commit 1d35e543dc424de38c6318c89b10793c04fbfdc5 Author: ModelHub XC Date: Tue Sep 15 08:09:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ConfTuner-LLaMA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1daddc --- /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 +ConfTuner-LLaMA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.f16.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConfTuner-LLaMA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ConfTuner-LLaMA.IQ4_XS.gguf b/ConfTuner-LLaMA.IQ4_XS.gguf new file mode 100644 index 0000000..8bdd320 --- /dev/null +++ b/ConfTuner-LLaMA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3545390ba4c7603a86d2ec30baab1241a9a35d5aa54710ecfefbe156c74cd77e +size 4484368032 diff --git a/ConfTuner-LLaMA.Q2_K.gguf b/ConfTuner-LLaMA.Q2_K.gguf new file mode 100644 index 0000000..91b4333 --- /dev/null +++ b/ConfTuner-LLaMA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d731ca037bb65cbbce429468493cc5a91d21b6ea3c2f4519e48ed58b4492b810 +size 3179136672 diff --git a/ConfTuner-LLaMA.Q3_K_L.gguf b/ConfTuner-LLaMA.Q3_K_L.gguf new file mode 100644 index 0000000..9e1964f --- /dev/null +++ b/ConfTuner-LLaMA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342d3eab92bec1a5e61e7d674b52ffacd20eec5b307377551fb0e4119838144d +size 4321961632 diff --git a/ConfTuner-LLaMA.Q3_K_M.gguf b/ConfTuner-LLaMA.Q3_K_M.gguf new file mode 100644 index 0000000..0e17421 --- /dev/null +++ b/ConfTuner-LLaMA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16da6ebb10ff4d1f4a16a42852722ceb6bd408649d17b61b6d9e7715cc760d3d +size 4018923168 diff --git a/ConfTuner-LLaMA.Q3_K_S.gguf b/ConfTuner-LLaMA.Q3_K_S.gguf new file mode 100644 index 0000000..db20e01 --- /dev/null +++ b/ConfTuner-LLaMA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206b72ced9055775f5ba419ff469276d36d868bb125e49ec5fb4018220907043 +size 3664504480 diff --git a/ConfTuner-LLaMA.Q4_K_M.gguf b/ConfTuner-LLaMA.Q4_K_M.gguf new file mode 100644 index 0000000..0396f21 --- /dev/null +++ b/ConfTuner-LLaMA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e6fd4738db0c006e1694f953163784f88969875d93a65e2c4a437d525831db6 +size 4920739488 diff --git a/ConfTuner-LLaMA.Q4_K_S.gguf b/ConfTuner-LLaMA.Q4_K_S.gguf new file mode 100644 index 0000000..224d6d5 --- /dev/null +++ b/ConfTuner-LLaMA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466eb081fbb1892a9fe54105f46f1b03b32cf45d86b819e49e1a4952a053ffec +size 4692674208 diff --git a/ConfTuner-LLaMA.Q5_K_M.gguf b/ConfTuner-LLaMA.Q5_K_M.gguf new file mode 100644 index 0000000..627cbaa --- /dev/null +++ b/ConfTuner-LLaMA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b6274e4b1095c7cff18246ba5955677a7f38893283e587d10141c40bb85f83d +size 5732992672 diff --git a/ConfTuner-LLaMA.Q5_K_S.gguf b/ConfTuner-LLaMA.Q5_K_S.gguf new file mode 100644 index 0000000..418991f --- /dev/null +++ b/ConfTuner-LLaMA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6c82eccc7f3d2f0ef7b9e944062db58680f255065dbfc484785de970d7df13 +size 5599299232 diff --git a/ConfTuner-LLaMA.Q6_K.gguf b/ConfTuner-LLaMA.Q6_K.gguf new file mode 100644 index 0000000..542c673 --- /dev/null +++ b/ConfTuner-LLaMA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c895b30c7bc802919ad677f2b9c0da433559ac846a0e4e48a3ea6a463a2868f +size 6596011680 diff --git a/ConfTuner-LLaMA.Q8_0.gguf b/ConfTuner-LLaMA.Q8_0.gguf new file mode 100644 index 0000000..a354e69 --- /dev/null +++ b/ConfTuner-LLaMA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4045bc146215ee5883a7603e0da5f2741662bea339523fc9ff98aa3b105458ba +size 8540776096 diff --git a/ConfTuner-LLaMA.f16.gguf b/ConfTuner-LLaMA.f16.gguf new file mode 100644 index 0000000..15571c7 --- /dev/null +++ b/ConfTuner-LLaMA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf51cfecb5f264cec54000674e3cd9531afe7a67a400abbaf50e07b40cbf1ee3 +size 16068896416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b90d8e1 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: liushiliushi/ConfTuner-LLaMA +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/liushiliushi/ConfTuner-LLaMA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ConfTuner-LLaMA-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ConfTuner-LLaMA-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/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ConfTuner-LLaMA-GGUF/resolve/main/ConfTuner-LLaMA.f16.gguf) | f16 | 16.2 | 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. + +