commit 6c8419f67b0f47ef35cb3672c4cb38fddd6418c8 Author: ModelHub XC Date: Sun Jun 28 14:20:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fcec82c --- /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 +EXAONE-3.0-7.8B-Instruct-converted.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.f16.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.0-7.8B-Instruct-converted.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EXAONE-3.0-7.8B-Instruct-converted.IQ4_XS.gguf b/EXAONE-3.0-7.8B-Instruct-converted.IQ4_XS.gguf new file mode 100644 index 0000000..0be3d75 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7c1f66a34b1379fb52b67d8770bce36e72cac9dd907cc4baebb65f9fbc69ac +size 4337588096 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q2_K.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q2_K.gguf new file mode 100644 index 0000000..300c29d --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5e8f938722e1b3bdffdb111289bdd7d950ef72ed5c9ed40640d08d8a76b77c +size 3053868928 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_L.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_L.gguf new file mode 100644 index 0000000..514da03 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca0aa01d90409566ab110ef90341d6c57145f455042356dd5e6a86317b30274 +size 4185937792 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_M.gguf new file mode 100644 index 0000000..556c999 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc0f699e8f2ed25c0a55b4018d80981558cb4331448765d09192cd9e08955e6 +size 3882899328 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_S.gguf new file mode 100644 index 0000000..5d090b1 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4845c1b2ed2d6e86e9ee941e8d62ace8cfaa2c9dd4701cb76fc64525c2512327 +size 3528480640 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_M.gguf new file mode 100644 index 0000000..30d975e --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a454b7715b71a194c059a901acbeeecdab2bb66c81c5a44ca4c9459209d18e1a +size 4770649984 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_S.gguf new file mode 100644 index 0000000..6681abc --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609b0d64bffd43d483d92f3777f8b74d93ac1e9593f13cc70bfeb09a9dfde793 +size 4542584704 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_M.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_M.gguf new file mode 100644 index 0000000..ea5dba3 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8935cb03e604e92f126df66fe38b153fcb773dcfcfed4f7faec7a3b5c8df5515 +size 5569664896 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_S.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_S.gguf new file mode 100644 index 0000000..e47d226 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133d26cd0d98d3bff9d9b1f604bb8008aa62d2b529967ee1df76eba2cccaba03 +size 5435971456 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q6_K.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q6_K.gguf new file mode 100644 index 0000000..fbcdfcb --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9316a27d2a6e00fd3b197bbe691683965fbd668359ad4d898673ed91c5a2226 +size 6418618240 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.Q8_0.gguf b/EXAONE-3.0-7.8B-Instruct-converted.Q8_0.gguf new file mode 100644 index 0000000..d7cb822 --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d4adaef10964535ae0bb384f24a5a7c3c4988c61fd598d425f2b336b9eb27d +size 8312084352 diff --git a/EXAONE-3.0-7.8B-Instruct-converted.f16.gguf b/EXAONE-3.0-7.8B-Instruct-converted.f16.gguf new file mode 100644 index 0000000..5bf74fc --- /dev/null +++ b/EXAONE-3.0-7.8B-Instruct-converted.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41352e8efd8786b939e4686eb168d2ad524d445099cd25af7172c50b6eb4e4d9 +size 15641630592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..724eb2c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: furiosa-ai-dev/EXAONE-3.0-7.8B-Instruct-converted +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/furiosa-ai-dev/EXAONE-3.0-7.8B-Instruct-converted + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EXAONE-3.0-7.8B-Instruct-converted-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-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/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q3_K_L.gguf) | Q3_K_L | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q5_K_M.gguf) | Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q6_K.gguf) | Q6_K | 6.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-3.0-7.8B-Instruct-converted-GGUF/resolve/main/EXAONE-3.0-7.8B-Instruct-converted.f16.gguf) | f16 | 15.7 | 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. + +