From 2245779869d2c33759efcadf1c3da1a1ef63125b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 20 Oct 2026 04:32:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/llama-3-8B-rpg-v4-i1-GGUF Source: Original Platform --- .gitattributes | 57 ++++++++++++++++++++++++ README.md | 73 +++++++++++++++++++++++++++++++ imatrix.dat | 3 ++ llama-3-8B-rpg-v4.i1-IQ1_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ1_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ2_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ2_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ2_XS.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ3_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ3_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ3_XS.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf | 3 ++ llama-3-8B-rpg-v4.i1-IQ4_XS.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q2_K.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q3_K_L.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q3_K_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q3_K_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q4_0.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q4_K_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q4_K_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q5_K_M.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q5_K_S.gguf | 3 ++ llama-3-8B-rpg-v4.i1-Q6_K.gguf | 3 ++ 24 files changed, 196 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 llama-3-8B-rpg-v4.i1-IQ1_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ1_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ2_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ2_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ2_XS.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ3_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ3_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ3_XS.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf create mode 100644 llama-3-8B-rpg-v4.i1-IQ4_XS.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q2_K.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q3_K_L.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q3_K_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q3_K_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q4_0.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q4_K_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q4_K_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q5_K_M.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q5_K_S.gguf create mode 100644 llama-3-8B-rpg-v4.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95ceb11 --- /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 +llama-3-8B-rpg-v4.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-rpg-v4.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ca5925 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: osouza/llama-3-8B-rpg-v4 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/osouza/llama-3-8B-rpg-v4 + + +static quants are available at https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-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-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-rpg-v4-i1-GGUF/resolve/main/llama-3-8B-rpg-v4.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..68de4f1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594c645b698290a708861f414cdabfbc909a9262d3974a0ba6ce174a64158140 +size 4988143 diff --git a/llama-3-8B-rpg-v4.i1-IQ1_M.gguf b/llama-3-8B-rpg-v4.i1-IQ1_M.gguf new file mode 100644 index 0000000..13a2e3d --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f5eafaf234a18b008e6c275dd194fb8d95e40250d9d79d45e6b4472307ff53 +size 2161972192 diff --git a/llama-3-8B-rpg-v4.i1-IQ1_S.gguf b/llama-3-8B-rpg-v4.i1-IQ1_S.gguf new file mode 100644 index 0000000..c2152af --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f0f1f5cd643fab0d838763b0332fca26c630b9eb8f9bfd219c26c7837cf17b +size 2019628000 diff --git a/llama-3-8B-rpg-v4.i1-IQ2_M.gguf b/llama-3-8B-rpg-v4.i1-IQ2_M.gguf new file mode 100644 index 0000000..cc70ffe --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67f9e53d9e22cd41d659069099c4ccaf84e38694ac264f77d514d9214174c40 +size 2948281312 diff --git a/llama-3-8B-rpg-v4.i1-IQ2_S.gguf b/llama-3-8B-rpg-v4.i1-IQ2_S.gguf new file mode 100644 index 0000000..b3c275a --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8321ce07c2be58a2dc9043f99c3901b1748d57227ae118fdc82a0a1f73774021 +size 2758489056 diff --git a/llama-3-8B-rpg-v4.i1-IQ2_XS.gguf b/llama-3-8B-rpg-v4.