commit 65b090de5336c86793e83a774a9d687df84d7369 Author: ModelHub XC Date: Sat Jul 11 10:06:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TunnedLlama-3.1-8B_v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95cc0f9 --- /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 +TunnedLlama-3.1-8B_v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TunnedLlama-3.1-8B_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..8a32290 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: sofiaamores/TunnedLlama-3.1-8B_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/sofiaamores/TunnedLlama-3.1-8B_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/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TunnedLlama-3.1-8B_v2-GGUF/resolve/main/TunnedLlama-3.1-8B_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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/TunnedLlama-3.1-8B_v2.IQ4_XS.gguf b/TunnedLlama-3.1-8B_v2.IQ4_XS.gguf new file mode 100644 index 0000000..342bb13 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2865215afce10d91a4a75c8b5ff788885b3e072f4c1e313d881a81939909c1 +size 4484364544 diff --git a/TunnedLlama-3.1-8B_v2.Q2_K.gguf b/TunnedLlama-3.1-8B_v2.Q2_K.gguf new file mode 100644 index 0000000..f4f7e43 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8c958fbd32a75f35c73062de7f989f5e434baa99e185cf0deff3a7a8f5931f +size 3179133184 diff --git a/TunnedLlama-3.1-8B_v2.Q3_K_L.gguf b/TunnedLlama-3.1-8B_v2.Q3_K_L.gguf new file mode 100644 index 0000000..bbdee1f --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3068be943aa9fe85cae3f1db500e16dde8f1a2d26a87d9ecd06e35fd43050ed +size 4321958144 diff --git a/TunnedLlama-3.1-8B_v2.Q3_K_M.gguf b/TunnedLlama-3.1-8B_v2.Q3_K_M.gguf new file mode 100644 index 0000000..8658a4f --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a625648f66580089080fd9fec102cf4e8702585abc0e3c917d6eab8ed27ca64 +size 4018919680 diff --git a/TunnedLlama-3.1-8B_v2.Q3_K_S.gguf b/TunnedLlama-3.1-8B_v2.Q3_K_S.gguf new file mode 100644 index 0000000..d8b83a3 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d74297cf91e46f9b65861b124ec1d9ddbcf420669e199087a4d3e40f44bc99 +size 3664500992 diff --git a/TunnedLlama-3.1-8B_v2.Q4_K_M.gguf b/TunnedLlama-3.1-8B_v2.Q4_K_M.gguf new file mode 100644 index 0000000..54bd7bd --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131539fa4fa80f839b4506150b745b49003a4c03c775f4b3640573068531f6e0 +size 4920736000 diff --git a/TunnedLlama-3.1-8B_v2.Q4_K_S.gguf b/TunnedLlama-3.1-8B_v2.Q4_K_S.gguf new file mode 100644 index 0000000..c8822f3 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f3e04e78df4d1b8f0e1c1df444df801efa8fa0a8c1dc953744dbf3eca5311f +size 4692670720 diff --git a/TunnedLlama-3.1-8B_v2.Q5_K_M.gguf b/TunnedLlama-3.1-8B_v2.Q5_K_M.gguf new file mode 100644 index 0000000..4a59094 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d6e5448e549a593281159eeea571e93d9707bf7b01101755344d7de58b29f4 +size 5732989184 diff --git a/TunnedLlama-3.1-8B_v2.Q5_K_S.gguf b/TunnedLlama-3.1-8B_v2.Q5_K_S.gguf new file mode 100644 index 0000000..fee92f4 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297b3431061235398d3acbf543b3fa3cdca9dab2ce96409b374a79c1f1d5a4b0 +size 5599295744 diff --git a/TunnedLlama-3.1-8B_v2.Q6_K.gguf b/TunnedLlama-3.1-8B_v2.Q6_K.gguf new file mode 100644 index 0000000..3afdfdf --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ace5d7c79d86b59b4dab834401b0254648b49bf681ce7e3b1aba9d01ca35b9 +size 6596008192 diff --git a/TunnedLlama-3.1-8B_v2.Q8_0.gguf b/TunnedLlama-3.1-8B_v2.Q8_0.gguf new file mode 100644 index 0000000..5e63272 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2374ac4f8cd130590936dff5ea2871afea779ecb1e6b48c2b5e0fbbb903accbb +size 8540772608 diff --git a/TunnedLlama-3.1-8B_v2.f16.gguf b/TunnedLlama-3.1-8B_v2.f16.gguf new file mode 100644 index 0000000..b0d4341 --- /dev/null +++ b/TunnedLlama-3.1-8B_v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92ced9ce32a9b272d593a4d425625aecca58a1230c50fad9c8c4fd443ec7ed2 +size 16068892928