commit 0efc900496cc41e3404f12b0ed23d67a9bd54700 Author: ModelHub XC Date: Thu Sep 24 11:51:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/pankaj-llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e50b72f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +pankaj-llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +pankaj-llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3b65b43 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: pankajshakya627/pankaj-llama-3-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/pankajshakya627/pankaj-llama-3-8B + + +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/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/pankaj-llama-3-8B-GGUF/resolve/main/pankaj-llama-3-8B.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. + + diff --git a/pankaj-llama-3-8B.IQ3_M.gguf b/pankaj-llama-3-8B.IQ3_M.gguf new file mode 100644 index 0000000..767130d --- /dev/null +++ b/pankaj-llama-3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b178d9328fcd0261ade807314f71ddc65d76f3c60af999112f7b6cf0cbdb84d8 +size 3784823136 diff --git a/pankaj-llama-3-8B.IQ3_S.gguf b/pankaj-llama-3-8B.IQ3_S.gguf new file mode 100644 index 0000000..d543650 --- /dev/null +++ b/pankaj-llama-3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1fd58b46492c19754412db65801e2c1f55f1350e6a77f76c8e8b34dd53f513 +size 3682324832 diff --git a/pankaj-llama-3-8B.IQ3_XS.gguf b/pankaj-llama-3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..9e6c685 --- /dev/null +++ b/pankaj-llama-3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aa2ab03c54269c4f45691dffbb0ff2fa8f49cdb1e9ba82ff8953d5d53257045 +size 3518746976 diff --git a/pankaj-llama-3-8B.IQ4_XS.gguf b/pankaj-llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..8f0d14f --- /dev/null +++ b/pankaj-llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ff6a820b8bebed64b11aab8061925c1b0923d5b6ebdb705568228f08885205 +size 4484362592 diff --git a/pankaj-llama-3-8B.Q2_K.gguf b/pankaj-llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..2441e2e --- /dev/null +++ b/pankaj-llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e217133f147dee77a993574d0f466781e1b01abe8a0ce007ee11d21026bf04e3 +size 3179131232 diff --git a/pankaj-llama-3-8B.Q3_K_L.gguf b/pankaj-llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0f4d03e --- /dev/null +++ b/pankaj-llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2adebf79b5cad8c010f8407e99b7e2248e15199efb3a9f0344617126e27406 +size 4321956192 diff --git a/pankaj-llama-3-8B.Q3_K_M.gguf b/pankaj-llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..60349cf --- /dev/null +++ b/pankaj-llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f522fb2e2228661b209908f3ad7f9eeac0f6379e791bb8fd0cabdb0d1fec4a3 +size 4018917728 diff --git a/pankaj-llama-3-8B.Q3_K_S.gguf b/pankaj-llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..0455187 --- /dev/null +++ b/pankaj-llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7765f40625312a02493fbc2ba5139ade0bccb432d11debfcbbd52ae875458ae1 +size 3664499040 diff --git a/pankaj-llama-3-8B.Q4_K_M.gguf b/pankaj-llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..677584b --- /dev/null +++ b/pankaj-llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d175b020800ff3e1f5fa30ec64a7b9c2ba13e2e2ebed596361e5d1ed6ab167 +size 4920734048 diff --git a/pankaj-llama-3-8B.Q4_K_S.gguf b/pankaj-llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..8c198bd --- /dev/null +++ b/pankaj-llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046463962471dcdadd2f912885e3eddd760c954118780fc811d3006bfe9fd9e3 +size 4692668768 diff --git a/pankaj-llama-3-8B.Q5_K_M.gguf b/pankaj-llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..17540a7 --- /dev/null +++ b/pankaj-llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7a48fd3123724ff5c18e7de9587e5924b2789604fb6e50486ca002342bb580 +size 5732987232 diff --git a/pankaj-llama-3-8B.Q5_K_S.gguf b/pankaj-llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..164751d --- /dev/null +++ b/pankaj-llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa8261f3e40251963a556fcfbf624b4223a87f824ac33d8a09d207a547839eb +size 5599293792 diff --git a/pankaj-llama-3-8B.Q6_K.gguf b/pankaj-llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..fdfa059 --- /dev/null +++ b/pankaj-llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8058b6cebe270255ba707feb6428f4b972afb4eaab12d82b80f78ec3714a4267 +size 6596006240 diff --git a/pankaj-llama-3-8B.Q8_0.gguf b/pankaj-llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..15c6121 --- /dev/null +++ b/pankaj-llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5be5da1b96bf48904bf48e7e3822b77c503196e61df5f32c08c70393b86a244 +size 8540770656 diff --git a/pankaj-llama-3-8B.f16.gguf b/pankaj-llama-3-8B.f16.gguf new file mode 100644 index 0000000..8ec1b47 --- /dev/null +++ b/pankaj-llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b288652973bf0283720eb682bdd8d67449ef09a0a6412dde4caf01b6c230cd62 +size 16068890976