commit 8f3c4dace673c4485c2f3959c33759dac2b9452b Author: ModelHub XC Date: Sat Sep 26 22:45:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3SOME-8B-v2a-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da78a48 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Llama-3SOME-8B-v2a.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2a.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3SOME-8B-v2a.IQ3_M.gguf b/Llama-3SOME-8B-v2a.IQ3_M.gguf new file mode 100644 index 0000000..28be83a --- /dev/null +++ b/Llama-3SOME-8B-v2a.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d8a86c26be5b15dba5bace4f30ee870dcf511354b24298d57fac83b64f0ff1 +size 3784823552 diff --git a/Llama-3SOME-8B-v2a.IQ3_S.gguf b/Llama-3SOME-8B-v2a.IQ3_S.gguf new file mode 100644 index 0000000..3fa7f87 --- /dev/null +++ b/Llama-3SOME-8B-v2a.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91d857059ea2928882ef12ca0214bb2d472a19a5fcc6c770bc2d465cb04e6c0 +size 3682325248 diff --git a/Llama-3SOME-8B-v2a.IQ3_XS.gguf b/Llama-3SOME-8B-v2a.IQ3_XS.gguf new file mode 100644 index 0000000..3938c1f --- /dev/null +++ b/Llama-3SOME-8B-v2a.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7230ad52dda47da34cbe9ad05f0b272dccc7eb9241d289e8d1ee79e736e1abb +size 3518747392 diff --git a/Llama-3SOME-8B-v2a.IQ4_XS.gguf b/Llama-3SOME-8B-v2a.IQ4_XS.gguf new file mode 100644 index 0000000..f67ae65 --- /dev/null +++ b/Llama-3SOME-8B-v2a.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42190a420f2cabed19ffbfef5e6cf154fce39f46813d0e0733fadfa24a92b5d9 +size 4484363008 diff --git a/Llama-3SOME-8B-v2a.Q2_K.gguf b/Llama-3SOME-8B-v2a.Q2_K.gguf new file mode 100644 index 0000000..477d6be --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd5a57f151c867142b76b40d0b9a3d3612a46d47a1e78aa63c64dcc0ff0b2aa +size 3179131648 diff --git a/Llama-3SOME-8B-v2a.Q3_K_L.gguf b/Llama-3SOME-8B-v2a.Q3_K_L.gguf new file mode 100644 index 0000000..7af1563 --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7e8b5d0b4c735cce7e84f95db81da2e54c94e57223660902069e1daaea647d +size 4321956608 diff --git a/Llama-3SOME-8B-v2a.Q3_K_M.gguf b/Llama-3SOME-8B-v2a.Q3_K_M.gguf new file mode 100644 index 0000000..56d4a7c --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e195888d723da88f1aba9e629952adde2a6be6e5f30efb24023ea4a7b9c7ee +size 4018918144 diff --git a/Llama-3SOME-8B-v2a.Q3_K_S.gguf b/Llama-3SOME-8B-v2a.Q3_K_S.gguf new file mode 100644 index 0000000..c5e28c8 --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba701802b9783734eb3601dbe598dd96d69c825ede8034652aa17dc7b4bbe06 +size 3664499456 diff --git a/Llama-3SOME-8B-v2a.Q4_K_M.gguf b/Llama-3SOME-8B-v2a.Q4_K_M.gguf new file mode 100644 index 0000000..830cc25 --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04c44f168ff4c2c78ca0a7f738b804b9090ad84f9f5d10cbdbe348f03d3aa511 +size 4920734464 diff --git a/Llama-3SOME-8B-v2a.Q4_K_S.gguf b/Llama-3SOME-8B-v2a.Q4_K_S.gguf new file mode 100644 index 0000000..88b2a4c --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e9ee02aaa57dcaa3d91d7cbf7ab0fe2bd9eb9cc592cf28f227cfcf18d5ae7c +size 4692669184 diff --git a/Llama-3SOME-8B-v2a.Q5_K_M.gguf b/Llama-3SOME-8B-v2a.Q5_K_M.gguf new file mode 100644 index 0000000..0991e8c --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbcfb56fda515a80155be5440b5363a92501d49c2916b2331bcc87ba0ff3352 +size 5732987648 diff --git a/Llama-3SOME-8B-v2a.Q5_K_S.gguf b/Llama-3SOME-8B-v2a.Q5_K_S.gguf new file mode 100644 index 0000000..41d3107 --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf26af7bc6121371be6e9f635d6ae27a14256e924c63b04aa0329696e37c19f1 +size 5599294208 diff --git a/Llama-3SOME-8B-v2a.Q6_K.gguf b/Llama-3SOME-8B-v2a.Q6_K.gguf new file mode 100644 index 0000000..eed302e --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c85536566a8a11c6b6c3a45843e44ab6426c6f0c41f75cbad3978d7e10f43f +size 6596006656 diff --git a/Llama-3SOME-8B-v2a.Q8_0.gguf b/Llama-3SOME-8B-v2a.Q8_0.gguf new file mode 100644 index 0000000..1600514 --- /dev/null +++ b/Llama-3SOME-8B-v2a.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75774d91d9b2bf2504aff030cd2ef2887844356352e1a55549557177bd1f9354 +size 8540771072 diff --git a/Llama-3SOME-8B-v2a.f16.gguf b/Llama-3SOME-8B-v2a.f16.gguf new file mode 100644 index 0000000..38d81ae --- /dev/null +++ b/Llama-3SOME-8B-v2a.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401d2f9260ee7e9352751bc4f59b2e02db7e9ccd5f25d51bbeadc8e74a34fea7 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b65446 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: BeaverAI/Llama-3SOME-8B-v2a +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BeaverAI/Llama-3SOME-8B-v2a + + +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/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2a-GGUF/resolve/main/Llama-3SOME-8B-v2a.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. + +