commit 56374bd30410fb4403d74a2b674c69e313dac118 Author: ModelHub XC Date: Sat Jun 13 23:14:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/penny-llama3-2x8b-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..85615e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +penny-llama3-2x8b-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +penny-llama3-2x8b-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e4837cc --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: giannisan/penny-llama3-2x8b-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/giannisan/penny-llama3-2x8b-v2 + + +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/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q2_K.gguf) | Q2_K | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.IQ3_XS.gguf) | IQ3_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q3_K_S.gguf) | Q3_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.IQ3_S.gguf) | IQ3_S | 6.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.IQ3_M.gguf) | IQ3_M | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q3_K_M.gguf) | Q3_K_M | 6.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q3_K_L.gguf) | Q3_K_L | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.IQ4_XS.gguf) | IQ4_XS | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q4_K_S.gguf) | Q4_K_S | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q4_K_M.gguf) | Q4_K_M | 8.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q5_K_S.gguf) | Q5_K_S | 9.6 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q5_K_M.gguf) | Q5_K_M | 9.8 | | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q6_K.gguf) | Q6_K | 11.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/penny-llama3-2x8b-v2-GGUF/resolve/main/penny-llama3-2x8b-v2.Q8_0.gguf) | Q8_0 | 14.6 | fast, best quality | + +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. + + diff --git a/penny-llama3-2x8b-v2.IQ3_M.gguf b/penny-llama3-2x8b-v2.IQ3_M.gguf new file mode 100644 index 0000000..fa824ed --- /dev/null +++ b/penny-llama3-2x8b-v2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec7e8e674bba64313cec8f851bb7a45ffc7c32cb442343a9d3f8370a4464d0b +size 6238767360 diff --git a/penny-llama3-2x8b-v2.IQ3_S.gguf b/penny-llama3-2x8b-v2.IQ3_S.gguf new file mode 100644 index 0000000..b2f37f7 --- /dev/null +++ b/penny-llama3-2x8b-v2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39888dc3f0e35cd3a659dd058f1b89917ead657254002dd7ad69676af4fca7d2 +size 6105073920 diff --git a/penny-llama3-2x8b-v2.IQ3_XS.gguf b/penny-llama3-2x8b-v2.IQ3_XS.gguf new file mode 100644 index 0000000..dc5d24c --- /dev/null +++ b/penny-llama3-2x8b-v2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35206ea2e53d1ce0722a8201ddad1f4e68cceb041a512ea0b7478e2dbd9035f9 +size 5809375488 diff --git a/penny-llama3-2x8b-v2.IQ4_XS.gguf b/penny-llama3-2x8b-v2.IQ4_XS.gguf new file mode 100644 index 0000000..56cb921 --- /dev/null +++ b/penny-llama3-2x8b-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5303e5c318278c234b7abfbe88083cb26c7ef7fbdca07c3a4be18bc22ba07205 +size 7516335168 diff --git a/penny-llama3-2x8b-v2.Q2_K.gguf b/penny-llama3-2x8b-v2.Q2_K.gguf new file mode 100644 index 0000000..18db8ff --- /dev/null +++ b/penny-llama3-2x8b-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a91d9055b1118f66567cbb4ee541d005d4b14a239a83ba11a5ece38a486eea0 +size 5220197824 diff --git a/penny-llama3-2x8b-v2.Q3_K_L.gguf b/penny-llama3-2x8b-v2.Q3_K_L.gguf new file mode 100644 index 0000000..b7926d4 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d74df2ad07f30927560cd060a7146e3748bde5174621290bcac913830fc700 +size 7229147392 diff --git a/penny-llama3-2x8b-v2.Q3_K_M.gguf b/penny-llama3-2x8b-v2.Q3_K_M.gguf new file mode 100644 index 0000000..8ff8728 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305f9b7a2cf9d3ac238a9cbc5e803d790f2fb5aa65a63b3ee9dd9f0e482f3056 +size 6705907968 diff --git a/penny-llama3-2x8b-v2.Q3_K_S.gguf b/penny-llama3-2x8b-v2.Q3_K_S.gguf new file mode 100644 index 0000000..7e0e875 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7028933fc4420bdb3ba0b6b92a7c85cf6200b1d5123b479984006452da8e4f +size 6087248128 diff --git a/penny-llama3-2x8b-v2.Q4_K_M.gguf b/penny-llama3-2x8b-v2.Q4_K_M.gguf new file mode 100644 index 0000000..af6cdb1 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8486d7acb1da119af2cb79c5cfe2004c6c0ad405b4342d5bc5876e89b1f6b5d2 +size 8334388544 diff --git a/penny-llama3-2x8b-v2.Q4_K_S.gguf b/penny-llama3-2x8b-v2.Q4_K_S.gguf new file mode 100644 index 0000000..acce942 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6361b3c80d9c5e23de1e424ce4f4ca01c1577a71b0f10e704fb1569b4137c3c +size 7893462336 diff --git a/penny-llama3-2x8b-v2.Q5_K_M.gguf b/penny-llama3-2x8b-v2.Q5_K_M.gguf new file mode 100644 index 0000000..57fb7e1 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50eb5618f2ac34a59999d8af5a92961e8ba6f71a82853af0c8f9be68ea24edc7 +size 9733845312 diff --git a/penny-llama3-2x8b-v2.Q5_K_S.gguf b/penny-llama3-2x8b-v2.Q5_K_S.gguf new file mode 100644 index 0000000..8f4d575 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcab8d284d443dcf4351866b66d509cb65eb19a05f44bb2565b6e5788279a011 +size 9475371328 diff --git a/penny-llama3-2x8b-v2.Q6_K.gguf b/penny-llama3-2x8b-v2.Q6_K.gguf new file mode 100644 index 0000000..93d7f77 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5921aebe41c1575324aeaf9b1037df32b52ec0f5555489241b16cdafd04225c0 +size 11220768128 diff --git a/penny-llama3-2x8b-v2.Q8_0.gguf b/penny-llama3-2x8b-v2.Q8_0.gguf new file mode 100644 index 0000000..9324157 --- /dev/null +++ b/penny-llama3-2x8b-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8093825d3a1aecdfc547a9f2627ce1d20bddc707a9d233a9bac8ad743bd233a +size 14530782464