commit fd398fbd06fcfb7779bfebfbcad8de19ed79883e Author: ModelHub XC Date: Fri Jul 24 04:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-dare-ties-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2134a28 --- /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-dare-ties-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dare-ties-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..b78097f --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Alelcv27/llama3-8b-dare-ties-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Alelcv27/llama3-8b-dare-ties-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-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dare-ties-v2-GGUF/resolve/main/llama3-8b-dare-ties-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-dare-ties-v2.IQ4_XS.gguf b/llama3-8b-dare-ties-v2.IQ4_XS.gguf new file mode 100644 index 0000000..5b1363e --- /dev/null +++ b/llama3-8b-dare-ties-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a515a597d57563e1e9a98ccba83105e481a5099aa0dcd42f2b27bbfe4008e43b +size 4484363904 diff --git a/llama3-8b-dare-ties-v2.Q2_K.gguf b/llama3-8b-dare-ties-v2.Q2_K.gguf new file mode 100644 index 0000000..c4463a3 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a41fb824d4c55d13ec724adb6595e3e63d9fe30180d7c79ac2c2ccbf1de7f2f +size 3179132544 diff --git a/llama3-8b-dare-ties-v2.Q3_K_L.gguf b/llama3-8b-dare-ties-v2.Q3_K_L.gguf new file mode 100644 index 0000000..12f3d39 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0e7230639d2d466e4d12a98d664717594a0befdc42aab02f0e34050e52c392 +size 4321957504 diff --git a/llama3-8b-dare-ties-v2.Q3_K_M.gguf b/llama3-8b-dare-ties-v2.Q3_K_M.gguf new file mode 100644 index 0000000..926a026 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292bea9a065490699161cbe2932a65ec6e04cf516becc4e6b72de1668029d5a0 +size 4018919040 diff --git a/llama3-8b-dare-ties-v2.Q3_K_S.gguf b/llama3-8b-dare-ties-v2.Q3_K_S.gguf new file mode 100644 index 0000000..b3f95e7 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1de60ebe4c64982daa8dcd7adfe40e3f9788b792a59f56dee1972b24b8e551 +size 3664500352 diff --git a/llama3-8b-dare-ties-v2.Q4_K_M.gguf b/llama3-8b-dare-ties-v2.Q4_K_M.gguf new file mode 100644 index 0000000..9b3fd47 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b6fc9dc2befccfae9b889d24074a1d4700c726ad4d4a37aecd46e8069c8010b +size 4920735360 diff --git a/llama3-8b-dare-ties-v2.Q4_K_S.gguf b/llama3-8b-dare-ties-v2.Q4_K_S.gguf new file mode 100644 index 0000000..f875e60 --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd69a16c2641be0cc572b84f33cd30e369e9212ca160a8b92ef2dc4c5ad8d092 +size 4692670080 diff --git a/llama3-8b-dare-ties-v2.Q5_K_M.gguf b/llama3-8b-dare-ties-v2.Q5_K_M.gguf new file mode 100644 index 0000000..1ec2edc --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daaff77cf351c4d67ce7205af85c9c0814231450e01ff9dbe219a3c76a842376 +size 5732988544 diff --git a/llama3-8b-dare-ties-v2.Q5_K_S.gguf b/llama3-8b-dare-ties-v2.Q5_K_S.gguf new file mode 100644 index 0000000..bd73d4c --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bddf8c43798bbc508d603a435a3322629788181724d730998f6c07b5d679420 +size 5599295104 diff --git a/llama3-8b-dare-ties-v2.Q6_K.gguf b/llama3-8b-dare-ties-v2.Q6_K.gguf new file mode 100644 index 0000000..9309fad --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfd3bb475ec4b401a552049a21101d3b2d86fd0580d62a1751dc9b1e2c41db84 +size 6596007552 diff --git a/llama3-8b-dare-ties-v2.Q8_0.gguf b/llama3-8b-dare-ties-v2.Q8_0.gguf new file mode 100644 index 0000000..7e86bef --- /dev/null +++ b/llama3-8b-dare-ties-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ba704e44647cf42d162685bbd2c20d5011f4ba109b4f789c8d65cf7f67be53 +size 8540771968 diff --git a/llama3-8b-dare-ties-v2.f16.gguf b/llama3-8b-dare-ties-v2.f16.gguf new file mode 100644 index 0000000..baf31ac --- /dev/null +++ b/llama3-8b-dare-ties-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e424543dca9c7bddcf2e54bb85bac74ad223b8e20171bd1908b6c50ba69d42 +size 16068892288