commit 5cf665b6259c20a668c9f1ce0b43d50234a3879d Author: ModelHub XC Date: Sat Jun 27 15:54:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7511e74 --- /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-3.1-8B-cdj2-20250217.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-cdj2-20250217.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-cdj2-20250217.IQ4_XS.gguf b/Llama-3.1-8B-cdj2-20250217.IQ4_XS.gguf new file mode 100644 index 0000000..1678c8b --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c345d6e27679e1e646f84f5acc0de7155b1945545afd2b746807bcb00ed73a +size 4484368352 diff --git a/Llama-3.1-8B-cdj2-20250217.Q2_K.gguf b/Llama-3.1-8B-cdj2-20250217.Q2_K.gguf new file mode 100644 index 0000000..97630ae --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a6a792911c64b064ddeab853ab3bf40b6c490cb54b9e51bd39b4210c796f82 +size 3179136992 diff --git a/Llama-3.1-8B-cdj2-20250217.Q3_K_L.gguf b/Llama-3.1-8B-cdj2-20250217.Q3_K_L.gguf new file mode 100644 index 0000000..68e5223 --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55746e1b378ecfd439faa5cecb78fa178ff754859a6b5942651651b819164229 +size 4321961952 diff --git a/Llama-3.1-8B-cdj2-20250217.Q3_K_M.gguf b/Llama-3.1-8B-cdj2-20250217.Q3_K_M.gguf new file mode 100644 index 0000000..98cef4b --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c278ba39b7fb168db69e5504ce12eea34a83758eeb49de79c762b321ba52b7 +size 4018923488 diff --git a/Llama-3.1-8B-cdj2-20250217.Q3_K_S.gguf b/Llama-3.1-8B-cdj2-20250217.Q3_K_S.gguf new file mode 100644 index 0000000..7c5179a --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1efcfb2529c1ebe97953e0af28983d32a7d3bb7795b8660edff43c27179519ad +size 3664504800 diff --git a/Llama-3.1-8B-cdj2-20250217.Q4_K_M.gguf b/Llama-3.1-8B-cdj2-20250217.Q4_K_M.gguf new file mode 100644 index 0000000..69e83ac --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23637c0a09a2d37d71fe5f9eb049898d2ad1ff0570ebfde85a63aa0edf5770c +size 4920739808 diff --git a/Llama-3.1-8B-cdj2-20250217.Q4_K_S.gguf b/Llama-3.1-8B-cdj2-20250217.Q4_K_S.gguf new file mode 100644 index 0000000..b63657a --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e219c57324e4c9df7afdb81c4d189c7aa70683b5d324e66fb001bcecedbafc13 +size 4692674528 diff --git a/Llama-3.1-8B-cdj2-20250217.Q5_K_M.gguf b/Llama-3.1-8B-cdj2-20250217.Q5_K_M.gguf new file mode 100644 index 0000000..77183ac --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6fc18137a5cd21bd4386e6ad4aff7dca21869f59ac338a071881c8dfdf7af7 +size 5732992992 diff --git a/Llama-3.1-8B-cdj2-20250217.Q5_K_S.gguf b/Llama-3.1-8B-cdj2-20250217.Q5_K_S.gguf new file mode 100644 index 0000000..1826c75 --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28cde5d2aba22680b3beb1f6b54b879fdf7e596893db193ea1a7d5481bb5467 +size 5599299552 diff --git a/Llama-3.1-8B-cdj2-20250217.Q6_K.gguf b/Llama-3.1-8B-cdj2-20250217.Q6_K.gguf new file mode 100644 index 0000000..666ae41 --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d38a6209d80ed717ee45d91d12118049e8fa5d7603c6ac1a081de82a3539d8a +size 6596012000 diff --git a/Llama-3.1-8B-cdj2-20250217.Q8_0.gguf b/Llama-3.1-8B-cdj2-20250217.Q8_0.gguf new file mode 100644 index 0000000..0ab44ce --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e568e114ca19163cd530c9e8e8c5101a2c61a1b295557f3cbc5d81d12ed44462 +size 8540776416 diff --git a/Llama-3.1-8B-cdj2-20250217.f16.gguf b/Llama-3.1-8B-cdj2-20250217.f16.gguf new file mode 100644 index 0000000..bbee8e9 --- /dev/null +++ b/Llama-3.1-8B-cdj2-20250217.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3851cf7246ee781b3ae257cc9ffedeaaa51130662a166f29b21c69ec5ba5bf65 +size 16068896736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1340e8c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: KONIexp/Llama-3.1-8B-cdj2-20250217 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/KONIexp/Llama-3.1-8B-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/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-cdj2-20250217.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-cdj2-20250217-GGUF/resolve/main/Llama-3.1-8B-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. + +