commit 9a0a5c1921b04c54fb033219350fc1d75e834ad4 Author: ModelHub XC Date: Mon Sep 28 16:11:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88eb3a8 --- /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 +KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf b/KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf new file mode 100644 index 0000000..412ab54 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d7858550a4271053d2e318100fea01b63a9e770de39791a8086595e5017fe7 +size 4484362752 diff --git a/KoLlama-3-8B-Instruct-Mix.Q2_K.gguf b/KoLlama-3-8B-Instruct-Mix.Q2_K.gguf new file mode 100644 index 0000000..81c4873 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1c60b3728ee4c9cc6153f89fc640d0d1e356e369b729a43a45faa7ce0924e9 +size 3179131392 diff --git a/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf b/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf new file mode 100644 index 0000000..d0602c8 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69deb2a79c71fe905098d1ee529f3f49e79e28690d9fc9e95771364d0d4c3fc6 +size 4321956352 diff --git a/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf b/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf new file mode 100644 index 0000000..ccd67be --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda5190a6d8480b519f8c06486bafb0569f8a3393df57ddd25e40e8a4578f255 +size 4018917888 diff --git a/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf b/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf new file mode 100644 index 0000000..08d71b3 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f8899e9b5f8d34f90a03d95e5dddfb2066519381ba5c859724047d383b9292 +size 3664499200 diff --git a/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf b/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf new file mode 100644 index 0000000..857d4c7 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b06bd7447354d99e26084f3bb6bc805edd5a2e0de68cf604c29c21779ac21b1 +size 4920734208 diff --git a/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf b/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf new file mode 100644 index 0000000..95f299a --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088018159660e9b185914bbb130c010b2f8639c592c090e36643590209a4747f +size 4692668928 diff --git a/KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf b/KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf new file mode 100644 index 0000000..51f03b1 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa39898204e9f5be435bc743c41967c1a69e0d63644706883601287e98cba972 +size 5732987392 diff --git a/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf b/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf new file mode 100644 index 0000000..e75935b --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8d6c368ee0676a212d1a84e241fc3746857606757bb2b777d05d4982b8f451 +size 5599293952 diff --git a/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf b/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf new file mode 100644 index 0000000..affdbce --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0615535661ff2565b843a68c9a1af9b653694860afd84713a0b41c5949f1cf3 +size 6596006400 diff --git a/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf b/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf new file mode 100644 index 0000000..ba399c8 --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d4d6c9adabbd814c4bdc254fca5cbc101a2c0c9ac654f73d571c26d30393c5 +size 8540770816 diff --git a/KoLlama-3-8B-Instruct-Mix.f16.gguf b/KoLlama-3-8B-Instruct-Mix.f16.gguf new file mode 100644 index 0000000..8d1ee8c --- /dev/null +++ b/KoLlama-3-8B-Instruct-Mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c169745ec3bbfdee5785de9a6540ff51eb1159cf8304a1e0a2dc30fecbf88a0 +size 16068891136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6f28f5 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: fiveflow/KoLlama-3-8B-Instruct-Mix +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/fiveflow/KoLlama-3-8B-Instruct-Mix + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-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/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.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. + +