commit d7c27db45497f0c93f808b863fbfc1920972444c Author: ModelHub XC Date: Mon Apr 27 13:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tat-llm-7b-fft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd08ddb --- /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 +tat-llm-7b-fft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.f16.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tat-llm-7b-fft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fcba2b --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: next-tat/tat-llm-7b-fft +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/next-tat/tat-llm-7b-fft + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/tat-llm-7b-fft-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/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tat-llm-7b-fft-GGUF/resolve/main/tat-llm-7b-fft.f16.gguf) | f16 | 13.6 | 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/tat-llm-7b-fft.IQ4_XS.gguf b/tat-llm-7b-fft.IQ4_XS.gguf new file mode 100644 index 0000000..d0e144e --- /dev/null +++ b/tat-llm-7b-fft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab1286b12d1cb699b1a4f2010a26224a15e219ed9817b22f9278c3ca98c73f4 +size 3647517312 diff --git a/tat-llm-7b-fft.Q2_K.gguf b/tat-llm-7b-fft.Q2_K.gguf new file mode 100644 index 0000000..c7b8a65 --- /dev/null +++ b/tat-llm-7b-fft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa198017cb3721d9187caf750b74c0a1a85cccddc0197c3eb0a92298f63cd817 +size 2532864640 diff --git a/tat-llm-7b-fft.Q3_K_L.gguf b/tat-llm-7b-fft.Q3_K_L.gguf new file mode 100644 index 0000000..f6dd272 --- /dev/null +++ b/tat-llm-7b-fft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e152123241049afe41dad0250f3be3e0a98c7809dc82802e6f1208704f84a043 +size 3597111936 diff --git a/tat-llm-7b-fft.Q3_K_M.gguf b/tat-llm-7b-fft.Q3_K_M.gguf new file mode 100644 index 0000000..fa06833 --- /dev/null +++ b/tat-llm-7b-fft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725e442bd111281076361a352ac507435b1d7cd955d00720f5e8531813bd9988 +size 3298005632 diff --git a/tat-llm-7b-fft.Q3_K_S.gguf b/tat-llm-7b-fft.Q3_K_S.gguf new file mode 100644 index 0000000..0772fa2 --- /dev/null +++ b/tat-llm-7b-fft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228b86049aaf9923e3fd63900774faa0008da0a5c1351fed7290a849c736c334 +size 2948305536 diff --git a/tat-llm-7b-fft.Q4_0_4_4.gguf b/tat-llm-7b-fft.Q4_0_4_4.gguf new file mode 100644 index 0000000..48f31af --- /dev/null +++ b/tat-llm-7b-fft.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e4aaa3781e0f257d6e9e89b05e70e84bcfdc77fb97bfc7998204c05c0f65d8 +size 3825808000 diff --git a/tat-llm-7b-fft.Q4_K_M.gguf b/tat-llm-7b-fft.Q4_K_M.gguf new file mode 100644 index 0000000..1a23220 --- /dev/null +++ b/tat-llm-7b-fft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39120fa4ae9f6c30398715a44f4071a18e43178f834e4a7ddf38d4bedd76610 +size 4081005184 diff --git a/tat-llm-7b-fft.Q4_K_S.gguf b/tat-llm-7b-fft.Q4_K_S.gguf new file mode 100644 index 0000000..eb5943b --- /dev/null +++ b/tat-llm-7b-fft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d42c5a723b738ed64384028dde992576720782e1ea3468e80ed3f3ad165b428 +size 3856740992 diff --git a/tat-llm-7b-fft.Q5_K_M.gguf b/tat-llm-7b-fft.Q5_K_M.gguf new file mode 100644 index 0000000..b034bed --- /dev/null +++ b/tat-llm-7b-fft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06652b7d24d1d9d246eaeb3eb6ffb3ecc85f9ef316eabb9c68c02d41b06ffb1a +size 4783157888 diff --git a/tat-llm-7b-fft.Q5_K_S.gguf b/tat-llm-7b-fft.Q5_K_S.gguf new file mode 100644 index 0000000..45afb93 --- /dev/null +++ b/tat-llm-7b-fft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fc4106c62409c5ed5417dac709372b2c6738b6b72ea49052ec0cb574eb3210 +size 4651692672 diff --git a/tat-llm-7b-fft.Q6_K.gguf b/tat-llm-7b-fft.Q6_K.gguf new file mode 100644 index 0000000..af490af --- /dev/null +++ b/tat-llm-7b-fft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d06abb737ee31b5460f12c0e267b19729f1d86591c9f40e1bb13b9f8d38a0e8 +size 5529195136 diff --git a/tat-llm-7b-fft.Q8_0.gguf b/tat-llm-7b-fft.Q8_0.gguf new file mode 100644 index 0000000..63c249e --- /dev/null +++ b/tat-llm-7b-fft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f45954b82b24c76dfb32a2b3135f04ecb6bf826ae1d5477bd4d49df4dc39163 +size 7161090688 diff --git a/tat-llm-7b-fft.f16.gguf b/tat-llm-7b-fft.f16.gguf new file mode 100644 index 0000000..1f1d8d4 --- /dev/null +++ b/tat-llm-7b-fft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beeba1be73e0135a51097c112bf7b5475349a25ecbd98d615a451b1fb61c0845 +size 13478105728