commit 64f5eb94cbac4fba0b31ff9386655a484dec2f2d Author: ModelHub XC Date: Tue Sep 15 18:36:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Prakrit1.0-7b-small-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a8b8c4 --- /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 +Prakrit1.0-7b-small.f16.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Prakrit1.0-7b-small.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Prakrit1.0-7b-small.IQ4_XS.gguf b/Prakrit1.0-7b-small.IQ4_XS.gguf new file mode 100644 index 0000000..96eee93 --- /dev/null +++ b/Prakrit1.0-7b-small.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d7086a3b45e542f9342ba66006a99345383cbbc00e11bcb85c0296ddf7b275 +size 4248357440 diff --git a/Prakrit1.0-7b-small.Q2_K.gguf b/Prakrit1.0-7b-small.Q2_K.gguf new file mode 100644 index 0000000..1c9c7d7 --- /dev/null +++ b/Prakrit1.0-7b-small.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a440314643895e39361d81224d440fdec0a72e8974bd3e1144f7c938f571e7 +size 3014289632 diff --git a/Prakrit1.0-7b-small.Q3_K_L.gguf b/Prakrit1.0-7b-small.Q3_K_L.gguf new file mode 100644 index 0000000..266d8c9 --- /dev/null +++ b/Prakrit1.0-7b-small.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e062edd5af280aa74c8391e9eb76e1f8574bb8dcb3183d8828f0cdec256dba +size 4086663584 diff --git a/Prakrit1.0-7b-small.Q3_K_M.gguf b/Prakrit1.0-7b-small.Q3_K_M.gguf new file mode 100644 index 0000000..61887de --- /dev/null +++ b/Prakrit1.0-7b-small.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b5705ef8247266a0dba9481648e4c3c68918538b9da0760566fb80ebea373d0 +size 3806595488 diff --git a/Prakrit1.0-7b-small.Q3_K_S.gguf b/Prakrit1.0-7b-small.Q3_K_S.gguf new file mode 100644 index 0000000..ea76b5f --- /dev/null +++ b/Prakrit1.0-7b-small.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b14f6f280ca0836f1544fbd44f93872f6e7a1b552b4c73f90b4cc49f37df4767 +size 3490572704 diff --git a/Prakrit1.0-7b-small.Q4_K_M.gguf b/Prakrit1.0-7b-small.Q4_K_M.gguf new file mode 100644 index 0000000..c283ea5 --- /dev/null +++ b/Prakrit1.0-7b-small.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320e758d43b9dae51151151c2ef00889c361f98be97ee431ed2d1bb8e37ea14c +size 4681087904 diff --git a/Prakrit1.0-7b-small.Q4_K_S.gguf b/Prakrit1.0-7b-small.Q4_K_S.gguf new file mode 100644 index 0000000..c06392b --- /dev/null +++ b/Prakrit1.0-7b-small.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5475bf8ed997e862181f93916c0f8d3e97669446931b9e83291d71358ea48f +size 4455783328 diff --git a/Prakrit1.0-7b-small.Q5_K_M.gguf b/Prakrit1.0-7b-small.Q5_K_M.gguf new file mode 100644 index 0000000..b54f18b --- /dev/null +++ b/Prakrit1.0-7b-small.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca22543f70616ebb6b6f4e0f7f34be2b9fd601edf0a5971e3fc8922b5c056b0 +size 5442666848 diff --git a/Prakrit1.0-7b-small.Q5_K_S.gguf b/Prakrit1.0-7b-small.Q5_K_S.gguf new file mode 100644 index 0000000..38e31e5 --- /dev/null +++ b/Prakrit1.0-7b-small.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6cb5d0395e4f2d8d52121849822973a85d50d879d27a92b8d899cc76464abeb +size 5313012064 diff --git a/Prakrit1.0-7b-small.Q6_K.gguf b/Prakrit1.0-7b-small.Q6_K.gguf new file mode 100644 index 0000000..dcd48a6 --- /dev/null +++ b/Prakrit1.0-7b-small.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d879006861d651f2dbcfd552cc23d95e9b5aab43280887722b65495c35fd04de +size 6251844480 diff --git a/Prakrit1.0-7b-small.Q8_0.gguf b/Prakrit1.0-7b-small.Q8_0.gguf new file mode 100644 index 0000000..f0ac0e7 --- /dev/null +++ b/Prakrit1.0-7b-small.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186568a44f7fb7c09b78cfe68cbf4ac698c3a34a2108ac6bba90b2e4c5d15731 +size 8095478208 diff --git a/Prakrit1.0-7b-small.f16.gguf b/Prakrit1.0-7b-small.f16.gguf new file mode 100644 index 0000000..d2fdbc5 --- /dev/null +++ b/Prakrit1.0-7b-small.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e61308d684d646405b85bf5792f524d78dc56bdfc6b458d433c7841f6f3b912 +size 15232124928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac8d636 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Jagneshdeveloper/Prakrit1.0-7b-small +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- code +- agent +- text-generation +- custom-tune +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jagneshdeveloper/Prakrit1.0-7b-small + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Prakrit1.0-7b-small-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/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Prakrit1.0-7b-small-GGUF/resolve/main/Prakrit1.0-7b-small.f16.gguf) | f16 | 15.3 | 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. + +