commit 7a2cbec058b009d1faf0bccfaff4d9ee25bbbf8c Author: ModelHub XC Date: Fri Jun 19 03:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neural-chat-7b-v3-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f339c0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-v3-3.f16.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..44cf3a6 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Intel/neural-chat-7b-v3-3 +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-v3-3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/neural-chat-7b-v3-3-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-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-GGUF/resolve/main/neural-chat-7b-v3-3.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-v3-3.IQ3_M.gguf b/neural-chat-7b-v3-3.IQ3_M.gguf new file mode 100644 index 0000000..c731828 --- /dev/null +++ b/neural-chat-7b-v3-3.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e815d1dfbbbe84efdff0e7d421166d70e84f64c071b12a306296732c3ec38081 +size 3284893536 diff --git a/neural-chat-7b-v3-3.IQ3_S.gguf b/neural-chat-7b-v3-3.IQ3_S.gguf new file mode 100644 index 0000000..dffd96c --- /dev/null +++ b/neural-chat-7b-v3-3.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a6055cc337932d4844d149157e762942a81a393f30facd2dbfe3a583cde32 +size 3182395232 diff --git a/neural-chat-7b-v3-3.IQ3_XS.gguf b/neural-chat-7b-v3-3.IQ3_XS.gguf new file mode 100644 index 0000000..54d679a --- /dev/null +++ b/neural-chat-7b-v3-3.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd7098021225bbb0c31879e4a7af77c0c2a82803f30c148a88c4badd2981379 +size 3018817376 diff --git a/neural-chat-7b-v3-3.IQ4_XS.gguf b/neural-chat-7b-v3-3.IQ4_XS.gguf new file mode 100644 index 0000000..9444aa1 --- /dev/null +++ b/neural-chat-7b-v3-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d01cd88a5254d1846931b331828cf68f4f5f1674d692135443a000e182584d1 +size 3944390496 diff --git a/neural-chat-7b-v3-3.Q2_K.gguf b/neural-chat-7b-v3-3.Q2_K.gguf new file mode 100644 index 0000000..ea0914e --- /dev/null +++ b/neural-chat-7b-v3-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:269e0931b51350cd8537d058f62c62fda70be0ecedc0a587c11903b5db24bd24 +size 2719244128 diff --git a/neural-chat-7b-v3-3.Q3_K_L.gguf b/neural-chat-7b-v3-3.Q3_K_L.gguf new file mode 100644 index 0000000..800c17d --- /dev/null +++ b/neural-chat-7b-v3-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884863d19e24d7a969733d9a1f6ac2aac176d35f3cc935bf29135cb5fde20c6d +size 3822026592 diff --git a/neural-chat-7b-v3-3.Q3_K_M.gguf b/neural-chat-7b-v3-3.Q3_K_M.gguf new file mode 100644 index 0000000..634207d --- /dev/null +++ b/neural-chat-7b-v3-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5f28f215ad37671eaacea6b6137c90e0f4483c81a80154eb23894a47a62da7 +size 3518988128 diff --git a/neural-chat-7b-v3-3.Q3_K_S.gguf b/neural-chat-7b-v3-3.Q3_K_S.gguf new file mode 100644 index 0000000..2b3a5fa --- /dev/null +++ b/neural-chat-7b-v3-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273a6d2aa30ab95b86d107303a36809a83c7c77dc11c8f1b91cab26ef2e7b013 +size 3164569440 diff --git a/neural-chat-7b-v3-3.Q4_K_M.gguf b/neural-chat-7b-v3-3.Q4_K_M.gguf new file mode 100644 index 0000000..e21fc70 --- /dev/null +++ b/neural-chat-7b-v3-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9c0291bef5ec7bfd9456aba62ed51a9529ededab2b56a88f83eae27db6c9a2 +size 4368441184 diff --git a/neural-chat-7b-v3-3.Q4_K_S.gguf b/neural-chat-7b-v3-3.Q4_K_S.gguf new file mode 100644 index 0000000..2cdcaf2 --- /dev/null +++ b/neural-chat-7b-v3-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a923295c87c7e6c8e16517e4c938c314a6e660338a42922d544a996e62cde1b6 +size 4140375904 diff --git a/neural-chat-7b-v3-3.Q5_K_M.gguf b/neural-chat-7b-v3-3.Q5_K_M.gguf new file mode 100644 index 0000000..d3158db --- /dev/null +++ b/neural-chat-7b-v3-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfbc8d1bc0347671f49bfba9ca2f73ce13f45bcef7c71706f4a1fed0bd5dd38 +size 5131411296 diff --git a/neural-chat-7b-v3-3.Q5_K_S.gguf b/neural-chat-7b-v3-3.Q5_K_S.gguf new file mode 100644 index 0000000..2bd8b7a --- /dev/null +++ b/neural-chat-7b-v3-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94eef62d7b275f1b26a0133e5a51eebfabb04faca54cb1c45860e3913626dc5 +size 4997717856 diff --git a/neural-chat-7b-v3-3.Q6_K.gguf b/neural-chat-7b-v3-3.Q6_K.gguf new file mode 100644 index 0000000..72bb3e5 --- /dev/null +++ b/neural-chat-7b-v3-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b818ca3596ba1284d45f0a3597b4feea57a6ff7b1b908d8a5975855ab85e01e +size 5942067040 diff --git a/neural-chat-7b-v3-3.Q8_0.gguf b/neural-chat-7b-v3-3.Q8_0.gguf new file mode 100644 index 0000000..c4a5355 --- /dev/null +++ b/neural-chat-7b-v3-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ec827dd9f71f9b61cf46d7ea09d3133c51d5c8fecfe218fb185f594b051f37 +size 7695859552 diff --git a/neural-chat-7b-v3-3.f16.gguf b/neural-chat-7b-v3-3.f16.gguf new file mode 100644 index 0000000..699ecc2 --- /dev/null +++ b/neural-chat-7b-v3-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff7cd76b697eb28aaabd451dd76241a634326a181c0cb28a6f70385ec5475f9 +size 14484733792