commit f85ef256bffb699c87152c729d0d58a296ba9232 Author: ModelHub XC Date: Tue Jul 21 11:53:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-della-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f595653 --- /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-della-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-della-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..7668e02 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Alelcv27/llama3-8b-della-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Alelcv27/llama3-8b-della-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-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-della-v2-GGUF/resolve/main/llama3-8b-della-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-della-v2.IQ4_XS.gguf b/llama3-8b-della-v2.IQ4_XS.gguf new file mode 100644 index 0000000..0880231 --- /dev/null +++ b/llama3-8b-della-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89149cc0a9ff37dbd98d0855b2f71fd609bb81391336370048c25e9334c9c86 +size 4484363904 diff --git a/llama3-8b-della-v2.Q2_K.gguf b/llama3-8b-della-v2.Q2_K.gguf new file mode 100644 index 0000000..afbb5d9 --- /dev/null +++ b/llama3-8b-della-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a5215b290a74ec326814b48ffc598cc478eb43209311bc9698d3d358950f28 +size 3179132544 diff --git a/llama3-8b-della-v2.Q3_K_L.gguf b/llama3-8b-della-v2.Q3_K_L.gguf new file mode 100644 index 0000000..353409a --- /dev/null +++ b/llama3-8b-della-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22d97bc828ea53e1c83005ef9e1f374ff276952e5ba9fd9ad90e05096e08164 +size 4321957504 diff --git a/llama3-8b-della-v2.Q3_K_M.gguf b/llama3-8b-della-v2.Q3_K_M.gguf new file mode 100644 index 0000000..81f3f8f --- /dev/null +++ b/llama3-8b-della-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0661d01d4e9b86bd98c8df0c516dc958b09304c19a5abdbd079ae6d7ea2c1660 +size 4018919040 diff --git a/llama3-8b-della-v2.Q3_K_S.gguf b/llama3-8b-della-v2.Q3_K_S.gguf new file mode 100644 index 0000000..7b249ef --- /dev/null +++ b/llama3-8b-della-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d8f736f88b9f4bc14be0c2877d75d9050179173b59c3db7483b49d9f686111 +size 3664500352 diff --git a/llama3-8b-della-v2.Q4_K_M.gguf b/llama3-8b-della-v2.Q4_K_M.gguf new file mode 100644 index 0000000..812e7ca --- /dev/null +++ b/llama3-8b-della-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1e6b35fb16aaf9c07f3ed2c08ed99c11252af3bd3c57dcaa6c8e92f2157557 +size 4920735360 diff --git a/llama3-8b-della-v2.Q4_K_S.gguf b/llama3-8b-della-v2.Q4_K_S.gguf new file mode 100644 index 0000000..7ef0820 --- /dev/null +++ b/llama3-8b-della-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7039d4918cc2e03ec6f1cebef548d567c8bc022405c1b85098b7e6b104c6484a +size 4692670080 diff --git a/llama3-8b-della-v2.Q5_K_M.gguf b/llama3-8b-della-v2.Q5_K_M.gguf new file mode 100644 index 0000000..301363b --- /dev/null +++ b/llama3-8b-della-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd7b0853efb50dea1e93b74d9b33c44260cad238f43ad0c07ba7169e25074ff +size 5732988544 diff --git a/llama3-8b-della-v2.Q5_K_S.gguf b/llama3-8b-della-v2.Q5_K_S.gguf new file mode 100644 index 0000000..b79ebe2 --- /dev/null +++ b/llama3-8b-della-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02ad9efb6f26c298823160e6805819d0b3bfbec4e7b00814e72466993a1eeb2 +size 5599295104 diff --git a/llama3-8b-della-v2.Q6_K.gguf b/llama3-8b-della-v2.Q6_K.gguf new file mode 100644 index 0000000..b08b036 --- /dev/null +++ b/llama3-8b-della-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3954c3110fadd472dfee31aab0a03cfc0a0e4fdffe0a1a0286dfb60e46f9a1ff +size 6596007552 diff --git a/llama3-8b-della-v2.Q8_0.gguf b/llama3-8b-della-v2.Q8_0.gguf new file mode 100644 index 0000000..de68cad --- /dev/null +++ b/llama3-8b-della-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816d729fc25c8e0cb85d383a96fa1b7dd967a07c565ab84440b8f5d59ef61daf +size 8540771968 diff --git a/llama3-8b-della-v2.f16.gguf b/llama3-8b-della-v2.f16.gguf new file mode 100644 index 0000000..1d6a953 --- /dev/null +++ b/llama3-8b-della-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eee217793cc7e29f5152e3543c28a1c9217dbd9fde8714aee6d71d028af4ad7 +size 16068892288