commit 2911d9d1b6ca6876dd231d3a65bca7aec0c20005 Author: ModelHub XC Date: Thu Aug 6 02:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5177341 --- /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 +Llama3.1-DeepDilemma-V1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeepDilemma-V1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-DeepDilemma-V1-8B.IQ4_XS.gguf b/Llama3.1-DeepDilemma-V1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..3100ac8 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136efe407e2fe354162a9bd257889ede5552cce37fc332260fad148ef38e621d +size 4484364224 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q2_K.gguf b/Llama3.1-DeepDilemma-V1-8B.Q2_K.gguf new file mode 100644 index 0000000..a991fff --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa534c3728fef76613f39ddd9621f0ace1972849f5a1d797b03dd90ecf1862b +size 3179132864 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q3_K_L.gguf b/Llama3.1-DeepDilemma-V1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..c55598c --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05639c562dc191c3df45d26c09932b93fb0c0352dae4ffa85a2481b57c619b04 +size 4321957824 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q3_K_M.gguf b/Llama3.1-DeepDilemma-V1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..591659a --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abda2ad077c7c5481815f8f513c95692c5354f05dcd8dc02906c48a6f1cc6985 +size 4018919360 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q3_K_S.gguf b/Llama3.1-DeepDilemma-V1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..19c4106 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50327a4e5e49db4dabcec887408c2eb2d297bea6d3539c11a10410b55b1f1f8d +size 3664500672 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q4_K_M.gguf b/Llama3.1-DeepDilemma-V1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..7fa8542 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d124cd0f34b7983ca8aed0bf78de56456aade08b97549364f4a7fa725878d7da +size 4920735680 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q4_K_S.gguf b/Llama3.1-DeepDilemma-V1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..85ca568 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c073510f3b2ef0177025812523ed0e6ee1ad8b8c73b87f0769e605353981a02 +size 4692670400 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q5_K_M.gguf b/Llama3.1-DeepDilemma-V1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..21e169d --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8840438246844303740afcdd8ee2d2b5bb1c784420a17690de68b55d6c650e +size 5732988864 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q5_K_S.gguf b/Llama3.1-DeepDilemma-V1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..bfbc7e1 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912dcecb7f1f3b56bc36881f5441b4ab4bbb15479d4a5d3f35365816710fb887 +size 5599295424 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q6_K.gguf b/Llama3.1-DeepDilemma-V1-8B.Q6_K.gguf new file mode 100644 index 0000000..a069624 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78cc8e71b9d8c40d8268afbfc811837ec73c3347d0bda75e40aaaec55c128217 +size 6596007872 diff --git a/Llama3.1-DeepDilemma-V1-8B.Q8_0.gguf b/Llama3.1-DeepDilemma-V1-8B.Q8_0.gguf new file mode 100644 index 0000000..12308d5 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7efb9ba1a99dc76c58d10bf198df49a2a15e2a2b2dc4fbb91ebaf679a27052c6 +size 8540772288 diff --git a/Llama3.1-DeepDilemma-V1-8B.f16.gguf b/Llama3.1-DeepDilemma-V1-8B.f16.gguf new file mode 100644 index 0000000..17bde74 --- /dev/null +++ b/Llama3.1-DeepDilemma-V1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2ded3a3c4087592135e53b240b0a3fe8afb4cca3eaf3af8ed527c83c1dde5b +size 16068892608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e1933e --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Yuma42/Llama3.1-DeepDilemma-V1-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Yuma42/Llama3.1-StableRoots-V0.5-8B +- Yuma42/Llama3.1-DeepDilemma-V0.9-8B +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuma42/Llama3.1-DeepDilemma-V1-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-DeepDilemma-V1-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-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/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeepDilemma-V1-8B-GGUF/resolve/main/Llama3.1-DeepDilemma-V1-8B.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. + +