commit a0fb5e4c1c7925c6e1a8966ae63262bf7f2819fe Author: ModelHub XC Date: Fri Oct 16 21:32:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-drill-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1663ec5 --- /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 +Llama3.1-8B-drill.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-drill.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-drill.IQ4_XS.gguf b/Llama3.1-8B-drill.IQ4_XS.gguf new file mode 100644 index 0000000..81dbe39 --- /dev/null +++ b/Llama3.1-8B-drill.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35af72e3cf01966bc0b17758b376441c8a2b4346527360acbbd507ae6fc24e7 +size 4484363552 diff --git a/Llama3.1-8B-drill.Q2_K.gguf b/Llama3.1-8B-drill.Q2_K.gguf new file mode 100644 index 0000000..486739d --- /dev/null +++ b/Llama3.1-8B-drill.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfade8e07eab7b0765f4a388d3d930e725a14e98dfd1c6c20eb750d9aa7c9b89 +size 3179132192 diff --git a/Llama3.1-8B-drill.Q3_K_L.gguf b/Llama3.1-8B-drill.Q3_K_L.gguf new file mode 100644 index 0000000..677798a --- /dev/null +++ b/Llama3.1-8B-drill.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514deaa3c33fa9b77d6b7318596c10e275a4c4864fd1c8c8733c12d15cdc9a17 +size 4321957152 diff --git a/Llama3.1-8B-drill.Q3_K_M.gguf b/Llama3.1-8B-drill.Q3_K_M.gguf new file mode 100644 index 0000000..f58d7a5 --- /dev/null +++ b/Llama3.1-8B-drill.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d81b3f8ddbdd572670819a96e54c935143bce0a3e8ec85a0cd8486710803c48 +size 4018918688 diff --git a/Llama3.1-8B-drill.Q3_K_S.gguf b/Llama3.1-8B-drill.Q3_K_S.gguf new file mode 100644 index 0000000..c54a00d --- /dev/null +++ b/Llama3.1-8B-drill.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33217ccb1b6b1b876504f7ee5dfbf902c6116d6f4f93767d979013e973737c1c +size 3664500000 diff --git a/Llama3.1-8B-drill.Q4_K_M.gguf b/Llama3.1-8B-drill.Q4_K_M.gguf new file mode 100644 index 0000000..b4a39c6 --- /dev/null +++ b/Llama3.1-8B-drill.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77e32a3dca1b47f0753c9a0f5cff9a8f8e4bfc3e8bba625ab276e8133415c1e +size 4920735008 diff --git a/Llama3.1-8B-drill.Q4_K_S.gguf b/Llama3.1-8B-drill.Q4_K_S.gguf new file mode 100644 index 0000000..48345e9 --- /dev/null +++ b/Llama3.1-8B-drill.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019d01b74280cbe505f52dd8ef10d1e97ba3bbaa192d6ce9b98ee01159dcd0b9 +size 4692669728 diff --git a/Llama3.1-8B-drill.Q5_K_M.gguf b/Llama3.1-8B-drill.Q5_K_M.gguf new file mode 100644 index 0000000..f4de2fa --- /dev/null +++ b/Llama3.1-8B-drill.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4736284cd11b736c5b3aa344d432950899934a06a83cec7d828ebe2371fba8 +size 5732988192 diff --git a/Llama3.1-8B-drill.Q5_K_S.gguf b/Llama3.1-8B-drill.Q5_K_S.gguf new file mode 100644 index 0000000..4b48c7f --- /dev/null +++ b/Llama3.1-8B-drill.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76bf73a94c88490f35cbb9a0757e626d18edbb0794ac239fa198e4f4bc675e67 +size 5599294752 diff --git a/Llama3.1-8B-drill.Q6_K.gguf b/Llama3.1-8B-drill.Q6_K.gguf new file mode 100644 index 0000000..c0f3c9a --- /dev/null +++ b/Llama3.1-8B-drill.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639acf35811bca3e939adc0b08ac19795d85723c335840736ba823a4ec943b09 +size 6596007200 diff --git a/Llama3.1-8B-drill.Q8_0.gguf b/Llama3.1-8B-drill.Q8_0.gguf new file mode 100644 index 0000000..04434b2 --- /dev/null +++ b/Llama3.1-8B-drill.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb050694f953162e3f00fd04f1c4772f2afd9ff095a1d999d226caebcd12818 +size 8540771616 diff --git a/Llama3.1-8B-drill.f16.gguf b/Llama3.1-8B-drill.f16.gguf new file mode 100644 index 0000000..1b73722 --- /dev/null +++ b/Llama3.1-8B-drill.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7a61db8e59dac9a948e30c9552eac1932cf71b7783b645dc6ce836cea23255 +size 16068891936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3100568 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: agentlans/Llama3.1-8B-drill +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/agentlans/Llama3.1-8B-drill + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-drill-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/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-drill-GGUF/resolve/main/Llama3.1-8B-drill.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. + +