commit 0e013de0be6d7a942cb8a3ea54bd86e00a8017a1 Author: ModelHub XC Date: Sun Aug 30 18:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49ba6a3 --- /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 +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.f16.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Merged-cdj2-20250217.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.IQ4_XS.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.IQ4_XS.gguf new file mode 100644 index 0000000..7383af9 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39797f9f417e3907a1beb1ffd728a396ee88d9269f6735ad4656378d2ca62bdd +size 4484368384 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q2_K.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q2_K.gguf new file mode 100644 index 0000000..e53a61a --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd142887f6067edd21bea9f34cca58608bb6fd1e2ad69b3f9960a83a59facbb +size 3179137024 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_L.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_L.gguf new file mode 100644 index 0000000..f3b7809 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab698481bbcebb6957efce1c909615e15d59630477cd32cf2db0c40721c36e41 +size 4321961984 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_M.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_M.gguf new file mode 100644 index 0000000..1dcacab --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed721a8b28ae5c225f905a4f48e72d92c47d01e277c6fe48f623b423a7421e4b +size 4018923520 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_S.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_S.gguf new file mode 100644 index 0000000..343537d --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:318d04169b4bd1d367b1072f054e8b6c390d4ab21e163bd89ed256beaeba3b1e +size 3664504832 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_M.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_M.gguf new file mode 100644 index 0000000..419248e --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdfeef484aed4d136f045298752d5ed776c246e6c1691c8241c2b326093cbf43 +size 4920739840 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_S.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_S.gguf new file mode 100644 index 0000000..74ca93f --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d13936fe51ad97ccb7f157514eb7c459001f1025841723991d274788388729 +size 4692674560 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_M.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_M.gguf new file mode 100644 index 0000000..73ba484 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb423488fd69207b4acf6ea4d9e952567e2086fa37cabfde82b4ab3297399c44 +size 5732993024 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_S.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_S.gguf new file mode 100644 index 0000000..32b1c25 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab279c3186e70391a0b80175b833d75aba7f9412f662e9ba7a9322c14791b014 +size 5599299584 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q6_K.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q6_K.gguf new file mode 100644 index 0000000..d6268e6 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef1668a851b976a98a63eeed341a8dad51009db351ea21b485b0fcc729e6d4a +size 6596012032 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q8_0.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q8_0.gguf new file mode 100644 index 0000000..f757459 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b250b06a29fec2f9ee680b0d6c5cf4a3c28d12074a9f3a6e3079925c6dcb001 +size 8540776448 diff --git a/KONI-Llama3.1-8B-Merged-cdj2-20250217.f16.gguf b/KONI-Llama3.1-8B-Merged-cdj2-20250217.f16.gguf new file mode 100644 index 0000000..4279a36 --- /dev/null +++ b/KONI-Llama3.1-8B-Merged-cdj2-20250217.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9960007829bb5126b0bcb874bd63044093b67d95983be6f4bdfc67a4d1f18de3 +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7129da --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: KONIexp/KONI-Llama3.1-8B-Merged-cdj2-20250217 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/KONIexp/KONI-Llama3.1-8B-Merged-cdj2-20250217 + + +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/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Merged-cdj2-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Merged-cdj2-20250217.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. + +