commit 13f26dfc5cc80ef9100a3bb2dc9a28883e5fc0e6 Author: ModelHub XC Date: Mon Jul 6 21:44:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FastApply-1.5B-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b7b7afa --- /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 +FastApply-1.5B-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FastApply-1.5B-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FastApply-1.5B-v1.0.IQ4_XS.gguf b/FastApply-1.5B-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..e99759e --- /dev/null +++ b/FastApply-1.5B-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8e4f7fe7ec1bde65272d4eab83b316398309242b9517279074f3c4080017b2 +size 902181632 diff --git a/FastApply-1.5B-v1.0.Q2_K.gguf b/FastApply-1.5B-v1.0.Q2_K.gguf new file mode 100644 index 0000000..d338dcb --- /dev/null +++ b/FastApply-1.5B-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cb81c9b3da92fe6fb1ad3e77b1c9b3324469a075c74fd4aafed6660ecab37fb +size 676303616 diff --git a/FastApply-1.5B-v1.0.Q3_K_L.gguf b/FastApply-1.5B-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..1263a9d --- /dev/null +++ b/FastApply-1.5B-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e50b021966be094bb9a9524cc2e02da8383a622428cfe237df23620707d9552 +size 880161536 diff --git a/FastApply-1.5B-v1.0.Q3_K_M.gguf b/FastApply-1.5B-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..457b53e --- /dev/null +++ b/FastApply-1.5B-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04b32431d067b8ab02dc3738060be080d98eacf486b2635ab51f4062d93dd25 +size 824177408 diff --git a/FastApply-1.5B-v1.0.Q3_K_S.gguf b/FastApply-1.5B-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..41bd947 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ccc03127e4d04fb6d295ad07dd1fadf3736c8c0c0c04a6a729376910b1ffcb +size 760943360 diff --git a/FastApply-1.5B-v1.0.Q4_K_M.gguf b/FastApply-1.5B-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..1724af3 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99affdd33f956f83e3e8b3e63f346d5e9452a5ef27a93791fbb0b0dfffd3fb1c +size 986047232 diff --git a/FastApply-1.5B-v1.0.Q4_K_S.gguf b/FastApply-1.5B-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..fa876c6 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501bd255d793b57b20b11e8374e0c7164381f802eb0556a703df0fc3b77350d2 +size 940311296 diff --git a/FastApply-1.5B-v1.0.Q5_K_M.gguf b/FastApply-1.5B-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..6e2d0e7 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7cdcb58960f84419ae9da1d1f3d41febf45ac00d3cf62b47067dfbce1f2bce +size 1125049088 diff --git a/FastApply-1.5B-v1.0.Q5_K_S.gguf b/FastApply-1.5B-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..f47589b --- /dev/null +++ b/FastApply-1.5B-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fddb95c8b171f86bc4e5edb6290ba9463d4401288eb43691cbf7675f1a8383 +size 1098728192 diff --git a/FastApply-1.5B-v1.0.Q6_K.gguf b/FastApply-1.5B-v1.0.Q6_K.gguf new file mode 100644 index 0000000..09c6bb4 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a006e076a0e23ced0e7eceeaf204ab630cc30f45e371d4d24c0235fde04c087 +size 1272738560 diff --git a/FastApply-1.5B-v1.0.Q8_0.gguf b/FastApply-1.5B-v1.0.Q8_0.gguf new file mode 100644 index 0000000..937dfa3 --- /dev/null +++ b/FastApply-1.5B-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2528262514d254d04afa25153c45318e6c85aa445400fbc7e46b5d8b291ae3d8 +size 1646571776 diff --git a/FastApply-1.5B-v1.0.f16.gguf b/FastApply-1.5B-v1.0.f16.gguf new file mode 100644 index 0000000..8c9f3d8 --- /dev/null +++ b/FastApply-1.5B-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc2b8b138d2415f5ac6e93c65aa65b0f524e7d3c3232ecb531d6cc77e7373f3 +size 3093668096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..24610ba --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Kortix/FastApply-1.5B-v1.0 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +- fast-apply +- instant-apply +--- +## About + + + + + + +static quants of https://huggingface.co/Kortix/FastApply-1.5B-v1.0 + + +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/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FastApply-1.5B-v1.0-GGUF/resolve/main/FastApply-1.5B-v1.0.f16.gguf) | f16 | 3.2 | 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. + +