 --- /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 +Phi-3-mini-4k-instruct-opus-samantha.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-opus-samantha.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3-mini-4k-instruct-opus-samantha.IQ4_XS.gguf b/Phi-3-mini-4k-instruct-opus-samantha.IQ4_XS.gguf new file mode 100644 index 0000000..9d5d46b --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9381236645e3bd21ff25b8262de5fb578d3405e6b5ca670f6f844582439d725d +size 2075581312 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q2_K.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q2_K.gguf new file mode 100644 index 0000000..0f17ae5 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282b9d33268a075b112c3d7eee14b724f19dc5eec339c315676bf9c711a6c952 +size 1416204160 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_L.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_L.gguf new file mode 100644 index 0000000..986b9ed --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593fd78d5b3280e194dca9fa6bf58ea7f7801f48a5601a136763353c7873f791 +size 2087597440 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_M.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_M.gguf new file mode 100644 index 0000000..1990a62 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c45723173f53a2b047797c1caa2c580decbc98e5c56b4cb2f614a1ed6e9cdae +size 1955476864 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_S.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_S.gguf new file mode 100644 index 0000000..0d509c8 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e770cf5f6d40e26416cf78912a59c2d8976102ce16e96aee3ff5a6b65cdba5ba +size 1681798528 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_M.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_M.gguf new file mode 100644 index 0000000..63d42e8 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62684241074288afd58e3bb576f1f0f8642787ac772fd79954bdd4847bc7f22 +size 2393232256 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_S.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_S.gguf new file mode 100644 index 0000000..8275329 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cc747738ed5792c1d2251ffc06e13080c4fcc54e29c12fa5e94b978750f48c +size 2188759936 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_M.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_M.gguf new file mode 100644 index 0000000..71cdcda --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414b5aa48f8ae808ddfa1ff30594326d66f253f4e59ca1e45370acb1e611d0dd +size 2815275904 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_S.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_S.gguf new file mode 100644 index 0000000..ce5d5ea --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8cfd1715a1e231d6b315d076c808c03d40ae8ae7da4ff4098bfe43a583addf +size 2641474432 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q6_K.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q6_K.gguf new file mode 100644 index 0000000..740ee2a --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0853cc749fbe0921171556735858c72a575a4449236cb842909fd38891a7ce13 +size 3135852928 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.Q8_0.gguf b/Phi-3-mini-4k-instruct-opus-samantha.Q8_0.gguf new file mode 100644 index 0000000..2751ecd --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5edb2fcfe77160df9eef2d4fdd02a2663d3a42a14a8cf0d08162373278edeb4d +size 4061222272 diff --git a/Phi-3-mini-4k-instruct-opus-samantha.f16.gguf b/Phi-3-mini-4k-instruct-opus-samantha.f16.gguf new file mode 100644 index 0000000..af0ab87 --- /dev/null +++ b/Phi-3-mini-4k-instruct-opus-samantha.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1386e3bf1c7b56c220ab03e6ea5898cfb3cefe6f6be92c3a7d0c67ae906db2 +size 7643297152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff558a2 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: anezatra/Phi-3-mini-4k-instruct-opus-samantha +datasets: +- macadeliccc/opus_samantha +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/anezatra/Phi-3-mini-4k-instruct-opus-samantha + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phi-3-mini-4k-instruct-opus-samantha-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/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-opus-samantha-GGUF/resolve/main/Phi-3-mini-4k-instruct-opus-samantha.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. + +