commit eeca667d445388ef4493ae6c6b9878395be28d0a Author: ModelHub XC Date: Wed Aug 26 19:00:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Neural4gsm8k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1ca1e95 --- /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 +Neural4gsm8k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Neural4gsm8k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Neural4gsm8k.IQ4_XS.gguf b/Neural4gsm8k.IQ4_XS.gguf new file mode 100644 index 0000000..5098350 --- /dev/null +++ b/Neural4gsm8k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e3913c5e6df47c4745fd075e2c38a773451ca6ba0d644ffdae4830ae03fb04 +size 3944389664 diff --git a/Neural4gsm8k.Q2_K.gguf b/Neural4gsm8k.Q2_K.gguf new file mode 100644 index 0000000..690d15d --- /dev/null +++ b/Neural4gsm8k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac913bfe31c32c8184a4713c6208926e3925b1aa7c141a9cd4eaf7ce24529fb3 +size 2719243296 diff --git a/Neural4gsm8k.Q3_K_L.gguf b/Neural4gsm8k.Q3_K_L.gguf new file mode 100644 index 0000000..f413c01 --- /dev/null +++ b/Neural4gsm8k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323a101ae9c7c326b009b06bd39ffab726c839fb1a66d90ad7137f3be92c0dd2 +size 3822025760 diff --git a/Neural4gsm8k.Q3_K_M.gguf b/Neural4gsm8k.Q3_K_M.gguf new file mode 100644 index 0000000..6cb3977 --- /dev/null +++ b/Neural4gsm8k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4d99a47da596b67d493e65e04df2dce8f6aadf12415638de85be30a676e17d +size 3518987296 diff --git a/Neural4gsm8k.Q3_K_S.gguf b/Neural4gsm8k.Q3_K_S.gguf new file mode 100644 index 0000000..66d038b --- /dev/null +++ b/Neural4gsm8k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec069c959108210db694d59454adcca3f936e04cd0932b94a89886cb98c036d +size 3164568608 diff --git a/Neural4gsm8k.Q4_K_M.gguf b/Neural4gsm8k.Q4_K_M.gguf new file mode 100644 index 0000000..43cf362 --- /dev/null +++ b/Neural4gsm8k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d4cdb8b82208a80806a57f7cd03ff0e77418d05aa490e3cc81c8aa96535f1e +size 4368440352 diff --git a/Neural4gsm8k.Q4_K_S.gguf b/Neural4gsm8k.Q4_K_S.gguf new file mode 100644 index 0000000..144b3ae --- /dev/null +++ b/Neural4gsm8k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7184a038f905e1edaedc30c3c9e99fbd49cf4b454dcaf8c876088dbbb0c944a +size 4140375072 diff --git a/Neural4gsm8k.Q5_K_M.gguf b/Neural4gsm8k.Q5_K_M.gguf new file mode 100644 index 0000000..f5a19e2 --- /dev/null +++ b/Neural4gsm8k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c034cd362ee4bb7b61802f57d6b85739347ad24db19cd7a805e545f6c842ab1 +size 5131410464 diff --git a/Neural4gsm8k.Q5_K_S.gguf b/Neural4gsm8k.Q5_K_S.gguf new file mode 100644 index 0000000..a11e8b6 --- /dev/null +++ b/Neural4gsm8k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90316afa223e3c7c99ba4583d56da15524b46d1b89acc72e4f9b9815c9e9f630 +size 4997717024 diff --git a/Neural4gsm8k.Q6_K.gguf b/Neural4gsm8k.Q6_K.gguf new file mode 100644 index 0000000..d6e5218 --- /dev/null +++ b/Neural4gsm8k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2020685c80eeb1a5bbb177591eda36019be951f3aa6359da613467bec449559d +size 5942066208 diff --git a/Neural4gsm8k.Q8_0.gguf b/Neural4gsm8k.Q8_0.gguf new file mode 100644 index 0000000..c9f20a8 --- /dev/null +++ b/Neural4gsm8k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13adc3ed251b26c691b1a14485c9ee3171f88cb1c16753225dfeb91bf94f3010 +size 7695858720 diff --git a/Neural4gsm8k.f16.gguf b/Neural4gsm8k.f16.gguf new file mode 100644 index 0000000..09bd9cb --- /dev/null +++ b/Neural4gsm8k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64259171c88f9ce96b163bd11b913e02b0e4b1ee6f894107c8d18268ccb627b7 +size 14484732960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..109c7d3 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Kukedlc/Neural4gsm8k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Kukedlc/Neural-4-ARC-7B-slerp +- Kukedlc/Neural-4-GSM8K-7B-slerp +--- +## About + + + + + + +static quants of https://huggingface.co/Kukedlc/Neural4gsm8k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Neural4gsm8k-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Neural4gsm8k-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/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Neural4gsm8k-GGUF/resolve/main/Neural4gsm8k.f16.gguf) | f16 | 14.6 | 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. + +