commit de1eeb906c2d0bdc645ecf925e22f4d98876c4d6 Author: ModelHub XC Date: Wed May 20 01:36:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5685541 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChimeraLlama-3-8B-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChimeraLlama-3-8B-v2.i1-IQ1_M.gguf b/ChimeraLlama-3-8B-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..08141af --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffdcc3f2ff3c2a19bf7288ca0efddbcfcf7093ac553c0900949833c7d382e12 +size 2161973664 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ1_S.gguf b/ChimeraLlama-3-8B-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..9aa7b56 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62b37d845b5d5761a8e7ff707a570674ca57bed663b1a85d31cf5595d2d65fc +size 2019629472 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ2_M.gguf b/ChimeraLlama-3-8B-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..48f4558 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ddce7f88cc8fde4af81779f49785fd11b43295e9a823dd2c5c0789687863a6 +size 2948282784 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ2_S.gguf b/ChimeraLlama-3-8B-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..631df50 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ebbeb70c1156b8a5eddb556aebed4af71fd607bd538ec55731376ef757feb1 +size 2758490528 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ2_XS.gguf b/ChimeraLlama-3-8B-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2158a50 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d1cb9813b5117e218bf5713a151ec8c3400b4b28a8570396cefaf74b5b4023 +size 2605783456 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ2_XXS.gguf b/ChimeraLlama-3-8B-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..866c3c2 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:521f46a8953884cfcd4aa223eb2cc607019f4e4cbe3b37765e08e10d3c3c10e1 +size 2399213984 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ3_M.gguf b/ChimeraLlama-3-8B-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..646a541 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82169d09262cddb68504943eef602c5a591f8ee18b5df10357080801ac45b64 +size 3784825248 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ3_S.gguf b/ChimeraLlama-3-8B-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..b0a3d7f --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a4f04137020ba21126783bf1927b5a78964259355c97dc55e97202e67d64c9 +size 3682326944 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ3_XS.gguf b/ChimeraLlama-3-8B-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cc3af7a --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b4591b97367c78bdce4e94b7988c2d41214190659da73b8e0c398622014057 +size 3518749088 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ3_XXS.gguf b/ChimeraLlama-3-8B-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..64b603d --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464370d68f8c107353547ae53827413af707a66d5c84fd59b15d2df327dca605 +size 3274914208 diff --git a/ChimeraLlama-3-8B-v2.i1-IQ4_XS.gguf b/ChimeraLlama-3-8B-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..48894be --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb4c331eafd1ea88ff1961c4419a255da6fb5349711a627393932778ee3bbe9 +size 4447664544 diff --git a/ChimeraLlama-3-8B-v2.i1-Q2_K.gguf b/ChimeraLlama-3-8B-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..4866efb --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d205fe8af0ddc30d08eff6c7df82b715228bb8b5919430c6e466a4ecbfedde5c +size 3179133344 diff --git a/ChimeraLlama-3-8B-v2.i1-Q3_K_L.gguf b/ChimeraLlama-3-8B-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4c17298 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3384e22497d681c09a99ae5a2a98a7617061e161345507a9a796470f635dca1d +size 4321958304 diff --git a/ChimeraLlama-3-8B-v2.i1-Q3_K_M.gguf b/ChimeraLlama-3-8B-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e325178 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a424323428f43027a5480af835926a3e4dbe47488503ee27ca2e41fcbc6b8ef1 +size 4018919840 diff --git a/ChimeraLlama-3-8B-v2.i1-Q3_K_S.gguf b/ChimeraLlama-3-8B-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3bd9bbf --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76104414252377d116878f8cfe411404a08b15391aefe6b0a65e09e0537da7c +size 3664501152 diff --git a/ChimeraLlama-3-8B-v2.i1-Q4_0.gguf b/ChimeraLlama-3-8B-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..d99f6b5 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f23ab5ccc95d76294b7388b54849071dde75a9d2f0e74701162b4d9e5284ecd +size 4675893664 diff --git a/ChimeraLlama-3-8B-v2.i1-Q4_K_M.gguf b/ChimeraLlama-3-8B-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..da018a7 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d54ebba98162b5fe6275b46be0a97b13244262684826e44922b3a310eda788f +size 4920736160 diff --git a/ChimeraLlama-3-8B-v2.i1-Q4_K_S.gguf b/ChimeraLlama-3-8B-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b1c30ae --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d8859ac0ee9aed3023e6abbe36b91907ceff415096678a8204eecc5e8b246e +size 4692670880 diff --git a/ChimeraLlama-3-8B-v2.i1-Q5_K_M.gguf b/ChimeraLlama-3-8B-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7aa035a --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c3b54c77f0f4cedbd3440f25806b296a5ff8efd7febfc55710b932c6308c47 +size 5732989344 diff --git a/ChimeraLlama-3-8B-v2.i1-Q5_K_S.gguf b/ChimeraLlama-3-8B-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..dcf8fe0 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a65b6522364eae60d4d7bb33e8769a3675bb5cc5fb2ec7fc5ddfa511091699c +size 5599295904 diff --git a/ChimeraLlama-3-8B-v2.i1-Q6_K.gguf b/ChimeraLlama-3-8B-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..bf7adb3 --- /dev/null +++ b/ChimeraLlama-3-8B-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a066928c2e575aa9d53920bf16f9588f12183e1d03ad543b7e2cfd84bd0aa7f +size 6596008352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3c3a711 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: mlabonne/ChimeraLlama-3-8B-v2 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2 + + +static quants are available at https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-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-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF/resolve/main/ChimeraLlama-3-8B-v2.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..9cef1c2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044fc376ff0a5da57f7fe4d79b6833894c698a16a79daaa880d1b47070c694ae +size 4988157