commit 4e93d4f051caa0c7b65545fb71fcc3d660ad6ab2 Author: ModelHub XC Date: Wed Jul 22 04:26:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChimeraLlama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bc5f3d --- /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 +ChimeraLlama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChimeraLlama-3-8B.IQ4_XS.gguf b/ChimeraLlama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9a39274 --- /dev/null +++ b/ChimeraLlama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc014ae6989cbd38d2df313a31e2caa6867b8f6ac1c5cdb98ef27a9ecf41b89 +size 4484364192 diff --git a/ChimeraLlama-3-8B.Q2_K.gguf b/ChimeraLlama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..9d28cce --- /dev/null +++ b/ChimeraLlama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e06dcd0fbef7f63928c987527d8d363bc34c7d9a916a8b4d922fd9a8003df3 +size 3179132832 diff --git a/ChimeraLlama-3-8B.Q3_K_L.gguf b/ChimeraLlama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..1de50f8 --- /dev/null +++ b/ChimeraLlama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e13bf5fd3e5069eef71837f3252c8a5f1df31f7be7fd3447c28d7ac465d51a93 +size 4321957792 diff --git a/ChimeraLlama-3-8B.Q3_K_M.gguf b/ChimeraLlama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..4fec075 --- /dev/null +++ b/ChimeraLlama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f43a079461945c828201f4931e9375977b206718b75526f5a3def1e9a3170b6c +size 4018919328 diff --git a/ChimeraLlama-3-8B.Q3_K_S.gguf b/ChimeraLlama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..98ebc32 --- /dev/null +++ b/ChimeraLlama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6024466d863bd16dd5d33a012c3db1b897386fefd9cb69319fc3139b6e282ba6 +size 3664500640 diff --git a/ChimeraLlama-3-8B.Q4_K_M.gguf b/ChimeraLlama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..e2c4a52 --- /dev/null +++ b/ChimeraLlama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff0948a5654fe3376111de24aa840910e88a8adba580f7d8763ac967f413e09 +size 4920735648 diff --git a/ChimeraLlama-3-8B.Q4_K_S.gguf b/ChimeraLlama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..f456b7f --- /dev/null +++ b/ChimeraLlama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24008ad92151175e22eab3e8941547952c80e97b31f9501d17f553fc8cf4a02f +size 4692670368 diff --git a/ChimeraLlama-3-8B.Q5_K_M.gguf b/ChimeraLlama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..5a6f230 --- /dev/null +++ b/ChimeraLlama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d41fd8c334bb3591917de88351612348f0069221cbbcc3a7d7348e58970f242 +size 5732988832 diff --git a/ChimeraLlama-3-8B.Q5_K_S.gguf b/ChimeraLlama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9ad2d54 --- /dev/null +++ b/ChimeraLlama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3095ca4b5fdb5a6df65767501b7ac31d0868df66272108465ad0c6bfbbbf85c9 +size 5599295392 diff --git a/ChimeraLlama-3-8B.Q6_K.gguf b/ChimeraLlama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..a87cd66 --- /dev/null +++ b/ChimeraLlama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e010364c5c642db2a7394e613fb613c6eaae532e6e04943df6ba763634303f +size 6596007840 diff --git a/ChimeraLlama-3-8B.Q8_0.gguf b/ChimeraLlama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..299b80e --- /dev/null +++ b/ChimeraLlama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4294249dc9c3314af858e8c6b72f8de8c5d9890ae7b50480381d7542b34a000 +size 8540772256 diff --git a/ChimeraLlama-3-8B.f16.gguf b/ChimeraLlama-3-8B.f16.gguf new file mode 100644 index 0000000..664d791 --- /dev/null +++ b/ChimeraLlama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55f2f6457bccdbf01bf281c1505573144ec1a14f2961696eb664b9c772352e7 +size 16068892576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bb3c252 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: mlabonne/ChimeraLlama-3-8B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- llama +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/ChimeraLlama-3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ChimeraLlama-3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChimeraLlama-3-8B-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/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-GGUF/resolve/main/ChimeraLlama-3-8B.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. + +