commit f1c0583e3dbc1a6364ee38ad5d1bde51d197c072 Author: ModelHub XC Date: Wed Jun 24 21:20:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e3660c2 --- /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 +MASID-v1_Llama-3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MASID-v1_Llama-3.1-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MASID-v1_Llama-3.1-8B-Instruct.IQ4_XS.gguf b/MASID-v1_Llama-3.1-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..f94fce5 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63b8b554e8042c4ecd400258a6bfe80f5dec571602ff1b51c7821888c30e2030 +size 4484367968 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q2_K.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..d3cd7ff --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff69f65706314cfc99db74481498d74f7db7592655e293609ff518e9548aec2 +size 3179136608 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_L.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9ea2e6a --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ae13873c3bae80e882ff35759aa4ef42d7ee5f51e0ae77dcfe8bda613e8f42 +size 4321961568 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_M.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..05b8b48 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4de6fe5dd2c937d712dc5b9430462cbc2c5170922c764cb9822b48ed8d6903 +size 4018923104 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_S.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bfa9722 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ff066a479b57ac403af62ed35914636e83f08bc8b7dc542f4f22a3cd8f8492 +size 3664504416 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_M.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..96d03ad --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7a94bd8c5e0479db450a7e6a1a5c0309430c97ad518cf58735188a9efafc1b +size 4920739424 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_S.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..987b8a3 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae88da196d9e65a419d342ae3bf4d99b0cccbc823b88bfdfcc1c75b36fddc70e +size 4692674144 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_M.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..6528754 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fc38722c366ca96ef4d3f0f73a1bec42e94692ab7b8ed30a293ce5c237088f +size 5732992608 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_S.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..bef60c6 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e099ddc90521b9734121b914af341f16508f458e264b533047f3ea729edb2d +size 5599299168 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q6_K.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..31db870 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dd13ee86ce4273ca2eb98ea1ecf06265c655285f30bceb5d214928699c4b64 +size 6596011616 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.Q8_0.gguf b/MASID-v1_Llama-3.1-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..cc34cd1 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84d404a3bb56c9be13dc8b482b935d4a2a53373f687dcdfbc544bdf9cfa87d5 +size 8540776032 diff --git a/MASID-v1_Llama-3.1-8B-Instruct.f16.gguf b/MASID-v1_Llama-3.1-8B-Instruct.f16.gguf new file mode 100644 index 0000000..fe02b16 --- /dev/null +++ b/MASID-v1_Llama-3.1-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3795819a289ec6239f05fe4ce0d227a432a696fb8fad610597bf9ebb90b9fb +size 16068896352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..70e78fb --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: joackimagno/MASID-v1_Llama-3.1-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/joackimagno/MASID-v1_Llama-3.1-8B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MASID-v1_Llama-3.1-8B-Instruct-GGUF).*** + +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/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MASID-v1_Llama-3.1-8B-Instruct-GGUF/resolve/main/MASID-v1_Llama-3.1-8B-Instruct.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. + +