commit 203e5824ea3bc6192bda82853c0cc7aa2bb4286a Author: ModelHub XC Date: Tue Jul 7 18:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1dac249 --- /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 +BI-Llama-8layers-SGR-Dolci.f16.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BI-Llama-8layers-SGR-Dolci.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BI-Llama-8layers-SGR-Dolci.IQ4_XS.gguf b/BI-Llama-8layers-SGR-Dolci.IQ4_XS.gguf new file mode 100644 index 0000000..aa5bbd3 --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d749ef1810821684f3456ef4280e19f0e5abce3d11178a0f20998908acb5b9 +size 3542742624 diff --git a/BI-Llama-8layers-SGR-Dolci.Q2_K.gguf b/BI-Llama-8layers-SGR-Dolci.Q2_K.gguf new file mode 100644 index 0000000..0edc5bb --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b991463f7ac2fe93b0b73bd08fba860061cffc86bfbf51de789de84a9b2e2dca +size 2537141856 diff --git a/BI-Llama-8layers-SGR-Dolci.Q3_K_L.gguf b/BI-Llama-8layers-SGR-Dolci.Q3_K_L.gguf new file mode 100644 index 0000000..2fd4133 --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b9920d4dc2315e6cce11367e32d264c7bd3c27f8f802fef33462e87c2f1cd5 +size 3407599200 diff --git a/BI-Llama-8layers-SGR-Dolci.Q3_K_M.gguf b/BI-Llama-8layers-SGR-Dolci.Q3_K_M.gguf new file mode 100644 index 0000000..29dc1fd --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a8d8963e41ac834c29b7fd30975e7216ffc67850287a3fcb582861b45e1db9 +size 3176912480 diff --git a/BI-Llama-8layers-SGR-Dolci.Q3_K_S.gguf b/BI-Llama-8layers-SGR-Dolci.Q3_K_S.gguf new file mode 100644 index 0000000..b675c6e --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4cd2ee1dc06e41f7b78a63480954daadc34f09135aae53e0453ba3bdf78d31 +size 2914506336 diff --git a/BI-Llama-8layers-SGR-Dolci.Q4_K_M.gguf b/BI-Llama-8layers-SGR-Dolci.Q4_K_M.gguf new file mode 100644 index 0000000..b54df3a --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da86a122c8ce2084e5b6b01d284ad41636aeca5199aaee7c32db1f8616157b3f +size 3874125408 diff --git a/BI-Llama-8layers-SGR-Dolci.Q4_K_S.gguf b/BI-Llama-8layers-SGR-Dolci.Q4_K_S.gguf new file mode 100644 index 0000000..2ca645b --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f325c332d02c193044d437a990523dbf8b125102626707281f05a8a3ce6c64 +size 3703600736 diff --git a/BI-Llama-8layers-SGR-Dolci.Q5_K_M.gguf b/BI-Llama-8layers-SGR-Dolci.Q5_K_M.gguf new file mode 100644 index 0000000..c3f9412 --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fe51dc699977ef59842eb1f162cf6ca804bbcddabaf296d3c204b570f4ce50 +size 4499732064 diff --git a/BI-Llama-8layers-SGR-Dolci.Q5_K_S.gguf b/BI-Llama-8layers-SGR-Dolci.Q5_K_S.gguf new file mode 100644 index 0000000..697291c --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76028fb6c536e18dac2f17483fd11ba21eb9827903b4a23dd8eb6cfc5611217e +size 4399461984 diff --git a/BI-Llama-8layers-SGR-Dolci.Q6_K.gguf b/BI-Llama-8layers-SGR-Dolci.Q6_K.gguf new file mode 100644 index 0000000..4ef90fe --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ba67778d0dc74900bc9f136a8e73ace88608b5ea068d2719ca5b8bcb22a6f5 +size 5164439136 diff --git a/BI-Llama-8layers-SGR-Dolci.Q8_0.gguf b/BI-Llama-8layers-SGR-Dolci.Q8_0.gguf new file mode 100644 index 0000000..3633599 --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec34673d778f10ea1f1f512442e1d7a18b8854e3b25f1cd6d9e34b6bec952f83 +size 6686627424 diff --git a/BI-Llama-8layers-SGR-Dolci.f16.gguf b/BI-Llama-8layers-SGR-Dolci.f16.gguf new file mode 100644 index 0000000..88ac71a --- /dev/null +++ b/BI-Llama-8layers-SGR-Dolci.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d456097cc20bdca2a36e7905a1ac8e097974746287f7b1d94d82f006a3513a9 +size 12578969184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..80d8a1b --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: safal312/BI-Llama-8layers-SGR-Dolci +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- layer-pruning +- qlora +- compression +- reasoning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/safal312/BI-Llama-8layers-SGR-Dolci + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BI-Llama-8layers-SGR-Dolci-GGUF).*** + +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/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.Q8_0.gguf) | Q8_0 | 6.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BI-Llama-8layers-SGR-Dolci-GGUF/resolve/main/BI-Llama-8layers-SGR-Dolci.f16.gguf) | f16 | 12.7 | 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. + +