commit 0e9513639a7a5ed29a6305c78f3b111676935bda Author: ModelHub XC Date: Tue Jun 30 17:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0239f3c --- /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 +aise-llama3-8b-smol-smoltalk-sv.f16.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aise-llama3-8b-smol-smoltalk-sv.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..def142c --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: liu-nlp/aise-llama3-8b-smol-smoltalk-sv +language: +- en +library_name: transformers +model_name: aise-llama3-8b-smol-smoltalk-sv +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- sft +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/liu-nlp/aise-llama3-8b-smol-smoltalk-sv + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#aise-llama3-8b-smol-smoltalk-sv-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/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/aise-llama3-8b-smol-smoltalk-sv-GGUF/resolve/main/aise-llama3-8b-smol-smoltalk-sv.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. + + diff --git a/aise-llama3-8b-smol-smoltalk-sv.IQ4_XS.gguf b/aise-llama3-8b-smol-smoltalk-sv.IQ4_XS.gguf new file mode 100644 index 0000000..55bf8c3 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875a2f8262d6a7a6324202e092f424859ab0afb805f86038823af9b577f75c3e +size 4484374688 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q2_K.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q2_K.gguf new file mode 100644 index 0000000..251ddec --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc2f81a58309dbb01251026dbf20f8248447fe9ce0b2132f41789008f00b901 +size 3179141664 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q3_K_L.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_L.gguf new file mode 100644 index 0000000..a2e5d95 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53991a257075a63e9bcb04ff15d28d0ab34226908e2846590be125abb0ca2ab3 +size 4321967456 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q3_K_M.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_M.gguf new file mode 100644 index 0000000..9a8d0c2 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d45ac42ec3152e532069c956ed7cbc37c1fb1ca92acf277d5c23f5fc3561c11 +size 4018928992 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q3_K_S.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_S.gguf new file mode 100644 index 0000000..b099c32 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f901416c5e80ae9205654293b9d2f5b132a7ef591d0a61821aa05d434716d2 +size 3664510304 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q4_K_M.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q4_K_M.gguf new file mode 100644 index 0000000..4a49cb8 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b72e79b1bd04ae0820ff28312eec9ac1332fe2e0eb3e4da928ba7aa5d3f131 +size 4920746400 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q4_K_S.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q4_K_S.gguf new file mode 100644 index 0000000..df8d7b7 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ef35b354130f0c0edeffca9475ce923bb2e0c48e7c4fe4986d37fcb596e273 +size 4692681120 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q5_K_M.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q5_K_M.gguf new file mode 100644 index 0000000..bb6dbef --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004542e17fca3fe3e2686d2e699139aa81136c842f4d8cb6b9cc7c4b3f615050 +size 5733000608 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q5_K_S.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q5_K_S.gguf new file mode 100644 index 0000000..e516cf4 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8bd15012c2f761a61ba6def6e3c3ab9b16c3b5460e812eecd9c8ce13b8d7d5 +size 5599307168 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q6_K.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q6_K.gguf new file mode 100644 index 0000000..57d1e40 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9597667ced3396c75727ad2eea3f39608475cfc9ec649d17746d8ae4d7fcfb14 +size 6596020704 diff --git a/aise-llama3-8b-smol-smoltalk-sv.Q8_0.gguf b/aise-llama3-8b-smol-smoltalk-sv.Q8_0.gguf new file mode 100644 index 0000000..88fa3d3 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e0d59c985e0e7a053039ae8d8d055cf6520591b16ae072ef6cac24ef766e36 +size 8540789088 diff --git a/aise-llama3-8b-smol-smoltalk-sv.f16.gguf b/aise-llama3-8b-smol-smoltalk-sv.f16.gguf new file mode 100644 index 0000000..82b93b0 --- /dev/null +++ b/aise-llama3-8b-smol-smoltalk-sv.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad9e33d87d62aba9201d251012fef211e4cababdaa4d0451791b8a7df8a79ff +size 16068924768