commit 9a4dc7e184153397712ce5174e5aa5c72c50e9aa Author: ModelHub XC Date: Sat Jul 4 05:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Chicka-Mistral-3x7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56e9fc7 --- /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 +Chicka-Mistral-3x7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Chicka-Mistral-3x7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Chicka-Mistral-3x7b.IQ3_M.gguf b/Chicka-Mistral-3x7b.IQ3_M.gguf new file mode 100644 index 0000000..934acfb --- /dev/null +++ b/Chicka-Mistral-3x7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58353ae6e735c6908c276071cece0af3a5b48cbfb34977e3d9b3b9f537ebbda3 +size 8193289664 diff --git a/Chicka-Mistral-3x7b.IQ3_S.gguf b/Chicka-Mistral-3x7b.IQ3_S.gguf new file mode 100644 index 0000000..0326e02 --- /dev/null +++ b/Chicka-Mistral-3x7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090753d19823b53a8354f843d7db842dfeeec34951d506f1aade017ea54b387f +size 8028401088 diff --git a/Chicka-Mistral-3x7b.IQ3_XS.gguf b/Chicka-Mistral-3x7b.IQ3_XS.gguf new file mode 100644 index 0000000..e5baea0 --- /dev/null +++ b/Chicka-Mistral-3x7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f486ae0e981636bc47e87fbcde83ccaf460f0ddb61ce3c86c23697f46ed3bd38 +size 7600582080 diff --git a/Chicka-Mistral-3x7b.IQ4_XS.gguf b/Chicka-Mistral-3x7b.IQ4_XS.gguf new file mode 100644 index 0000000..7b3ee8e --- /dev/null +++ b/Chicka-Mistral-3x7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451373473a1d8ec6d9d4e4bee8a7b5b683df5b44b747a5750ae109c8ba20ab1f +size 10008842496 diff --git a/Chicka-Mistral-3x7b.Q2_K.gguf b/Chicka-Mistral-3x7b.Q2_K.gguf new file mode 100644 index 0000000..f411de0 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd53ae7865a7e08a1e6753c43e03ff1cbb0ee2c95792620dac9482c83bac4ba1 +size 6801885824 diff --git a/Chicka-Mistral-3x7b.Q3_K_L.gguf b/Chicka-Mistral-3x7b.Q3_K_L.gguf new file mode 100644 index 0000000..0b52e14 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbf33aa7acd88d56fab111e204381e40f9a57fd5fcc0bb208ba90d27980f736 +size 9636916672 diff --git a/Chicka-Mistral-3x7b.Q3_K_M.gguf b/Chicka-Mistral-3x7b.Q3_K_M.gguf new file mode 100644 index 0000000..da3e391 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1873a562a8cb5b204b5512f83d002925a56440bb48cdbffbaad893efb2c185 +size 8893476288 diff --git a/Chicka-Mistral-3x7b.Q3_K_S.gguf b/Chicka-Mistral-3x7b.Q3_K_S.gguf new file mode 100644 index 0000000..3a905d6 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ceaf2f506de238570a749aecd080bcd851075d63f6b79d3feb69d55306dae0 +size 8010575296 diff --git a/Chicka-Mistral-3x7b.Q4_K_M.gguf b/Chicka-Mistral-3x7b.Q4_K_M.gguf new file mode 100644 index 0000000..38d0aaa --- /dev/null +++ b/Chicka-Mistral-3x7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe0bf2f7aa0a01c4693d86c389b5493390d3d049e49171be0c1c52024cce40a +size 11196256768 diff --git a/Chicka-Mistral-3x7b.Q4_K_S.gguf b/Chicka-Mistral-3x7b.Q4_K_S.gguf new file mode 100644 index 0000000..12287a5 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce2de1502c503d6fe4544140c52ea74f12a971f0559ef82bf99cb509a0a1fc1 +size 10542469632 diff --git a/Chicka-Mistral-3x7b.Q5_K_M.gguf b/Chicka-Mistral-3x7b.Q5_K_M.gguf new file mode 100644 index 0000000..468fa7a --- /dev/null +++ b/Chicka-Mistral-3x7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad50d295c06d78086c950e0938d5bdd1d1c49c6179843673d8bdb3ab28584d4 +size 13133633024 diff --git a/Chicka-Mistral-3x7b.Q5_K_S.gguf b/Chicka-Mistral-3x7b.Q5_K_S.gguf new file mode 100644 index 0000000..f7e2b6b --- /dev/null +++ b/Chicka-Mistral-3x7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694398a5d7bd221b136f338db1c81e069694ad792183d5e27f73fe5b499e50c4 +size 12750378496 diff --git a/Chicka-Mistral-3x7b.Q6_K.gguf b/Chicka-Mistral-3x7b.Q6_K.gguf new file mode 100644 index 0000000..2b88af0 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c082ba836baf0705339846ff66395f5710facda19819105a01067ae23237250 +size 15192095296 diff --git a/Chicka-Mistral-3x7b.Q8_0.gguf b/Chicka-Mistral-3x7b.Q8_0.gguf new file mode 100644 index 0000000..19e5a63 --- /dev/null +++ b/Chicka-Mistral-3x7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3896cc54ee2452b22de7f46c5de84816ae750172af35128bcd072a4340f7f97 +size 19676383680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b15622 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Chickaboo/Chicka-Mixtral-3x7b +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- merge +- mergekit +- mistral +- moe +- conversational +- chicka +--- +## About + + + + + +static quants of https://huggingface.co/Chickaboo/Chicka-Mixtral-3x7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-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/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q2_K.gguf) | Q2_K | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.IQ3_XS.gguf) | IQ3_XS | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q3_K_S.gguf) | Q3_K_S | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.IQ3_S.gguf) | IQ3_S | 8.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.IQ3_M.gguf) | IQ3_M | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q3_K_M.gguf) | Q3_K_M | 9.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q3_K_L.gguf) | Q3_K_L | 9.7 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.IQ4_XS.gguf) | IQ4_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q4_K_S.gguf) | Q4_K_S | 10.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q4_K_M.gguf) | Q4_K_M | 11.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q5_K_S.gguf) | Q5_K_S | 12.9 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q5_K_M.gguf) | Q5_K_M | 13.2 | | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q6_K.gguf) | Q6_K | 15.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Chicka-Mistral-3x7b-GGUF/resolve/main/Chicka-Mistral-3x7b.Q8_0.gguf) | Q8_0 | 19.8 | 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. + +