commit 6f82e8d715e0acde72db25cfb86281ca0fb240ec Author: ModelHub XC Date: Mon Jul 13 01:05:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e51ffc --- /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 +Llama-3-KafkaLM-8B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-KafkaLM-8B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-KafkaLM-8B-v0.1.IQ4_XS.gguf b/Llama-3-KafkaLM-8B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..49d3068 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53bcf7d25b1c4813df001cc7ea0e139dc71760cffc0ef97330258267be4203fe +size 4484363712 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q2_K.gguf b/Llama-3-KafkaLM-8B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..f8c6e87 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9216a5353e44cddced9cff74994273d4a50889f45d4aee7c6465d5f6ae0f83 +size 3179132352 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q3_K_L.gguf b/Llama-3-KafkaLM-8B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..0797503 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e6741a0ed6a846cc0b6fc1fbb38802b4be36f788876d661e79e6947e26c84e0 +size 4321957312 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q3_K_M.gguf b/Llama-3-KafkaLM-8B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..5fe8e04 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cbdf6e0975c8080803a87725957b2cb1a83a6faf3ba8a0d96ca5dde309be1a +size 4018918848 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q3_K_S.gguf b/Llama-3-KafkaLM-8B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..8786c5c --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93365b8eebac2d82e4118b2557c09f0afa531228264f5ed2347f6a003e9a0dfc +size 3664500160 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q4_K_M.gguf b/Llama-3-KafkaLM-8B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..a6fb0c2 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17782b2908f895642608d8c32305abfeea990577898854f5406ea7a72929f413 +size 4920735168 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q4_K_S.gguf b/Llama-3-KafkaLM-8B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..a3f066d --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ea2e6b67dcf46a44e655e4bacb986a12396da048327f50a2cac6b1355d81c7 +size 4692669888 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q5_K_M.gguf b/Llama-3-KafkaLM-8B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..2040175 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7431877010e11d3fd83f486d795ca90e67ae9ba7bca457bd73709f48ba7f2f +size 5732988352 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q5_K_S.gguf b/Llama-3-KafkaLM-8B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..96957a5 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05cbb85a41aaf0fee941b86731272df3ab5e9a2402237bea596b579e9f730b5e +size 5599294912 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q6_K.gguf b/Llama-3-KafkaLM-8B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..d08d022 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe973b32dce25f15c37d2bb00e94c10a25eded54e1c86c181ccb95faaf80833 +size 6596007360 diff --git a/Llama-3-KafkaLM-8B-v0.1.Q8_0.gguf b/Llama-3-KafkaLM-8B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..f90c048 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cbf0a939213db186898158d217ed721231d569c8c94f93f5f82339eca017ce +size 8540771776 diff --git a/Llama-3-KafkaLM-8B-v0.1.f16.gguf b/Llama-3-KafkaLM-8B-v0.1.f16.gguf new file mode 100644 index 0000000..0a2df15 --- /dev/null +++ b/Llama-3-KafkaLM-8B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b92bd7e2722b5be9756f9ae6384c8b71aa62fa20bf9c7de6a99a967323f258a +size 16068892096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4227e7a --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: seedboxai/Llama-3-KafkaLM-8B-v0.1 +datasets: +- seedboxai/multitask_german_examples_32k +language: +- de +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- deutsch +- german +- seedbox +- llama3 +- english +--- +## About + + + + + + +static quants of https://huggingface.co/seedboxai/Llama-3-KafkaLM-8B-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-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/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-KafkaLM-8B-v0.1-GGUF/resolve/main/Llama-3-KafkaLM-8B-v0.1.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. + +