commit a177e240a73eca3e6de7c783c361e23ae2f11f6c Author: ModelHub XC Date: Tue Jun 2 12:08:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Conn-1.0-4K-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dcd2ab4 --- /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 +Conn-1.0-4K-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Conn-1.0-4K-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Conn-1.0-4K-Chat.IQ3_M.gguf b/Conn-1.0-4K-Chat.IQ3_M.gguf new file mode 100644 index 0000000..a8f44a0 --- /dev/null +++ b/Conn-1.0-4K-Chat.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4e936ebfe371eadc2f1fa5ea74e14e107a1f48591d7ebb618a43bcb864ee90 +size 1855599744 diff --git a/Conn-1.0-4K-Chat.IQ3_S.gguf b/Conn-1.0-4K-Chat.IQ3_S.gguf new file mode 100644 index 0000000..c4a67b3 --- /dev/null +++ b/Conn-1.0-4K-Chat.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3788ef2e12bb57564a912fb86db239187f717f37bb6b2f953e8755e5dcb4697b +size 1681798272 diff --git a/Conn-1.0-4K-Chat.IQ3_XS.gguf b/Conn-1.0-4K-Chat.IQ3_XS.gguf new file mode 100644 index 0000000..eb69cb9 --- /dev/null +++ b/Conn-1.0-4K-Chat.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83e047bebed96162cf30b0fb45079e7b57fca02ae520aef36ecc8c85c06abd0 +size 1625175168 diff --git a/Conn-1.0-4K-Chat.IQ4_XS.gguf b/Conn-1.0-4K-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..f1b389b --- /dev/null +++ b/Conn-1.0-4K-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d514d3b146f0e6ad105681109b6be31cd2ca2b02c403d05d8168c292899015 +size 2075581056 diff --git a/Conn-1.0-4K-Chat.Q2_K.gguf b/Conn-1.0-4K-Chat.Q2_K.gguf new file mode 100644 index 0000000..2d93629 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e804d299e4bd4853a3c552fb549916a39c737f254d2606c310231efdc382b2 +size 1416203904 diff --git a/Conn-1.0-4K-Chat.Q3_K_L.gguf b/Conn-1.0-4K-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..df322e3 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1dadba4e5e13d63896187b5774d5b4228d1e3cad16744eea47e69816766336f +size 2087597184 diff --git a/Conn-1.0-4K-Chat.Q3_K_M.gguf b/Conn-1.0-4K-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..b56c758 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e74f544cfc985d08a2351bb56dcbbb8f3fb705139c3b8a3da2fdb103f52558 +size 1955476608 diff --git a/Conn-1.0-4K-Chat.Q3_K_S.gguf b/Conn-1.0-4K-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..372e379 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:268fa7d41708d695293a3209750cd6ee0be5954d07453ac3d1363fc8e869de77 +size 1681798272 diff --git a/Conn-1.0-4K-Chat.Q4_K_M.gguf b/Conn-1.0-4K-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..cd26c09 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe76cd86db290f857ff13a622cb7aee84b66efac29fd4924bb4d1cf217d90a4 +size 2393232000 diff --git a/Conn-1.0-4K-Chat.Q4_K_S.gguf b/Conn-1.0-4K-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..5702944 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb31dcbfddba27a59ad6a634db7488625e62935c3c094dc1c88601aa53a04d64 +size 2188759680 diff --git a/Conn-1.0-4K-Chat.Q5_K_M.gguf b/Conn-1.0-4K-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..476645b --- /dev/null +++ b/Conn-1.0-4K-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef7f4b3dc1f8c9bf352bf68b021a63e2a74c159dd9de98aa9d9d0446a02b24b +size 2815275648 diff --git a/Conn-1.0-4K-Chat.Q5_K_S.gguf b/Conn-1.0-4K-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..983ba09 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a693bc51d218f71d596d9b134ae339ee0245543f775b5fb730b3339c265138f7 +size 2641474176 diff --git a/Conn-1.0-4K-Chat.Q6_K.gguf b/Conn-1.0-4K-Chat.Q6_K.gguf new file mode 100644 index 0000000..9879ca0 --- /dev/null +++ b/Conn-1.0-4K-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37931e8f8247c843d28445d2a33bc30f3b316ac6c6a4acab0b8af3651531e4b +size 3135852672 diff --git a/Conn-1.0-4K-Chat.Q8_0.gguf b/Conn-1.0-4K-Chat.Q8_0.gguf new file mode 100644 index 0000000..8b2494a --- /dev/null +++ b/Conn-1.0-4K-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2440ad114d853fd5dd0d39ccbfc2082f18f6e10095d4d5f00ad1572780b13d2 +size 4061222016 diff --git a/Conn-1.0-4K-Chat.f16.gguf b/Conn-1.0-4K-Chat.f16.gguf new file mode 100644 index 0000000..48d9f82 --- /dev/null +++ b/Conn-1.0-4K-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1baea1bfb0717860a845e06fe20dea03e31ef5a7f75354c2b464652eac55daf3 +size 7643296896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a91374 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Enderchef/ICONN +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- chatbot +- instruct +- CONN +--- +## About + + + + + + +static quants of https://huggingface.co/Enderchef/ICONN + + +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/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.IQ3_XS.gguf) | IQ3_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.IQ3_S.gguf) | IQ3_S | 1.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.IQ3_M.gguf) | IQ3_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Conn-1.0-4K-Chat-GGUF/resolve/main/Conn-1.0-4K-Chat.f16.gguf) | f16 | 7.7 | 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. + +