commit ae5439e4cec5b24701ca7ba1c9360c245089d1c4 Author: ModelHub XC Date: Thu May 7 05:47:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-base-instruct-gradient-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45b992a --- /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 +llama3.1-base-instruct-gradient-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed87479 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: deltanym/llama3.1-base-instruct-gradient-2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/deltanym/llama3.1-base-instruct-gradient-2 + + +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-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-2-GGUF/resolve/main/llama3.1-base-instruct-gradient-2.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. 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. + + diff --git a/llama3.1-base-instruct-gradient-2.IQ4_XS.gguf b/llama3.1-base-instruct-gradient-2.IQ4_XS.gguf new file mode 100644 index 0000000..661fb07 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812cf5bf528da536bf37e857189d62d7c3bb3523298b43af35c9e55af2fb4e46 +size 4484363712 diff --git a/llama3.1-base-instruct-gradient-2.Q2_K.gguf b/llama3.1-base-instruct-gradient-2.Q2_K.gguf new file mode 100644 index 0000000..6d92059 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c14b19da08e9db7fbfe44922db8f7b236132f69112ee06127368ebaed7e40d +size 3179132352 diff --git a/llama3.1-base-instruct-gradient-2.Q3_K_L.gguf b/llama3.1-base-instruct-gradient-2.Q3_K_L.gguf new file mode 100644 index 0000000..96a37fb --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99f361b6acd999e49cb7ec208b2abf6b5c3e5efa510c122422a37bfb39806bd +size 4321957312 diff --git a/llama3.1-base-instruct-gradient-2.Q3_K_M.gguf b/llama3.1-base-instruct-gradient-2.Q3_K_M.gguf new file mode 100644 index 0000000..b9c4ff1 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0468ba4c8ba511b2e70cd36f970a1d7352af84cc74953803ef85674771349e +size 4018918848 diff --git a/llama3.1-base-instruct-gradient-2.Q3_K_S.gguf b/llama3.1-base-instruct-gradient-2.Q3_K_S.gguf new file mode 100644 index 0000000..accdc03 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0e0579dc0409e7b315e6e57374bf9b152687ae72b7ddc45c1909ae2757d7b9 +size 3664500160 diff --git a/llama3.1-base-instruct-gradient-2.Q4_0_4_4.gguf b/llama3.1-base-instruct-gradient-2.Q4_0_4_4.gguf new file mode 100644 index 0000000..aa48968 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95ee414b59b26dc65a4bdaf3c3ba967932ed0e26750f9b4eae4a06f86460a59 +size 4661212608 diff --git a/llama3.1-base-instruct-gradient-2.Q4_K_M.gguf b/llama3.1-base-instruct-gradient-2.Q4_K_M.gguf new file mode 100644 index 0000000..1c6102a --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b04f410da30ef4a112d5ab9f01b8a7513dded178b2b9090a034dd8686ad78b6 +size 4920735168 diff --git a/llama3.1-base-instruct-gradient-2.Q4_K_S.gguf b/llama3.1-base-instruct-gradient-2.Q4_K_S.gguf new file mode 100644 index 0000000..f72230d --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3848452f361c4a61cb0c9ce47738ba1ffddcc779d59b524e86bd37a540e609a +size 4692669888 diff --git a/llama3.1-base-instruct-gradient-2.Q5_K_M.gguf b/llama3.1-base-instruct-gradient-2.Q5_K_M.gguf new file mode 100644 index 0000000..27e1fba --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b997c0842dc59d385ecd7a44d8a8fa79827af9a6a1996c3b0a6090be6760479a +size 5732988352 diff --git a/llama3.1-base-instruct-gradient-2.Q5_K_S.gguf b/llama3.1-base-instruct-gradient-2.Q5_K_S.gguf new file mode 100644 index 0000000..118c829 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58901d9becaf6a0eff535cf2101142bae7203bc2b1ed8ec3c8486ce88c3699cf +size 5599294912 diff --git a/llama3.1-base-instruct-gradient-2.Q6_K.gguf b/llama3.1-base-instruct-gradient-2.Q6_K.gguf new file mode 100644 index 0000000..8b4f69b --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7fa20226b05d9592ea7294e20f04f7854bd80e0ee47f62a9431b604d5090e5 +size 6596007360 diff --git a/llama3.1-base-instruct-gradient-2.Q8_0.gguf b/llama3.1-base-instruct-gradient-2.Q8_0.gguf new file mode 100644 index 0000000..bf82545 --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db96231720a06e5a4e94d887d2db1c57a3436f1a3bf5b9cdfb419342edfa441 +size 8540771776 diff --git a/llama3.1-base-instruct-gradient-2.f16.gguf b/llama3.1-base-instruct-gradient-2.f16.gguf new file mode 100644 index 0000000..d9a0d3d --- /dev/null +++ b/llama3.1-base-instruct-gradient-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a3cb2c15a891f96810d077d8dd8f76f79bae41228bb3a15d4591113ea9db9d +size 16068892096