commit 1111bc0b254b45cf573b8a9715b52c0fd0b181fe Author: ModelHub XC Date: Fri Jun 19 03:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neural-chat-7b-v3-2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9ab2b2f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..358ab62 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +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 + + + + + + +weighted/imatrix quants of https://huggingface.co/Intel/neural-chat-7b-v3-2 + + +static quants are available at https://huggingface.co/mradermacher/neural-chat-7b-v3-2-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-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-2-i1-GGUF/resolve/main/neural-chat-7b-v3-2.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1811505 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f69fda7803a65a64f76136e5b74b7a80afd4ca24c9bf6ad6b44f466b482aac1 +size 4988157 diff --git a/neural-chat-7b-v3-2.i1-IQ1_M.gguf b/neural-chat-7b-v3-2.i1-IQ1_M.gguf new file mode 100644 index 0000000..bc4f8b8 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4516d0c7bf06cc879049ae921b69c1fc6d04be6a7e76221579909e7c154e3a43 +size 1754446656 diff --git a/neural-chat-7b-v3-2.i1-IQ1_S.gguf b/neural-chat-7b-v3-2.i1-IQ1_S.gguf new file mode 100644 index 0000000..a2913c5 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff00d9a3adb42ff1fff7a90a1d44562f862c4f94b04f499777e6e1e411d0f1f7 +size 1612102464 diff --git a/neural-chat-7b-v3-2.i1-IQ2_M.gguf b/neural-chat-7b-v3-2.i1-IQ2_M.gguf new file mode 100644 index 0000000..c1951f6 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1194ec23ee647f625958eaea4a44860222069e8331849d8935d9ad029a57be +size 2500713280 diff --git a/neural-chat-7b-v3-2.i1-IQ2_S.gguf b/neural-chat-7b-v3-2.i1-IQ2_S.gguf new file mode 100644 index 0000000..20bbf66 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15894fa894f2b1e9af95cc047aa6360226340c0700eaee34ee5d3ee4380d6bf +size 2310921024 diff --git a/neural-chat-7b-v3-2.i1-IQ2_XS.gguf b/neural-chat-7b-v3-2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5210afc --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754143f8e618947a892483c30c1bcf937da7cf3b562b403fbd4bbbb0ddd15305 +size 2198256448 diff --git a/neural-chat-7b-v3-2.i1-IQ2_XXS.gguf b/neural-chat-7b-v3-2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ba08e54 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a86db032de9629e2597ded3985959ce4f5d16f4a0145ef5a97da1ba5b3ce169 +size 1991686976 diff --git a/neural-chat-7b-v3-2.i1-IQ3_M.gguf b/neural-chat-7b-v3-2.i1-IQ3_M.gguf new file mode 100644 index 0000000..f4703cb --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b33ee6a9e9dfb51b3d087910422ad90a6d91e0730ee1144249ba2d7cc4e1233 +size 3284892480 diff --git a/neural-chat-7b-v3-2.i1-IQ3_S.gguf b/neural-chat-7b-v3-2.i1-IQ3_S.gguf new file mode 100644 index 0000000..7799ccb --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba1f083370ffc7871ff01d501e15f3169c585182731d82d704064997fd2a138 +size 3182394176 diff --git a/neural-chat-7b-v3-2.i1-IQ3_XS.gguf b/neural-chat-7b-v3-2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ac93730 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7e12504e4ad64eb080e7f10adacd4ff85917375a9ccbd7c4dacf6b2e8a1c35 +size 3018816320 diff --git a/neural-chat-7b-v3-2.i1-IQ3_XXS.gguf b/neural-chat-7b-v3-2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ff1b55c --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42716ce631585c747588221162343fa1deb207c33bf4e29db3292f07b7acfade +size 2827344704 diff --git a/neural-chat-7b-v3-2.i1-IQ4_XS.gguf b/neural-chat-7b-v3-2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ceb62d1 