commit c9a2aefe97b0695d56e6c8d97a9969a7da87eb41 Author: ModelHub XC Date: Fri Aug 28 13:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Apriel-5B-Instruct-llamafied-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..784c0a7 --- /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 +Apriel-5B-Instruct-llamafied.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Apriel-5B-Instruct-llamafied.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Apriel-5B-Instruct-llamafied.IQ4_XS.gguf b/Apriel-5B-Instruct-llamafied.IQ4_XS.gguf new file mode 100644 index 0000000..1b48287 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44558e5fe601ab47f4fef6b3ee7bac9b59573efd459abf13b711bed02dd8c61a +size 2746642368 diff --git a/Apriel-5B-Instruct-llamafied.Q2_K.gguf b/Apriel-5B-Instruct-llamafied.Q2_K.gguf new file mode 100644 index 0000000..36290ba --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da84758a86d235ee85b02af87dc48797edfa277e0bdd9dea8609c608e26954cb +size 2001629120 diff --git a/Apriel-5B-Instruct-llamafied.Q3_K_L.gguf b/Apriel-5B-Instruct-llamafied.Q3_K_L.gguf new file mode 100644 index 0000000..5ebb67c --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46400ebfda696870ac68bae3668d306ebdfe36b3fa6ad17aba485f6ac31a6ac1 +size 2658037696 diff --git a/Apriel-5B-Instruct-llamafied.Q3_K_M.gguf b/Apriel-5B-Instruct-llamafied.Q3_K_M.gguf new file mode 100644 index 0000000..e936337 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7190bad41d48a18e1d698800cebafa2226c259c31b5a694695a6299c3ba94699 +size 2487119808 diff --git a/Apriel-5B-Instruct-llamafied.Q3_K_S.gguf b/Apriel-5B-Instruct-llamafied.Q3_K_S.gguf new file mode 100644 index 0000000..c37b744 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b130edc07724a59cdffb5fef65f8211a49f272f8f19558634c4dbb121e481348 +size 2294706112 diff --git a/Apriel-5B-Instruct-llamafied.Q4_K_M.gguf b/Apriel-5B-Instruct-llamafied.Q4_K_M.gguf new file mode 100644 index 0000000..dacb196 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135c005d1eb2765b476af5af10e87323afe46e64bd21fad36bca89eda6b89537 +size 3001380800 diff --git a/Apriel-5B-Instruct-llamafied.Q4_K_S.gguf b/Apriel-5B-Instruct-llamafied.Q4_K_S.gguf new file mode 100644 index 0000000..3606b75 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea811c68e470083e511450ff7067820b4eb0bea1d510c83e49890d75d97ec557 +size 2879811520 diff --git a/Apriel-5B-Instruct-llamafied.Q5_K_M.gguf b/Apriel-5B-Instruct-llamafied.Q5_K_M.gguf new file mode 100644 index 0000000..b298639 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c33ec9c0cfd4542563788a3617950fc452c7eb40de7f94b86a58904ef28f873 +size 3472191424 diff --git a/Apriel-5B-Instruct-llamafied.Q5_K_S.gguf b/Apriel-5B-Instruct-llamafied.Q5_K_S.gguf new file mode 100644 index 0000000..48c2ec4 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf07cbd0c30364979fc03546dabaeace10d8ecc8ffb0ca5b21c57da40fc5604 +size 3402002368 diff --git a/Apriel-5B-Instruct-llamafied.Q6_K.gguf b/Apriel-5B-Instruct-llamafied.Q6_K.gguf new file mode 100644 index 0000000..85dc8ba --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b291fe4a5fa9d436406793c148e4018eb20d05f65080a39962f6b96a8ec459e +size 3972427712 diff --git a/Apriel-5B-Instruct-llamafied.Q8_0.gguf b/Apriel-5B-Instruct-llamafied.Q8_0.gguf new file mode 100644 index 0000000..227fcba --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd890d095774f0c908b6635d141d7b74a17a71c5999cd0147f7cc162d2b8d54 +size 5142638528 diff --git a/Apriel-5B-Instruct-llamafied.f16.gguf b/Apriel-5B-Instruct-llamafied.f16.gguf new file mode 100644 index 0000000..3c0fae9 --- /dev/null +++ b/Apriel-5B-Instruct-llamafied.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd56b541f88f3ff79f9008dd6463ef5ba8f0272c414bc707848b39dc3e16431c +size 9672486848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7d145d5 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: mrfakename/Apriel-5B-Instruct-llamafied +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/mrfakename/Apriel-5B-Instruct-llamafied + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-i1-GGUF +## 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/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q2_K.gguf) | Q2_K | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q3_K_S.gguf) | Q3_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q3_K_M.gguf) | Q3_K_M | 2.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q3_K_L.gguf) | Q3_K_L | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.IQ4_XS.gguf) | IQ4_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q4_K_S.gguf) | Q4_K_S | 3.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q4_K_M.gguf) | Q4_K_M | 3.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q5_K_S.gguf) | Q5_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q5_K_M.gguf) | Q5_K_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q6_K.gguf) | Q6_K | 4.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.Q8_0.gguf) | Q8_0 | 5.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Apriel-5B-Instruct-llamafied-GGUF/resolve/main/Apriel-5B-Instruct-llamafied.f16.gguf) | f16 | 9.8 | 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. + +