commit 667c1ae604e6cf9318ee5397fedb637f1abbaf19 Author: ModelHub XC Date: Sun Sep 13 05:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.1-8B-7-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53af18d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +TwinLlama-3.1-8B-7.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.f16.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-7.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0c6ebc7 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mlabonne/TwinLlama-3.1-8B-7 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/TwinLlama-3.1-8B-7 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-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/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-7-GGUF/resolve/main/TwinLlama-3.1-8B-7.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/TwinLlama-3.1-8B-7.IQ3_M.gguf b/TwinLlama-3.1-8B-7.IQ3_M.gguf new file mode 100644 index 0000000..971326a --- /dev/null +++ b/TwinLlama-3.1-8B-7.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f619ab4a66e2ce44d6bb65599960918ff24826cbcaaf0edeb0e0e796a8195387 +size 3784823616 diff --git a/TwinLlama-3.1-8B-7.IQ3_S.gguf b/TwinLlama-3.1-8B-7.IQ3_S.gguf new file mode 100644 index 0000000..91a6905 --- /dev/null +++ b/TwinLlama-3.1-8B-7.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2619043e396d4b85fb613826fe72897bd39979cce147f7b92cadf6edf583e014 +size 3682325312 diff --git a/TwinLlama-3.1-8B-7.IQ3_XS.gguf b/TwinLlama-3.1-8B-7.IQ3_XS.gguf new file mode 100644 index 0000000..ad65705 --- /dev/null +++ b/TwinLlama-3.1-8B-7.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdb87e29ff1b61386416874adc6fe8ab63701a582c93533c66834552a16115e +size 3518747456 diff --git a/TwinLlama-3.1-8B-7.IQ4_XS.gguf b/TwinLlama-3.1-8B-7.IQ4_XS.gguf new file mode 100644 index 0000000..5fdb6f8 --- /dev/null +++ b/TwinLlama-3.1-8B-7.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbdde0639a8239eac9be38eec98f583ec60a759fbb5786c44e0fe940cad4aed +size 4484363072 diff --git a/TwinLlama-3.1-8B-7.Q2_K.gguf b/TwinLlama-3.1-8B-7.Q2_K.gguf new file mode 100644 index 0000000..8f50597 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcc0711b06b37fc63c9bdf6218c69dbcc796d284d658a701593eb2e6d9e73c3 +size 3179131712 diff --git a/TwinLlama-3.1-8B-7.Q3_K_L.gguf b/TwinLlama-3.1-8B-7.Q3_K_L.gguf new file mode 100644 index 0000000..b5c1b64 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b855d9df4b885888647d4b5d2c103647bf698f51c157489edb8d8afa0b4a44c4 +size 4321956672 diff --git a/TwinLlama-3.1-8B-7.Q3_K_M.gguf b/TwinLlama-3.1-8B-7.Q3_K_M.gguf new file mode 100644 index 0000000..edf86e7 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd7faae78663f47cb018587faf32a223a114cb754d127caaf0b657f1bac3450 +size 4018918208 diff --git a/TwinLlama-3.1-8B-7.Q3_K_S.gguf b/TwinLlama-3.1-8B-7.Q3_K_S.gguf new file mode 100644 index 0000000..6d7557c --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4442e93f4559625c125bcf62d1df8ac85ff7470b0380747b9eaee37242a04e +size 3664499520 diff --git a/TwinLlama-3.1-8B-7.Q4_K_M.gguf b/TwinLlama-3.1-8B-7.Q4_K_M.gguf new file mode 100644 index 0000000..7dcd415 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea7966e0ede95a71b63ef371b7fe47bb9bd909aa89e4eb94681319817d2945b +size 4920734528 diff --git a/TwinLlama-3.1-8B-7.Q4_K_S.gguf b/TwinLlama-3.1-8B-7.Q4_K_S.gguf new file mode 100644 index 0000000..4b5556b --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d363036ce906bcc2fca62ded8e99b3f436959df90ac27e4a4046d916714171 +size 4692669248 diff --git a/TwinLlama-3.1-8B-7.Q5_K_M.gguf b/TwinLlama-3.1-8B-7.Q5_K_M.gguf new file mode 100644 index 0000000..b8fdd46 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8390b4404daeb81b75e2ae53f7f419671a50729f4e54f90ef681077c8aa99cf6 +size 5732987712 diff --git a/TwinLlama-3.1-8B-7.Q5_K_S.gguf b/TwinLlama-3.1-8B-7.Q5_K_S.gguf new file mode 100644 index 0000000..85dd6fd --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbba04bbc3c2cee88e2c2412e329a46967a8b8d2532175466db801326a243f7 +size 5599294272 diff --git a/TwinLlama-3.1-8B-7.Q6_K.gguf b/TwinLlama-3.1-8B-7.Q6_K.gguf new file mode 100644 index 0000000..1c99fb7 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc403ef2b87596e7618543ef1251193937f4e29529a6151a2dfb749ef6a66de +size 6596006720 diff --git a/TwinLlama-3.1-8B-7.Q8_0.gguf b/TwinLlama-3.1-8B-7.Q8_0.gguf new file mode 100644 index 0000000..b024c23 --- /dev/null +++ b/TwinLlama-3.1-8B-7.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2e511d51aa64dbcfb13f360d42204a493c60849b8e9ab350c0bb1027ade106 +size 8540771136 diff --git a/TwinLlama-3.1-8B-7.f16.gguf b/TwinLlama-3.1-8B-7.f16.gguf new file mode 100644 index 0000000..2f769d0 --- /dev/null +++ b/TwinLlama-3.1-8B-7.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0546d83a5f83cece960025266aaaa1e07961d593615fb43a4ec414f4db7943cf +size 16068891456