commit 8cca47882c449d50c9c7f2f5e00724b55e9eafc8 Author: ModelHub XC Date: Thu Jul 16 15:00:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e3d7b2 --- /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 +LION-LLaMA-3-8b-sft-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LION-LLaMA-3-8b-sft-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LION-LLaMA-3-8b-sft-v1.0.IQ3_M.gguf b/LION-LLaMA-3-8b-sft-v1.0.IQ3_M.gguf new file mode 100644 index 0000000..be00fe2 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e64a8c9843d8a32b0381778cebbea1a9dbe18a4016510248a1f52f8a502a4a +size 3784823264 diff --git a/LION-LLaMA-3-8b-sft-v1.0.IQ3_S.gguf b/LION-LLaMA-3-8b-sft-v1.0.IQ3_S.gguf new file mode 100644 index 0000000..eb1b804 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbca7dfcf931f550792efbf7766ecb8d17ec236705395bb804f1ffdd9adf7ef0 +size 3682324960 diff --git a/LION-LLaMA-3-8b-sft-v1.0.IQ3_XS.gguf b/LION-LLaMA-3-8b-sft-v1.0.IQ3_XS.gguf new file mode 100644 index 0000000..00571bd --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d33603c68dacbe472507ce79a382306b792c965681d02749a8a623511293dfd +size 3518747104 diff --git a/LION-LLaMA-3-8b-sft-v1.0.IQ4_XS.gguf b/LION-LLaMA-3-8b-sft-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..7dc0118 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5182795366773ba2b0cee7581dfa142358b8b2b3c97c0c42bbb51732911737f9 +size 4484362720 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q2_K.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q2_K.gguf new file mode 100644 index 0000000..b6084c7 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8ab3177c834a0a99ad8e5fc476d84eb0e930e25b3a5e3cc08adb1686d012c7 +size 3179131360 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q3_K_L.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..ab4bae2 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e97057359c0afb0e839dd23eb4ad2a0271509144df09abfb792d42ac79d476 +size 4321956320 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q3_K_M.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..57f5fba --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01791b6ee8262507a5c6f25faa81813f2287ee61af7754c89b06975ed3b7faaa +size 4018917856 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q3_K_S.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..8a25073 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4310650bc189f8519713a6e622586f8a6f72a8226f2f4d1555571b0ad04eb8df +size 3664499168 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q4_K_M.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..b95a8ff --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e57c70f7ce300619c35fc0e01f340fb84d444f74507545ee36ff5caccf88a67 +size 4920734176 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q4_K_S.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..2647515 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bf2c6fc38032cae59c1e393a092bd5f0407f8cd79975140ef6789725f3b382 +size 4692668896 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q5_K_M.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..868d686 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1f541a24889d9db21bc76134b55895b137d42d2468b94bbb629be4bd8fbd62 +size 5732987360 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q5_K_S.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..21e9d29 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c8816a7a563a58b19eb4849beb3f72c160e4c4de3563499c2ed7d7f6159b4b +size 5599293920 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q6_K.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q6_K.gguf new file mode 100644 index 0000000..e04ea8a --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0ed2b98dee15174101b8fc19b9b13aa3ee5c8535f86add9c92c27615699b37 +size 6596006368 diff --git a/LION-LLaMA-3-8b-sft-v1.0.Q8_0.gguf b/LION-LLaMA-3-8b-sft-v1.0.Q8_0.gguf new file mode 100644 index 0000000..a6d7d9b --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7aab14a22c593e8ce67c30b2f68b2f128dea00cf7f00de26d42942b6a0d1cd8 +size 8540770784 diff --git a/LION-LLaMA-3-8b-sft-v1.0.f16.gguf b/LION-LLaMA-3-8b-sft-v1.0.f16.gguf new file mode 100644 index 0000000..44053a3 --- /dev/null +++ b/LION-LLaMA-3-8b-sft-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb1aec20e5a7052b6a58e8811b15d64d1f63712aeae0f220e4e5787dd54cee8 +size 16068891104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..85c10cd --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0 + + +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/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LION-LLaMA-3-8b-sft-v1.0-GGUF/resolve/main/LION-LLaMA-3-8b-sft-v1.0.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. + +