commit 377afa8e00a6bd204541532d257cfc5464296927 Author: ModelHub XC Date: Fri Jun 19 17:26:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..838bb60 --- /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 +Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malpyung_Meta-Llama-3.1-8B_SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.IQ4_XS.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.IQ4_XS.gguf new file mode 100644 index 0000000..95b6d9c --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfd51c5a7c511580dff92151eeae49412436396a14570895647bec9346bcb2d +size 4484363520 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q2_K.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q2_K.gguf new file mode 100644 index 0000000..54d800d --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8445eda63d424de65d534bdb76e68c5045353779e114d8f4b971aa1238fa96 +size 3179132160 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_L.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_L.gguf new file mode 100644 index 0000000..b7a2895 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77dfe4d5c8ab63e93ddd4a4e3eae5c2ed3036bafafb372833235eae9e725f9c3 +size 4321957120 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_M.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_M.gguf new file mode 100644 index 0000000..ddd6661 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de33478107ec3d00c032c5911b0062a6831708581157b3e891e6b8c47a71968b +size 4018918656 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_S.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_S.gguf new file mode 100644 index 0000000..903e123 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d00f48109d9a34614109cac902fbe7c94bd0d5da0b82055f567d4a7dae08f9e +size 3664499968 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_M.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_M.gguf new file mode 100644 index 0000000..cd41623 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e10f44163760f1711333c31e2c3901a21bc5f8a5fbcd175703ba4b08600ff3 +size 4920734976 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_S.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_S.gguf new file mode 100644 index 0000000..c2b307b --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0a40bef9a9f2825798ba5db8f7035219ba916a5988359b12c63201462ba3ec +size 4692669696 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_M.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_M.gguf new file mode 100644 index 0000000..84ce49d --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5daefae50ca90fc70dce57f62c6d31a89953e67bb39a02f472ee1f1782e34e +size 5732988160 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_S.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_S.gguf new file mode 100644 index 0000000..8234d44 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfeacaa4dfbe4e736f236cb5d93a0788353de35461e2746ae85e18a998fa578 +size 5599294720 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q6_K.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q6_K.gguf new file mode 100644 index 0000000..3b73e94 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c823a9d28160c6445df5547bc68511b822302c460e3ae86fb048ac9d3f943428 +size 6596007168 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.Q8_0.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.Q8_0.gguf new file mode 100644 index 0000000..b24ff3b --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1213b6689587254ebf81d41d64fcba18a5d4664596775689531e0a724a4a6d6 +size 8540771584 diff --git a/Malpyung_Meta-Llama-3.1-8B_SFT.f16.gguf b/Malpyung_Meta-Llama-3.1-8B_SFT.f16.gguf new file mode 100644 index 0000000..3d97942 --- /dev/null +++ b/Malpyung_Meta-Llama-3.1-8B_SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeb4c15071c91c9b85e8b5d53d6dea0fbf5a9be57ce55d57ce4691a2489d762 +size 16068891904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6db4d86 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: dddsaty/Malpyung_Meta-Llama-3.1-8B_SFT +language: +- ko +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/dddsaty/Malpyung_Meta-Llama-3.1-8B_SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-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/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Malpyung_Meta-Llama-3.1-8B_SFT-GGUF/resolve/main/Malpyung_Meta-Llama-3.1-8B_SFT.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. + +