commit 5c45a0688d761648798f56e3dca7764b3410d9f5 Author: ModelHub XC Date: Tue Jun 2 15:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mnemosyne-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f427ae --- /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 +Mnemosyne-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mnemosyne-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mnemosyne-3B.IQ4_XS.gguf b/Mnemosyne-3B.IQ4_XS.gguf new file mode 100644 index 0000000..3b3e78c --- /dev/null +++ b/Mnemosyne-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99003e3c1c6e613bd783c2b0bc73e2bf6e06116f73d5d17a116fe7e572b65adc +size 1753185152 diff --git a/Mnemosyne-3B.Q2_K.gguf b/Mnemosyne-3B.Q2_K.gguf new file mode 100644 index 0000000..ae9ad5e --- /dev/null +++ b/Mnemosyne-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156d82085c12582490a385fd0662a4feda350a9f4afcea97fe2913682a47fd0b +size 1274755968 diff --git a/Mnemosyne-3B.Q3_K_L.gguf b/Mnemosyne-3B.Q3_K_L.gguf new file mode 100644 index 0000000..1dfe495 --- /dev/null +++ b/Mnemosyne-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eec054b75652dddb381b77d6c6afc275e1966e19ee10804241ffd03a4e104c2 +size 1707391872 diff --git a/Mnemosyne-3B.Q3_K_M.gguf b/Mnemosyne-3B.Q3_K_M.gguf new file mode 100644 index 0000000..4ccd794 --- /dev/null +++ b/Mnemosyne-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e02b0208881ca598e80f97e0957e37b9235c3d46702193ba437abe1c47ac8bd +size 1590475648 diff --git a/Mnemosyne-3B.Q3_K_S.gguf b/Mnemosyne-3B.Q3_K_S.gguf new file mode 100644 index 0000000..dcfa6f5 --- /dev/null +++ b/Mnemosyne-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1346ed378c2a151507b4afd96ccae59340bfa8fd8f3cf3c1af8a231dcb86f90 +size 1454357376 diff --git a/Mnemosyne-3B.Q4_K_M.gguf b/Mnemosyne-3B.Q4_K_M.gguf new file mode 100644 index 0000000..cfab506 --- /dev/null +++ b/Mnemosyne-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1bf78fb1535836bc10de758393ea4b48d83eb7bcc704a67f37dc7d7487bd6b +size 1929902976 diff --git a/Mnemosyne-3B.Q4_K_S.gguf b/Mnemosyne-3B.Q4_K_S.gguf new file mode 100644 index 0000000..82270b2 --- /dev/null +++ b/Mnemosyne-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e15f1aa44f092daec2fbc09f39193d210ecf25209425252e7641d67fd679f5 +size 1834384256 diff --git a/Mnemosyne-3B.Q5_K_M.gguf b/Mnemosyne-3B.Q5_K_M.gguf new file mode 100644 index 0000000..ed389bc --- /dev/null +++ b/Mnemosyne-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366e055ba86fbbf0dbdc39db36419a7953116a9ea3740adc8b4a774f9eb50a89 +size 2224814976 diff --git a/Mnemosyne-3B.Q5_K_S.gguf b/Mnemosyne-3B.Q5_K_S.gguf new file mode 100644 index 0000000..b15e27c --- /dev/null +++ b/Mnemosyne-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e8a05ac7618231104f6072e0e1570951dd19942456690c40a162f213d15f8f +size 2169666432 diff --git a/Mnemosyne-3B.Q6_K.gguf b/Mnemosyne-3B.Q6_K.gguf new file mode 100644 index 0000000..d673d9f --- /dev/null +++ b/Mnemosyne-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c38ff0775dcbec47bd11181d4d74ed88e1eed7e36c58e5685c9bdfa5238c15d +size 2538158976 diff --git a/Mnemosyne-3B.Q8_0.gguf b/Mnemosyne-3B.Q8_0.gguf new file mode 100644 index 0000000..b7e4309 --- /dev/null +++ b/Mnemosyne-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d1ec5f8a0e8bde45774f13726fdee73be030028228ecb7c7312f86d7420e16 +size 3285476224 diff --git a/Mnemosyne-3B.f16.gguf b/Mnemosyne-3B.f16.gguf new file mode 100644 index 0000000..cf010fb --- /dev/null +++ b/Mnemosyne-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72e1472ca8f6ff1d22d976e09af5201a6756d1a32136f9df3ba674af4c284af +size 6178317184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ab498e --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: EphAsad/Mnemosyne-3B +datasets: +- b-mc2/sql-create-context +- gretelai/synthetic_text_to_sql +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-to-sql +- sql +- lims +- laboratory +- food-safety +- water-quality +- microbiology +- qwen2.5 +- unsloth +- qlora +- finetuned +--- +## About + + + + + + + + + +static quants of https://huggingface.co/EphAsad/Mnemosyne-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mnemosyne-3B-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/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mnemosyne-3B-GGUF/resolve/main/Mnemosyne-3B.f16.gguf) | f16 | 6.3 | 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. + +