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beedeaed188522e4bb386871fc928fd5dae223b6c730e9f78dd6edeb973429e4 +size 3907689280 diff --git a/neural-chat-7b-v3-2.i1-Q2_K.gguf b/neural-chat-7b-v3-2.i1-Q2_K.gguf new file mode 100644 index 0000000..885db69 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97f3f55f1274b82e90a05120594ae6826a90c06f39499df042c354e3946d275 +size 2719243072 diff --git a/neural-chat-7b-v3-2.i1-Q3_K_L.gguf b/neural-chat-7b-v3-2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0bb145f --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f952e3af5d2779fcb6b4cf594280859b7e6c7261c281312dcef6eec45b7dd4 +size 3822025536 diff --git a/neural-chat-7b-v3-2.i1-Q3_K_M.gguf b/neural-chat-7b-v3-2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..edf6b31 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501177f14b562bc126f58f03f4070f2d07f738df571c3b1368e1fe78a4ef444e +size 3518987072 diff --git a/neural-chat-7b-v3-2.i1-Q3_K_S.gguf b/neural-chat-7b-v3-2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..15ac74c --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2732b3317a013b3e35ff959661edd8b5213e3643438ea036d56eec2829f9a109 +size 3164568384 diff --git a/neural-chat-7b-v3-2.i1-Q4_0.gguf b/neural-chat-7b-v3-2.i1-Q4_0.gguf new file mode 100644 index 0000000..04b9d8b --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52249757637d688fb50ff9a21f37b27656c815dcca31f855c024ed423223ac9e +size 4123597632 diff --git a/neural-chat-7b-v3-2.i1-Q4_0_4_4.gguf b/neural-chat-7b-v3-2.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..9de9a14 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b421a5aa457df4e729d0332b718032003c7b4a8dd9c0f953ba56f5bde50ed59e +size 4108917568 diff --git a/neural-chat-7b-v3-2.i1-Q4_0_4_8.gguf b/neural-chat-7b-v3-2.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..8b68677 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebd588bab206ed45ab1442c6babe6d550161d37299a2c01d793ff31ef0f2b8d +size 4108917568 diff --git a/neural-chat-7b-v3-2.i1-Q4_0_8_8.gguf b/neural-chat-7b-v3-2.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..09a0873 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce666aa56b470e0993d6ea557f0f91d9d0d1355146a7859993857a5e1c37d4ef +size 4108917568 diff --git a/neural-chat-7b-v3-2.i1-Q4_K_M.gguf b/neural-chat-7b-v3-2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7d3e1ac --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad61af866e168f14d442eeecf0f6d961e2d3de129e5f871e72b4eec9d4725d7 +size 4368440128 diff --git a/neural-chat-7b-v3-2.i1-Q4_K_S.gguf b/neural-chat-7b-v3-2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..45c93a1 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:603663b0d4069c0e0cf22d1e8b900b47aed6664f198d37b95d09dc3a8e207d85 +size 4140374848 diff --git a/neural-chat-7b-v3-2.i1-Q5_K_M.gguf b/neural-chat-7b-v3-2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..617a406 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec002489ffdce0c7903944c0008b983bd57e61a700aded6d494340f689a9dc4 +size 5131410240 diff --git a/neural-chat-7b-v3-2.i1-Q5_K_S.gguf b/neural-chat-7b-v3-2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2eb168e --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c0ebe292205e6ccec1c6c628732f23d5cc7b86c853f6282835f84e944cad82 +size 4997716800 diff --git a/neural-chat-7b-v3-2.i1-Q6_K.gguf b/neural-chat-7b-v3-2.i1-Q6_K.gguf new file mode 100644 index 0000000..bfd9ce1 --- /dev/null +++ b/neural-chat-7b-v3-2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b69c22834c6a3ccdb1e9ca9299b579ea9547a1c63d66919d044e4fa8b7cffe +size 5942065984