From c40cfc51af97eafcb4aed8d98c95fabe75f341ba Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 19 May 2026 13:31:23 +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-3.1-8B-SmileyLlama-1.1-Mpro-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++ Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf | 3 + Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf | 3 + README.md | 72 +++++++++++++++++++ 14 files changed, 155 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf create mode 100644 Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aeafc83 --- /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-SmileyLlama-1.1-Mpro.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf new file mode 100644 index 0000000..015de25 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d726eafce11ca623f2f053a5763883ef8088d5dedef5b4e8f68d10e7ca816d9d +size 4484368288 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf new file mode 100644 index 0000000..bd840ff --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f0722ad779b2c29ea05ff350c9d00923865f6d82aaf69d5c84e1b56f5ced61 +size 3179136928 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf new file mode 100644 index 0000000..2621317 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ea5cac90f3e91c545eabcaa37d187f32d07e03bed5c4294be56891af68ad6e +size 4321961888 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf new file mode 100644 index 0000000..c82c0ba --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ad3e17d105b7dcc6d9bf21a3c8031778b2da044328cdb30ca67b7eb9d0311c +size 4018923424 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf new file mode 100644 index 0000000..c663f12 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00af6db898496a9d37900dcd56a491731484d6bede85e7679a53ee4ea860a0c8 +size 3664504736 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf new file mode 100644 index 0000000..cfcc5c8 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ceade2877b8b94e2565833df42aa4703554ae0cf89591dbaf2eb4183406b4d +size 4920739744 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf new file mode 100644 index 0000000..fa193b9 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:765eba6da328f9775149f137f491e68f7dcdd3352f5af8c56fa0a47a6b4d08aa +size 4692674464 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf new file mode 100644 index 0000000..5eb76fc --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ff43798540d21aee2f6c8bbdc013c892fa13d23248583b500582fd5564405a +size 5732992928 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf new file mode 100644 index 0000000..505f6cc --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda32c7fd0ea7275b0dd02fc03524768bf7ab6b4a69a8a92f2e4aed759c1460f +size 5599299488 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf new file mode 100644 index 0000000..79932f6 --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72bcc35065ec4ece48d7e9b8ac0a28f613f2034ac15ed33b8e6d8a20e2fa9531 +size 6596011936 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf new file mode 100644 index 0000000..a032e9f --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49611316eb3f44fe7bb6e2bffad31a76bcf213d2e51dac8934fc9d5fb399827a +size 8540776352 diff --git a/Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf new file mode 100644 index 0000000..a26114d --- /dev/null +++ b/Llama-3.1-8B-SmileyLlama-1.1-Mpro.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:192cb2635849b5c67784cda988785e30c360c9875b72e96cac1cf925d2dd8e0c +size 16068896672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2636faa --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: THGLab/Llama-3.1-8B-SmileyLlama-1.1-Mpro +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/THGLab/Llama-3.1-8B-SmileyLlama-1.1-Mpro + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-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-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-SmileyLlama-1.1-Mpro-GGUF/resolve/main/Llama-3.1-8B-SmileyLlama-1.1-Mpro.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. + +