commit f97d10a46496b1bc33dae982b8534a50a736d3bd Author: ModelHub XC Date: Thu Jun 11 01:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Chikuma_10.7B_v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f644215 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Chikuma_10.7B_v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Chikuma_10.7B_v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Chikuma_10.7B_v2.IQ4_XS.gguf b/Chikuma_10.7B_v2.IQ4_XS.gguf new file mode 100644 index 0000000..9eda110 --- /dev/null +++ b/Chikuma_10.7B_v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182443d0b15be0b9d708d3913a38d37a51a8d53e2104b12f13e14ab35962e95c +size 5827652448 diff --git a/Chikuma_10.7B_v2.Q2_K.gguf b/Chikuma_10.7B_v2.Q2_K.gguf new file mode 100644 index 0000000..15a0c7a --- /dev/null +++ b/Chikuma_10.7B_v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062d26168736c9b8760476826927fdaf0090b396dbf080498a18b6aefad0d3b6 +size 4003243232 diff --git a/Chikuma_10.7B_v2.Q3_K_L.gguf b/Chikuma_10.7B_v2.Q3_K_L.gguf new file mode 100644 index 0000000..d5410b3 --- /dev/null +++ b/Chikuma_10.7B_v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d660a49f7a1ca73d75d3a9803575ec7fcbb299662b89b7f735358790aea8783 +size 5650761760 diff --git a/Chikuma_10.7B_v2.Q3_K_M.gguf b/Chikuma_10.7B_v2.Q3_K_M.gguf new file mode 100644 index 0000000..42e3dbc --- /dev/null +++ b/Chikuma_10.7B_v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e146065d898a2f7cf4b35c479c288e5d2b75091f640aa47a343880369cd1bc3 +size 5195679776 diff --git a/Chikuma_10.7B_v2.Q3_K_S.gguf b/Chikuma_10.7B_v2.Q3_K_S.gguf new file mode 100644 index 0000000..f26c7fa --- /dev/null +++ b/Chikuma_10.7B_v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0efeaf6725661d40d5c4c062f9d9692a3fa8b1446ffb148b7b6aafb4298d4299 +size 4664576032 diff --git a/Chikuma_10.7B_v2.Q4_0_4_4.gguf b/Chikuma_10.7B_v2.Q4_0_4_4.gguf new file mode 100644 index 0000000..67e5eab --- /dev/null +++ b/Chikuma_10.7B_v2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b54c3b48f7b13647abb72db36cf3f34c86dfa58c1800ec29e9a2a0145b79b120 +size 6072396896 diff --git a/Chikuma_10.7B_v2.Q4_K_M.gguf b/Chikuma_10.7B_v2.Q4_K_M.gguf new file mode 100644 index 0000000..e169f8f --- /dev/null +++ b/Chikuma_10.7B_v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1fb49d21bf62301135dad36a287f218182fae6fd456706cb7aff2f6a91e5d05 +size 6461680736 diff --git a/Chikuma_10.7B_v2.Q4_K_S.gguf b/Chikuma_10.7B_v2.Q4_K_S.gguf new file mode 100644 index 0000000..021f1da --- /dev/null +++ b/Chikuma_10.7B_v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f74223230310dda63c7f8c37837f42d9d03c3e7f2343f8c1721872032c6caa0 +size 6118534240 diff --git a/Chikuma_10.7B_v2.Q5_K_M.gguf b/Chikuma_10.7B_v2.Q5_K_M.gguf new file mode 100644 index 0000000..6a653b2 --- /dev/null +++ b/Chikuma_10.7B_v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7db91f467148293429ff56e1bddfc2dd17fd1a3a2e1c70facdb13c0339d85e7 +size 7597944928 diff --git a/Chikuma_10.7B_v2.Q5_K_S.gguf b/Chikuma_10.7B_v2.Q5_K_S.gguf new file mode 100644 index 0000000..36d2aa9 --- /dev/null +++ b/Chikuma_10.7B_v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2b931921c0a65ce439715b56256e0c66680fc5c0c14cf1feede715b3659e4e +size 7397404768 diff --git a/Chikuma_10.7B_v2.Q6_K.gguf b/Chikuma_10.7B_v2.Q6_K.gguf new file mode 100644 index 0000000..dab6966 --- /dev/null +++ b/Chikuma_10.7B_v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3faa535a4b0693dd248bb159e7b038d169e6c20455b5644b2102a4205f9603b +size 8805225632 diff --git a/Chikuma_10.7B_v2.Q8_0.gguf b/Chikuma_10.7B_v2.Q8_0.gguf new file mode 100644 index 0000000..00ef8e5 --- /dev/null +++ b/Chikuma_10.7B_v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf97b0900de300059ae45442d7b0dfb2bdce0b148dfc4ace6bca27337e38975b +size 11404174368 diff --git a/Chikuma_10.7B_v2.f16.gguf b/Chikuma_10.7B_v2.f16.gguf new file mode 100644 index 0000000..4fbd65c --- /dev/null +++ b/Chikuma_10.7B_v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f845ed6adcfcb1bc98c5d9631e2a96c345216b61ffe1a996c0219ddccf2ae0 +size 21464621088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5329316 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: sethuiyer/Chikuma_10.7B_v2 +datasets: +- argilla/distilabel-intel-orca-dpo-pairs +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/sethuiyer/Chikuma_10.7B_v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Chikuma_10.7B_v2-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/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q3_K_S.gguf) | Q3_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q3_K_L.gguf) | Q3_K_L | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.IQ4_XS.gguf) | IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q5_K_S.gguf) | Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q6_K.gguf) | Q6_K | 8.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Chikuma_10.7B_v2-GGUF/resolve/main/Chikuma_10.7B_v2.f16.gguf) | f16 | 21.6 | 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. 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. + +