commit 250d35bec0330f560cfc19561f46a54f704b6eaa Author: ModelHub XC Date: Sat Jun 13 07:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neural-chat-7b-v3-1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fce88ea --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-v3-1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c4112a9 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Intel/neural-chat-7b-v3-1 +datasets: +- Open-Orca/SlimOrca +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- LLMs +- mistral +- Intel +--- +## About + + + +static quants of https://huggingface.co/Intel/neural-chat-7b-v3-1 + + +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/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.IQ3_XS.gguf) | IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.IQ3_M.gguf) | IQ3_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.IQ4_XS.gguf) | IQ4_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q5_K_M.gguf) | Q5_K_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q6_K.gguf) | Q6_K | 6.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | + +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-v3-1.IQ3_M.gguf b/neural-chat-7b-v3-1.IQ3_M.gguf new file mode 100644 index 0000000..676e58b --- /dev/null +++ b/neural-chat-7b-v3-1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68f83149df3da4439623572259c7f28ceecb42752c84409383dc1109c52360b +size 3439515264 diff --git a/neural-chat-7b-v3-1.IQ3_S.gguf b/neural-chat-7b-v3-1.IQ3_S.gguf new file mode 100644 index 0000000..413504d --- /dev/null +++ b/neural-chat-7b-v3-1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b89487a103cf3fc766ff09a23d13380a64471fadddf8ccb9a8ab3f0254e374 +size 3337016960 diff --git a/neural-chat-7b-v3-1.IQ3_XS.gguf b/neural-chat-7b-v3-1.IQ3_XS.gguf new file mode 100644 index 0000000..2336f2e --- /dev/null +++ b/neural-chat-7b-v3-1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60570af0fe5704f1d25929e497d21241c9c34f05794159106e99a372ed87a5b7 +size 3173439104 diff --git a/neural-chat-7b-v3-1.IQ4_XS.gguf b/neural-chat-7b-v3-1.IQ4_XS.gguf new file mode 100644 index 0000000..8ff637f --- /dev/null +++ b/neural-chat-7b-v3-1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5b3bbc5e7cb1b108632207f23fd89f148e9b5970be29484ec9f2a605676fd4 +size 4099012224 diff --git a/neural-chat-7b-v3-1.Q2_K.gguf b/neural-chat-7b-v3-1.Q2_K.gguf new file mode 100644 index 0000000..e18e285 --- /dev/null +++ b/neural-chat-7b-v3-1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7239e3117a4c1747103c9af4609344cc63f99f66aa906585bffde32c8c7a3a +size 2873865856 diff --git a/neural-chat-7b-v3-1.Q3_K_L.gguf b/neural-chat-7b-v3-1.Q3_K_L.gguf new file mode 100644 index 0000000..f70c9d0 --- /dev/null +++ b/neural-chat-7b-v3-1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1016b1b80e4d2c686d3997b8c89a2b92422b8577f504c114efa72d709f03870a +size 3976648320 diff --git a/neural-chat-7b-v3-1.Q3_K_M.gguf b/neural-chat-7b-v3-1.Q3_K_M.gguf new file mode 100644 index 0000000..176c11a --- /dev/null +++ b/neural-chat-7b-v3-1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846dc0a139c202c21811140e71fef3936a695b30bf043c42e09a08f772911f90 +size 3673609856 diff --git a/neural-chat-7b-v3-1.Q3_K_S.gguf b/neural-chat-7b-v3-1.Q3_K_S.gguf new file mode 100644 index 0000000..a032ab0 --- /dev/null +++ b/neural-chat-7b-v3-1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b96cfc87f4f86b542bb619f2d185781129132b5b2216b7adcf7db63973908ec +size 3319191168 diff --git a/neural-chat-7b-v3-1.Q4_K_M.gguf b/neural-chat-7b-v3-1.Q4_K_M.gguf new file mode 100644 index 0000000..fc12096 --- /dev/null +++ b/neural-chat-7b-v3-1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65332c5aee2e8e06c4e5e0cfc4f2e1216d73a05ba07480bd8466817e7d77d8f +size 4523062912 diff --git a/neural-chat-7b-v3-1.Q4_K_S.gguf b/neural-chat-7b-v3-1.Q4_K_S.gguf new file mode 100644 index 0000000..194503d --- /dev/null +++ b/neural-chat-7b-v3-1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07c5e9f46984172955029561f24224dd3501d503381ec3c68b3acdc63ddf198 +size 4294997632 diff --git a/neural-chat-7b-v3-1.Q5_K_M.gguf b/neural-chat-7b-v3-1.Q5_K_M.gguf new file mode 100644 index 0000000..f3b970f --- /dev/null +++ b/neural-chat-7b-v3-1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a54506ca11c2d170b4494ae839c1af7518711ab881f35b5d5af0a76de8c1d0b +size 5286033024 diff --git a/neural-chat-7b-v3-1.Q5_K_S.gguf b/neural-chat-7b-v3-1.Q5_K_S.gguf new file mode 100644 index 0000000..1592856 --- /dev/null +++ b/neural-chat-7b-v3-1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8a9b4b957088cdf90379ffe01fee0283adc57912f4794fdaf858f9695df2a9 +size 5152339584 diff --git a/neural-chat-7b-v3-1.Q6_K.gguf b/neural-chat-7b-v3-1.Q6_K.gguf new file mode 100644 index 0000000..1beee01 --- /dev/null +++ b/neural-chat-7b-v3-1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457dc4ad07c8c9cf32d047506e841dbcfef50188b75977c482e790de84b6e979 +size 6096688768 diff --git a/neural-chat-7b-v3-1.Q8_0.gguf b/neural-chat-7b-v3-1.Q8_0.gguf new file mode 100644 index 0000000..745ef7e --- /dev/null +++ b/neural-chat-7b-v3-1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc43ae05cd31282b3f158b6f2c0f04dc02bdc183ecad9abb5abffad01ae61e8 +size 7818737280