commit f14a75dffdf41e1eb0beef871614ffc941b9a137 Author: ModelHub XC Date: Sun Sep 13 09:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/adullama3.1-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a62b5dc --- /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 +adullama3.1-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +adullama3.1-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..674f80d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: lucid-gunner/adullama3.1-v2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/lucid-gunner/adullama3.1-v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/adullama3.1-v2-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/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/adullama3.1-v2-GGUF/resolve/main/adullama3.1-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/adullama3.1-v2.IQ4_XS.gguf b/adullama3.1-v2.IQ4_XS.gguf new file mode 100644 index 0000000..463b80d --- /dev/null +++ b/adullama3.1-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21bffa78002e88ad99f766f51d4de454e38801dc4d482da39ad0036ae3e2021 +size 4484364576 diff --git a/adullama3.1-v2.Q2_K.gguf b/adullama3.1-v2.Q2_K.gguf new file mode 100644 index 0000000..30ea38f --- /dev/null +++ b/adullama3.1-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb342aa8809841f2d5bb43c24aaab5041cf0868c45eaf1deb944548a6642260 +size 3179133216 diff --git a/adullama3.1-v2.Q3_K_L.gguf b/adullama3.1-v2.Q3_K_L.gguf new file mode 100644 index 0000000..105bb3b --- /dev/null +++ b/adullama3.1-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10bc7f277e524ebc0056ea3b0ca46e39ef23dd011f97e1a842d7d76d7c7544a +size 4321958176 diff --git a/adullama3.1-v2.Q3_K_M.gguf b/adullama3.1-v2.Q3_K_M.gguf new file mode 100644 index 0000000..abbfb4f --- /dev/null +++ b/adullama3.1-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2e7b62697fd8b31dcdf12b9ec5c2679cdabdc891b5a156331838fc3bc1b63c +size 4018919712 diff --git a/adullama3.1-v2.Q3_K_S.gguf b/adullama3.1-v2.Q3_K_S.gguf new file mode 100644 index 0000000..70ad0c1 --- /dev/null +++ b/adullama3.1-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dfdd8aa4e59c67b627c893fc054ca2a072ae96dcb325bd633d0372ffbe2420 +size 3664501024 diff --git a/adullama3.1-v2.Q4_K_M.gguf b/adullama3.1-v2.Q4_K_M.gguf new file mode 100644 index 0000000..72e2cba --- /dev/null +++ b/adullama3.1-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15408343799759b0e6922f57c83ef4e6f721ff31ffb9d0a21b052edaecc6042 +size 4920736032 diff --git a/adullama3.1-v2.Q4_K_S.gguf b/adullama3.1-v2.Q4_K_S.gguf new file mode 100644 index 0000000..39f0aaa --- /dev/null +++ b/adullama3.1-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce1a6495f41cdf92da4ebb79ca285fc3bd8baf7040c4d1af7f64e650b96a799 +size 4692670752 diff --git a/adullama3.1-v2.Q5_K_M.gguf b/adullama3.1-v2.Q5_K_M.gguf new file mode 100644 index 0000000..ec378cd --- /dev/null +++ b/adullama3.1-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e135a0e740151d21b0f93e7e81a3ca2e6c15e917f913b3db6a478e1eba444f +size 5732989216 diff --git a/adullama3.1-v2.Q5_K_S.gguf b/adullama3.1-v2.Q5_K_S.gguf new file mode 100644 index 0000000..92d807c --- /dev/null +++ b/adullama3.1-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcf9ae4eea420196e4bf87eb1a79c71957cb1105e3d11e18240d468f8a1a74c +size 5599295776 diff --git a/adullama3.1-v2.Q6_K.gguf b/adullama3.1-v2.Q6_K.gguf new file mode 100644 index 0000000..827aff5 --- /dev/null +++ b/adullama3.1-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d34fb422c58b5a378a54cc1fefd82512fbcb2313eefb7f77bc71fed11fda85 +size 6596008224 diff --git a/adullama3.1-v2.Q8_0.gguf b/adullama3.1-v2.Q8_0.gguf new file mode 100644 index 0000000..b82da3f --- /dev/null +++ b/adullama3.1-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319b233a9735365e07a313fbd69f4a2257cab0eb3db5953829d8d2f5c080ee48 +size 8540772640 diff --git a/adullama3.1-v2.f16.gguf b/adullama3.1-v2.f16.gguf new file mode 100644 index 0000000..a140eac --- /dev/null +++ b/adullama3.1-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42282a8a5a171bfcbec15a995989b1a86ededea83cca1ad77026e6d32a35f794 +size 16068892960