commit 82ced785a288f66b0359f1cb4d84e946bba11975 Author: ModelHub XC Date: Thu Sep 24 03:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3base-bsln-t4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..978325a --- /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 +llama3base-bsln-t4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3base-bsln-t4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..266fd49 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Windy/llama3base-bsln-t4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Windy/llama3base-bsln-t4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3base-bsln-t4-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/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3base-bsln-t4-GGUF/resolve/main/llama3base-bsln-t4.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/llama3base-bsln-t4.IQ4_XS.gguf b/llama3base-bsln-t4.IQ4_XS.gguf new file mode 100644 index 0000000..ff85a65 --- /dev/null +++ b/llama3base-bsln-t4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a3befc052f3507d4a7640c21b5e975d174d1194d9a4de52bcc8155a4a06879 +size 4484363104 diff --git a/llama3base-bsln-t4.Q2_K.gguf b/llama3base-bsln-t4.Q2_K.gguf new file mode 100644 index 0000000..73a1d01 --- /dev/null +++ b/llama3base-bsln-t4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0d99de99afe21a7b5437ecbd52a573d441fbba8a6d25fc03d190079c38ba51 +size 3179131744 diff --git a/llama3base-bsln-t4.Q3_K_L.gguf b/llama3base-bsln-t4.Q3_K_L.gguf new file mode 100644 index 0000000..019df94 --- /dev/null +++ b/llama3base-bsln-t4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641cd43febe42f9e676878b235097481f499841e0de409a8aab429c10221efb1 +size 4321956704 diff --git a/llama3base-bsln-t4.Q3_K_M.gguf b/llama3base-bsln-t4.Q3_K_M.gguf new file mode 100644 index 0000000..cd795c5 --- /dev/null +++ b/llama3base-bsln-t4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cc50265ccdef22ac8b1c622a6722a89e83003aa24e8e4faaea3a519e3e9ef6 +size 4018918240 diff --git a/llama3base-bsln-t4.Q3_K_S.gguf b/llama3base-bsln-t4.Q3_K_S.gguf new file mode 100644 index 0000000..3fff1c1 --- /dev/null +++ b/llama3base-bsln-t4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74459a12008729558cab8d9e89746ff2f3441200ad8ba3ae84f0a58ca7fcdba +size 3664499552 diff --git a/llama3base-bsln-t4.Q4_K_M.gguf b/llama3base-bsln-t4.Q4_K_M.gguf new file mode 100644 index 0000000..6cc03eb --- /dev/null +++ b/llama3base-bsln-t4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6cf58ef1efb702bb67a2a4645dea8039e9f99292df94223634522a717c5860b +size 4920734560 diff --git a/llama3base-bsln-t4.Q4_K_S.gguf b/llama3base-bsln-t4.Q4_K_S.gguf new file mode 100644 index 0000000..bf95ecd --- /dev/null +++ b/llama3base-bsln-t4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e320b1ef0d73fab0bebf89e6a0e5e3b2badcb35fb9cdb14ba6d13aa2b52f06ac +size 4692669280 diff --git a/llama3base-bsln-t4.Q5_K_M.gguf b/llama3base-bsln-t4.Q5_K_M.gguf new file mode 100644 index 0000000..e0e0977 --- /dev/null +++ b/llama3base-bsln-t4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c17b9602734dc3a6bcc49d1951423a39d87177dbd2988c128479b24ad91d12fd +size 5732987744 diff --git a/llama3base-bsln-t4.Q5_K_S.gguf b/llama3base-bsln-t4.Q5_K_S.gguf new file mode 100644 index 0000000..733f12c --- /dev/null +++ b/llama3base-bsln-t4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8886973ae70aa44dd87bb9ae9147514156ea98066d93f486f63ed08fc0720b18 +size 5599294304 diff --git a/llama3base-bsln-t4.Q6_K.gguf b/llama3base-bsln-t4.Q6_K.gguf new file mode 100644 index 0000000..9ab9f1d --- /dev/null +++ b/llama3base-bsln-t4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98728ffd105a6b56075cc68f4942a02a80ab71d0a8c26d8f019fafcd984c691e +size 6596006752 diff --git a/llama3base-bsln-t4.Q8_0.gguf b/llama3base-bsln-t4.Q8_0.gguf new file mode 100644 index 0000000..a2df721 --- /dev/null +++ b/llama3base-bsln-t4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876b291074a0d9e1b9d702fe8bf47e6710e0f80116cbc0f8e92fd1a6a36f98fd +size 8540771168 diff --git a/llama3base-bsln-t4.f16.gguf b/llama3base-bsln-t4.f16.gguf new file mode 100644 index 0000000..3dc1258 --- /dev/null +++ b/llama3base-bsln-t4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52af56022eac870405cd7335b4644e63e048ace26430360a94839ae8b5a1c4b4 +size 16068891488