commit 4f457eafdfbe93e65d9ad1d97dd5b69d4ce3059e Author: ModelHub XC Date: Sat Sep 26 15:31:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b84a518 --- /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 +Llama-3.1-8B-TitanFusion-Mix.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-TitanFusion-Mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-TitanFusion-Mix.IQ3_M.gguf b/Llama-3.1-8B-TitanFusion-Mix.IQ3_M.gguf new file mode 100644 index 0000000..3641b27 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4338199e473d0cf0a31a60f170aa34f67fb94603e52d6f950acb0548c79a7eb5 +size 3784825056 diff --git a/Llama-3.1-8B-TitanFusion-Mix.IQ3_S.gguf b/Llama-3.1-8B-TitanFusion-Mix.IQ3_S.gguf new file mode 100644 index 0000000..5235b4c --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50d65b2839c77db7d0a147023c6565af307ef0823e5fcf6bc7f450048e67ef7 +size 3682326752 diff --git a/Llama-3.1-8B-TitanFusion-Mix.IQ3_XS.gguf b/Llama-3.1-8B-TitanFusion-Mix.IQ3_XS.gguf new file mode 100644 index 0000000..15a672d --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266ca81f3c40c3f905a5b97a1149826880f60a9c73423f88e2ba2acccee5223e +size 3518748896 diff --git a/Llama-3.1-8B-TitanFusion-Mix.IQ4_XS.gguf b/Llama-3.1-8B-TitanFusion-Mix.IQ4_XS.gguf new file mode 100644 index 0000000..f1c089f --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d67ec5e51affea5d5481c996dc6c35d636da9e9dc322d146e0b1231c6d00138 +size 4484364512 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q2_K.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q2_K.gguf new file mode 100644 index 0000000..a550822 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b20af58cf08d7a19f4edde0110007f4842237eb06e302bb56b1630b234db39 +size 3179133152 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q3_K_L.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_L.gguf new file mode 100644 index 0000000..c84bf75 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4b854ab412c7ee38fc1dca4dd5268b9201a76e97c293a9e4c6770a2680f0f6 +size 4321958112 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q3_K_M.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_M.gguf new file mode 100644 index 0000000..be994d2 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef97675e9cd29f245f2e969367c2b7e3c7384318d3ec591b8859633fabab668 +size 4018919648 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q3_K_S.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_S.gguf new file mode 100644 index 0000000..cc9bf8b --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c39cacacf475eb217c8a42b0e9d67257e1902a637c3812aefee29f247ca5e6 +size 3664500960 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q4_K_M.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q4_K_M.gguf new file mode 100644 index 0000000..74620b4 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47e11e2094bcac95a1a2a8a138f44ad0a648ee01e8b9524ce80bb8ffab9a3f5 +size 4920735968 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q4_K_S.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q4_K_S.gguf new file mode 100644 index 0000000..a091635 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c41bb5503823edb3988a800b66b4ebdf7bb4e69c635fc540b86765f7c482d7d +size 4692670688 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q5_K_M.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q5_K_M.gguf new file mode 100644 index 0000000..c5ce3ac --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046008ebb9c3203a6c3af16f94347f1b1a284f357571e678d0188dbae1b3147d +size 5732989152 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q5_K_S.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q5_K_S.gguf new file mode 100644 index 0000000..15cc353 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1004f8f3f8e83dce722652b3871605538bedc1f28e927a30bddb90ef0a8e301 +size 5599295712 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q6_K.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q6_K.gguf new file mode 100644 index 0000000..bc66649 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b56239523e7419284a65efd1d9f2d969612fbe3b01398c4e4a08078f05f01c +size 6596008160 diff --git a/Llama-3.1-8B-TitanFusion-Mix.Q8_0.gguf b/Llama-3.1-8B-TitanFusion-Mix.Q8_0.gguf new file mode 100644 index 0000000..975fca8 --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822614ffbb29b7d350f382cd6d404d9845b2fa5a70693e2d7103a1f6d72e0a09 +size 8540772576 diff --git a/Llama-3.1-8B-TitanFusion-Mix.f16.gguf b/Llama-3.1-8B-TitanFusion-Mix.f16.gguf new file mode 100644 index 0000000..02696fa --- /dev/null +++ b/Llama-3.1-8B-TitanFusion-Mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23aeabe03a5987e28469c66d3c096d1ebad2c395654dd3f7e36ff16eaed9d31d +size 16068892896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c90e7fd --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: bunnycore/Llama-3.1-8B-TitanFusion-Mix +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.1-8B-TitanFusion-Mix + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-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/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF/resolve/main/Llama-3.1-8B-TitanFusion-Mix.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. + +