commit 8daf9442f7e4572c84e85b3075f529c6243db44b Author: ModelHub XC Date: Fri Jun 19 03:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neural-chat-7b-v3-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02a57c9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +neural-chat-7b-v3-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.f16.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..201cf14 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Intel/neural-chat-7b-v3-2 +datasets: +- meta-math/MetaMathQA +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- LLMs +- mistral +- math +- Intel +--- +## About + + + + + + +static quants of https://huggingface.co/Intel/neural-chat-7b-v3-2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/neural-chat-7b-v3-2-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/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-GGUF/resolve/main/neural-chat-7b-v3-2.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. + + diff --git a/neural-chat-7b-v3-2.IQ4_XS.gguf b/neural-chat-7b-v3-2.IQ4_XS.gguf new file mode 100644 index 0000000..ddcb716 --- /dev/null +++ b/neural-chat-7b-v3-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c64f02251aad62be320340ed5d21b3296fc5c0fdab11f75113fbde36e35dc1 +size 3944389216 diff --git a/neural-chat-7b-v3-2.Q2_K.gguf b/neural-chat-7b-v3-2.Q2_K.gguf new file mode 100644 index 0000000..51b74cd --- /dev/null +++ b/neural-chat-7b-v3-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76609522709a845912ffdba6f22c8fe6e0273a90bb7cd9be3619b7c2426c73ba +size 2719242848 diff --git a/neural-chat-7b-v3-2.Q3_K_L.gguf b/neural-chat-7b-v3-2.Q3_K_L.gguf new file mode 100644 index 0000000..6e6f439 --- /dev/null +++ b/neural-chat-7b-v3-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44cc148f58943fd6248ac1596176c4da69dcac81b025906b9e0a81f85a8f6254 +size 3822025312 diff --git a/neural-chat-7b-v3-2.Q3_K_M.gguf b/neural-chat-7b-v3-2.Q3_K_M.gguf new file mode 100644 index 0000000..1c3e1e4 --- /dev/null +++ b/neural-chat-7b-v3-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4133a0f46f2078a9ed9a84efd0e09c24e3b7f3779e518f6e528fd43344137113 +size 3518986848 diff --git a/neural-chat-7b-v3-2.Q3_K_S.gguf b/neural-chat-7b-v3-2.Q3_K_S.gguf new file mode 100644 index 0000000..ecc37d9 --- /dev/null +++ b/neural-chat-7b-v3-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7551c78fc2a8f3f9df4b1d065c25dd74e389638f9f268a323ac9c6bc6bf75b +size 3164568160 diff --git a/neural-chat-7b-v3-2.Q4_0_4_4.gguf b/neural-chat-7b-v3-2.Q4_0_4_4.gguf new file mode 100644 index 0000000..c22a234 --- /dev/null +++ b/neural-chat-7b-v3-2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7361b421c364de3ac6ff5dc71242b6b284a9d17676ed48faa15a52dc7ac65588 +size 4108917344 diff --git a/neural-chat-7b-v3-2.Q4_K_M.gguf b/neural-chat-7b-v3-2.Q4_K_M.gguf new file mode 100644 index 0000000..bd99345 --- /dev/null +++ b/neural-chat-7b-v3-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8bf24f7580613050fb10b90374d4208175584b23130e16d4048f6ad5816f220 +size 4368439904 diff --git a/neural-chat-7b-v3-2.Q4_K_S.gguf b/neural-chat-7b-v3-2.Q4_K_S.gguf new file mode 100644 index 0000000..34a0387 --- /dev/null +++ b/neural-chat-7b-v3-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4b4ddd348fd0c2bbbd8476ca9a848b069bcc6c33b207bbcac200f56de9a6aa +size 4140374624 diff --git a/neural-chat-7b-v3-2.Q5_K_M.gguf b/neural-chat-7b-v3-2.Q5_K_M.gguf new file mode 100644 index 0000000..d4671d0 --- /dev/null +++ b/neural-chat-7b-v3-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dacfbac3e16f356b8dd5a35b11f8b29c27d7b05109967c2247a8b728b332f29 +size 5131410016 diff --git a/neural-chat-7b-v3-2.Q5_K_S.gguf b/neural-chat-7b-v3-2.Q5_K_S.gguf new file mode 100644 index 0000000..4dfea02 --- /dev/null +++ b/neural-chat-7b-v3-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc6c7ac4dbb078bce10225fa9df25c4049d54b808e95684f35a5a6393fca96f +size 4997716576 diff --git a/neural-chat-7b-v3-2.Q6_K.gguf b/neural-chat-7b-v3-2.Q6_K.gguf new file mode 100644 index 0000000..7fe58c5 --- /dev/null +++ b/neural-chat-7b-v3-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728262b420734570cfb3e43bee6cd84b02c738674a0c7e007887d7bfcb248da3 +size 5942065760 diff --git a/neural-chat-7b-v3-2.Q8_0.gguf b/neural-chat-7b-v3-2.Q8_0.gguf new file mode 100644 index 0000000..c0599ce --- /dev/null +++ b/neural-chat-7b-v3-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92207a098c55b13c60b3fdc11db019869af1c8343636f452303cf9c56162d833 +size 7695858272 diff --git a/neural-chat-7b-v3-2.f16.gguf b/neural-chat-7b-v3-2.f16.gguf new file mode 100644 index 0000000..10c58c8 --- /dev/null +++ b/neural-chat-7b-v3-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28eb9ffc7b1b7d559100325794b7cc850846ff0134d4b42f43702e4066be39ad +size 14484732512