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3489cb0 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbbc9cbb06f20e862034a1557ae14b8f06b472829cf4f3ae02cee7d8a3892e61 +size 2605781984 diff --git a/llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf b/llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d5e0dbb --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f908eb6df45d471b7e3af6349f448916f3be2720729d52a1a03dff641542b0dc +size 2399212512 diff --git a/llama-3-8B-rpg-v4.i1-IQ3_M.gguf b/llama-3-8B-rpg-v4.i1-IQ3_M.gguf new file mode 100644 index 0000000..f2c8c8b --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3db4ff0298f989426c9271303f235f9b3d5f699f999debfac7f52ca4581688 +size 3784823776 diff --git a/llama-3-8B-rpg-v4.i1-IQ3_S.gguf b/llama-3-8B-rpg-v4.i1-IQ3_S.gguf new file mode 100644 index 0000000..6dd4283 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19c610cec973dd6746e8a36236772a0a056664bf868ad60bf59087fd1978460 +size 3682325472 diff --git a/llama-3-8B-rpg-v4.i1-IQ3_XS.gguf b/llama-3-8B-rpg-v4.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f7beed5 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adfd47480e8e675b2bed21dae1502ca5f1bc6f497963719a72851f986238312 +size 3518747616 diff --git a/llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf b/llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..51a8452 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3caaa841ecabed21849427ff7f4086e3e32f3bd04393c3c34ff99cb35c2475 +size 3274912736 diff --git a/llama-3-8B-rpg-v4.i1-IQ4_XS.gguf b/llama-3-8B-rpg-v4.i1-IQ4_XS.gguf new file mode 100644 index 0000000..16ac724 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15227cbf906a5dbd609c11d76986e298629553a22b893edf0596ca0acc2b4b47 +size 4447663072 diff --git a/llama-3-8B-rpg-v4.i1-Q2_K.gguf b/llama-3-8B-rpg-v4.i1-Q2_K.gguf new file mode 100644 index 0000000..2657d72 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:660de687a8db7a4d4a23a2ecff292eda4c5d7528b246df645e3a5f0ed04b9f6c +size 3179131872 diff --git a/llama-3-8B-rpg-v4.i1-Q3_K_L.gguf b/llama-3-8B-rpg-v4.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b9fcc15 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed18b57316c04830e0f2c9e58755e11da63ff4bd416a623933789f54d5f13595 +size 4321956832 diff --git a/llama-3-8B-rpg-v4.i1-Q3_K_M.gguf b/llama-3-8B-rpg-v4.i1-Q3_K_M.gguf new file mode 100644 index 0000000..adbb73a --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113d73981abd66666bbb463e8368e88fd7c521c322312e6b7804b33f61999242 +size 4018918368 diff --git a/llama-3-8B-rpg-v4.i1-Q3_K_S.gguf b/llama-3-8B-rpg-v4.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1a1b68f --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ca726910dc62c3bb23d1ffd66fbcfedc5bb57a709f741127f4bcd78c73314c +size 3664499680 diff --git a/llama-3-8B-rpg-v4.i1-Q4_0.gguf b/llama-3-8B-rpg-v4.i1-Q4_0.gguf new file mode 100644 index 0000000..d5ffcfa --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a87fe294d704d401759eec13dcb36df9113ad88e06e24e0b91f34189a0bf69 +size 4675892192 diff --git a/llama-3-8B-rpg-v4.i1-Q4_K_M.gguf b/llama-3-8B-rpg-v4.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e12eff0 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce35bc1b626eb3be819e9e094cf1fafd73ce17883438e4e42eb3f2c21916a5b +size 4920734688 diff --git a/llama-3-8B-rpg-v4.i1-Q4_K_S.gguf b/llama-3-8B-rpg-v4.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9d5bda3 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743a085f06933862d951f6c9d69f9161909d11b372610fef3fe6290d1abd3cfa +size 4692669408 diff --git a/llama-3-8B-rpg-v4.i1-Q5_K_M.gguf b/llama-3-8B-rpg-v4.i1-Q5_K_M.gguf new file mode 100644 index 0000000..88df770 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e73139777e67245608a584fdd7fb5e816235f1129f38adb0f760d7fcd3803a4 +size 5732987872 diff --git a/llama-3-8B-rpg-v4.i1-Q5_K_S.gguf b/llama-3-8B-rpg-v4.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7e25aca --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a45b4162e3dc71db5f8dc725a2387e255f72c653cc2ef444e689365b967370 +size 5599294432 diff --git a/llama-3-8B-rpg-v4.i1-Q6_K.gguf b/llama-3-8B-rpg-v4.i1-Q6_K.gguf new file mode 100644 index 0000000..0312079 --- /dev/null +++ b/llama-3-8B-rpg-v4.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ca03e48204576d0e2731eb057b0120743c250126a566f21fc64ba78f11e8ba +size 6596006880