commit 3c59b6d6406032d7f8d191f624b09b469640da21 Author: ModelHub XC Date: Thu Jul 30 21:35:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-1m-PoSE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..71d8444 --- /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 +llama-3-8b-1m-PoSE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-1m-PoSE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..01b3689 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: winglian/llama-3-8b-1m-PoSE +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- facebook +- meta +- pytorch +- llama +- llama-3 +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/winglian/llama-3-8b-1m-PoSE + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-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/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-1m-PoSE-GGUF/resolve/main/llama-3-8b-1m-PoSE.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-3-8b-1m-PoSE.IQ4_XS.gguf b/llama-3-8b-1m-PoSE.IQ4_XS.gguf new file mode 100644 index 0000000..e1a1fe0 --- /dev/null +++ b/llama-3-8b-1m-PoSE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d19ab938b18fc9316b63f5ac0b5751de3b826189a7234f339e30ffd51f4624a +size 4484363008 diff --git a/llama-3-8b-1m-PoSE.Q2_K.gguf b/llama-3-8b-1m-PoSE.Q2_K.gguf new file mode 100644 index 0000000..3791372 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeab97a7aeac8ea3ec9cd84c7263ffde9cbfec43a39fb278d3c82af311bb7f2 +size 3179131648 diff --git a/llama-3-8b-1m-PoSE.Q3_K_L.gguf b/llama-3-8b-1m-PoSE.Q3_K_L.gguf new file mode 100644 index 0000000..142f3e0 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828ae92dc50f0feffbb9d9e8d2e2ad8c8555c211cbaa07779e57a36993ed8563 +size 4321956608 diff --git a/llama-3-8b-1m-PoSE.Q3_K_M.gguf b/llama-3-8b-1m-PoSE.Q3_K_M.gguf new file mode 100644 index 0000000..eb8a125 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9723502cf780fc632e981e9352b98c966506274dcfde36504c8fe0523f19a9a0 +size 4018918144 diff --git a/llama-3-8b-1m-PoSE.Q3_K_S.gguf b/llama-3-8b-1m-PoSE.Q3_K_S.gguf new file mode 100644 index 0000000..1caf1a2 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc9d4ccaa1cc915b038a7af95f99fe53323fef85f7273e7c4ecf9aa3060cc55 +size 3664499456 diff --git a/llama-3-8b-1m-PoSE.Q4_K_M.gguf b/llama-3-8b-1m-PoSE.Q4_K_M.gguf new file mode 100644 index 0000000..c280036 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d833e34dd2a3b93bacad94f4c1775776a84c5ceb90506016b93fcb1df450efe +size 4920734464 diff --git a/llama-3-8b-1m-PoSE.Q4_K_S.gguf b/llama-3-8b-1m-PoSE.Q4_K_S.gguf new file mode 100644 index 0000000..2a3210d --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539b327d951918b6aae108c54d42e633085d4015388570ba8777c7ca18dd3d52 +size 4692669184 diff --git a/llama-3-8b-1m-PoSE.Q5_K_M.gguf b/llama-3-8b-1m-PoSE.Q5_K_M.gguf new file mode 100644 index 0000000..f22c3df --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94d1f6272f7f3ee5acc1efbaf172ff9119da7a35ecf097940073380982d2544 +size 5732987648 diff --git a/llama-3-8b-1m-PoSE.Q5_K_S.gguf b/llama-3-8b-1m-PoSE.Q5_K_S.gguf new file mode 100644 index 0000000..e3f0e6f --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c52eeb3d1394dfb0aa3828bf6a49bb6674152400557f433c199a7a5ee72043 +size 5599294208 diff --git a/llama-3-8b-1m-PoSE.Q6_K.gguf b/llama-3-8b-1m-PoSE.Q6_K.gguf new file mode 100644 index 0000000..f0719a0 --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16fe14fcfee4a0cea6c0b1fcbfde23f3121e59e73710be153faa84d6bdf20ea4 +size 6596006656 diff --git a/llama-3-8b-1m-PoSE.Q8_0.gguf b/llama-3-8b-1m-PoSE.Q8_0.gguf new file mode 100644 index 0000000..81135aa --- /dev/null +++ b/llama-3-8b-1m-PoSE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aceff848e01951f3ac2c2054c54b82d70c3372403f5a2328aa0ab9677ddfc0ee +size 8540771072 diff --git a/llama-3-8b-1m-PoSE.f16.gguf b/llama-3-8b-1m-PoSE.f16.gguf new file mode 100644 index 0000000..f6b60b8 --- /dev/null +++ b/llama-3-8b-1m-PoSE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69417ee54c439d0b8de8c7698181fffe02442805a9074a01067301005f677438 +size 16068891392