commit 30c98590c734a69368d54452cce5e14ae0d30e19 Author: ModelHub XC Date: Sat Jul 11 03:08:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-linear-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0699862 --- /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 +llama3-8b-linear-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-linear-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ae5202 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Alelcv27/llama3-8b-linear-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Alelcv27/llama3-8b-linear-v2 + + +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/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-linear-v2-GGUF/resolve/main/llama3-8b-linear-v2.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/llama3-8b-linear-v2.IQ4_XS.gguf b/llama3-8b-linear-v2.IQ4_XS.gguf new file mode 100644 index 0000000..9bc1c0c --- /dev/null +++ b/llama3-8b-linear-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460ec0d219f8f860ce25114ee18104a23a86b12349553c7c67a452031c63a2ac +size 4484363744 diff --git a/llama3-8b-linear-v2.Q2_K.gguf b/llama3-8b-linear-v2.Q2_K.gguf new file mode 100644 index 0000000..b34213f --- /dev/null +++ b/llama3-8b-linear-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591f31a7c7fdc24bf398c661066abea49a506fae5b2291cbe56575aae82fc313 +size 3179132384 diff --git a/llama3-8b-linear-v2.Q3_K_L.gguf b/llama3-8b-linear-v2.Q3_K_L.gguf new file mode 100644 index 0000000..1c25ee7 --- /dev/null +++ b/llama3-8b-linear-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6059620df54539876e5dbacf74234e0f5a535fec74aad83316759d673ee81bf8 +size 4321957344 diff --git a/llama3-8b-linear-v2.Q3_K_M.gguf b/llama3-8b-linear-v2.Q3_K_M.gguf new file mode 100644 index 0000000..8d8dde6 --- /dev/null +++ b/llama3-8b-linear-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f239e898013cf04a697c36d16ae83c4627886f58b88b9b1896205ec2ce4921 +size 4018918880 diff --git a/llama3-8b-linear-v2.Q3_K_S.gguf b/llama3-8b-linear-v2.Q3_K_S.gguf new file mode 100644 index 0000000..ec86458 --- /dev/null +++ b/llama3-8b-linear-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5379474a3b4c89689451b7d86ee8397ca62e758a780d177564a852444173cf9 +size 3664500192 diff --git a/llama3-8b-linear-v2.Q4_K_M.gguf b/llama3-8b-linear-v2.Q4_K_M.gguf new file mode 100644 index 0000000..e1caeae --- /dev/null +++ b/llama3-8b-linear-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724910a9531e7a805169d604307f4dc48c41a5258e45587d98ad6095043c21e2 +size 4920735200 diff --git a/llama3-8b-linear-v2.Q4_K_S.gguf b/llama3-8b-linear-v2.Q4_K_S.gguf new file mode 100644 index 0000000..110f158 --- /dev/null +++ b/llama3-8b-linear-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f8f10ee5147c002de89fda9088b9755c3b9cc875d7c1ef04903e2b2c3344ce +size 4692669920 diff --git a/llama3-8b-linear-v2.Q5_K_M.gguf b/llama3-8b-linear-v2.Q5_K_M.gguf new file mode 100644 index 0000000..1359d69 --- /dev/null +++ b/llama3-8b-linear-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2fdd623e4be8c694c514119fb8c17fe7687fde081924b3d547d46778fb0d9e +size 5732988384 diff --git a/llama3-8b-linear-v2.Q5_K_S.gguf b/llama3-8b-linear-v2.Q5_K_S.gguf new file mode 100644 index 0000000..832e055 --- /dev/null +++ b/llama3-8b-linear-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfe2444cd8ab5d27d3e0ab7b4c6a0743287235c4c350f97a8ecc5cc736cc8df +size 5599294944 diff --git a/llama3-8b-linear-v2.Q6_K.gguf b/llama3-8b-linear-v2.Q6_K.gguf new file mode 100644 index 0000000..c0c2518 --- /dev/null +++ b/llama3-8b-linear-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f1a3db9c95889206dfc1f2c4d749e46b7f108dd1a0ebe729d61a92daf5db8d +size 6596007392 diff --git a/llama3-8b-linear-v2.Q8_0.gguf b/llama3-8b-linear-v2.Q8_0.gguf new file mode 100644 index 0000000..75f8ff6 --- /dev/null +++ b/llama3-8b-linear-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a435ebb615bf61fa713b08d508c0f20d06605592fd044ab0a562923e719135 +size 8540771808 diff --git a/llama3-8b-linear-v2.f16.gguf b/llama3-8b-linear-v2.f16.gguf new file mode 100644 index 0000000..b928311 --- /dev/null +++ b/llama3-8b-linear-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5984f06c3f5501fe989cdbf89e6230e504bcb442eae2f7631a088f5851b11d +size 16068892128