commit bb6435c206d1635ed09dad414cd4fb6a89dcd286 Author: ModelHub XC Date: Tue Jun 2 12:18:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Chihiro-7B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c301b32 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Chihiro-7B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chihiro-7B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Chihiro-7B-v0.1.IQ4_XS.gguf b/Chihiro-7B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..d70579b --- /dev/null +++ b/Chihiro-7B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa0d30e7feabce6b38e4283b8765eb7442aad669c3d519849dca3f178242d65 +size 4110404128 diff --git a/Chihiro-7B-v0.1.Q2_K.gguf b/Chihiro-7B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..18da9f5 --- /dev/null +++ b/Chihiro-7B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3612259c3e7df970c688da113445cacd445706a67016b8e8123da523b74abd99 +size 2860401760 diff --git a/Chihiro-7B-v0.1.Q3_K_L.gguf b/Chihiro-7B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..95b3449 --- /dev/null +++ b/Chihiro-7B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005661f37059c2c64062b73f9d4573535a3b402fed9f572d6f1d7b97635fa94b +size 3975612224 diff --git a/Chihiro-7B-v0.1.Q3_K_M.gguf b/Chihiro-7B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..8d212b7 --- /dev/null +++ b/Chihiro-7B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe600fec1963596e3ec3a81a68ffba3d8b6148ebe59ad482404bcb23e2d9d0b +size 3672573760 diff --git a/Chihiro-7B-v0.1.Q3_K_S.gguf b/Chihiro-7B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..aaf09e9 --- /dev/null +++ b/Chihiro-7B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23218a31638fa585b28864d676afb4e3f9df94ab0085cddd641f5ea7b8ec955c +size 3318155072 diff --git a/Chihiro-7B-v0.1.Q4_K_M.gguf b/Chihiro-7B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..7b41b56 --- /dev/null +++ b/Chihiro-7B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbdd434656bc1b5f5500f6b0092220c9c76ce5b54bc4fe498bdf433297db4b19 +size 4538278816 diff --git a/Chihiro-7B-v0.1.Q4_K_S.gguf b/Chihiro-7B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..3b5d028 --- /dev/null +++ b/Chihiro-7B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5d12fe70b1150190baa79390568eb247ca02c8e2a6170c931c6d38dde16071 +size 4310213536 diff --git a/Chihiro-7B-v0.1.Q5_K_M.gguf b/Chihiro-7B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..7279213 --- /dev/null +++ b/Chihiro-7B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71bf6c5b83049e36875b4342f0ba55bc7c005ceb3163c3fe76c9060353416e1 +size 5316544928 diff --git a/Chihiro-7B-v0.1.Q5_K_S.gguf b/Chihiro-7B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..d5e76ad --- /dev/null +++ b/Chihiro-7B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2464c6d042a7f9e36557664f384702ffb1a3450423e07dcc7f49d41ce1d231d +size 5182851488 diff --git a/Chihiro-7B-v0.1.Q6_K.gguf b/Chihiro-7B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..26a8a72 --- /dev/null +++ b/Chihiro-7B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f885865301e636372c4f26fe80c7dc8c92351911920a359f0fcca4daa3246d +size 6143452672 diff --git a/Chihiro-7B-v0.1.Q8_0.gguf b/Chihiro-7B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..9982a96 --- /dev/null +++ b/Chihiro-7B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7266b8eb01c7259f18aa6ed4101c8584b56b3373f5bd768e6436811fa91c3a5 +size 7956517184 diff --git a/Chihiro-7B-v0.1.f16.gguf b/Chihiro-7B-v0.1.f16.gguf new file mode 100644 index 0000000..8c533bf --- /dev/null +++ b/Chihiro-7B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ced7c6daa2008d4202ae3b140ea159ee6c56ea3161e73dc87df73842377882 +size 14974831424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..468b511 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: yuuko-eth/Chihiro-7B-v0.1 +language: +- zh +- en +library_name: transformers +license: unknown +model_name: Chihiro-7B-v0.1 +prompt_template: SYS_PROMPT [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST] +quantized_by: mradermacher +tags: +- nlp +- chinese +- mistral +- traditional_chinese +- merge +- mergekit +- MediaTek-Research/Breeze-7B-Instruct-v0_1 +- mlabonne/Zebrafish-7B +--- +## About + + + + + + +static quants of https://huggingface.co/yuuko-eth/Chihiro-7B-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Chihiro-7B-v0.1-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/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q6_K.gguf) | Q6_K | 6.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Chihiro-7B-v0.1-GGUF/resolve/main/Chihiro-7B-v0.1.f16.gguf) | f16 | 15.1 | 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. + +