commit e102f63b6f096c8d457529ee040f41388b19ecc3 Author: ModelHub XC Date: Sat Jul 4 10:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sft-llama7b-qa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7001b8e --- /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 +sft-llama7b-qa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.f16.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-llama7b-qa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..449f38f --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Jennny/sft-llama7b-qa +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Jennny/sft-llama7b-qa + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/sft-llama7b-qa-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/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sft-llama7b-qa-GGUF/resolve/main/sft-llama7b-qa.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/sft-llama7b-qa.IQ4_XS.gguf b/sft-llama7b-qa.IQ4_XS.gguf new file mode 100644 index 0000000..55b04ed --- /dev/null +++ b/sft-llama7b-qa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e123a6f436c4ead8ef4994b831605c0ad02a18f5c63ff17713782d83cf1638d +size 3647517248 diff --git a/sft-llama7b-qa.Q2_K.gguf b/sft-llama7b-qa.Q2_K.gguf new file mode 100644 index 0000000..cad88e8 --- /dev/null +++ b/sft-llama7b-qa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68044da94b62df6dcc98966fad945cb1cdc082998fd9845e0893701e3f7ba595 +size 2532864576 diff --git a/sft-llama7b-qa.Q3_K_L.gguf b/sft-llama7b-qa.Q3_K_L.gguf new file mode 100644 index 0000000..e065eb1 --- /dev/null +++ b/sft-llama7b-qa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25df7f1d0221e96ba7a5b573270cfea236cf423f2fef77b9b98c51122c1272f +size 3597111872 diff --git a/sft-llama7b-qa.Q3_K_M.gguf b/sft-llama7b-qa.Q3_K_M.gguf new file mode 100644 index 0000000..ac18d7c --- /dev/null +++ b/sft-llama7b-qa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77bbcc07a9d5fab49b3ee96b6c947014cbb2c5168ca9ac4cf4c455c7945a558 +size 3298005568 diff --git a/sft-llama7b-qa.Q3_K_S.gguf b/sft-llama7b-qa.Q3_K_S.gguf new file mode 100644 index 0000000..25ab719 --- /dev/null +++ b/sft-llama7b-qa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:340a4cc4faa639ac7bc6fa6ab192dcc7ef63962ef5421de598a0589d9fae0f35 +size 2948305472 diff --git a/sft-llama7b-qa.Q4_K_M.gguf b/sft-llama7b-qa.Q4_K_M.gguf new file mode 100644 index 0000000..4e5dc7b --- /dev/null +++ b/sft-llama7b-qa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd23eb25d7d41a87860a8793cae808c703839c0dee1b0a60931ec3ef3f2fba21 +size 4081005120 diff --git a/sft-llama7b-qa.Q4_K_S.gguf b/sft-llama7b-qa.Q4_K_S.gguf new file mode 100644 index 0000000..23601ad --- /dev/null +++ b/sft-llama7b-qa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ec04ab748c7ac61907cabe48aca4a76a04ddef4397bae3bcaa31089b64ab44 +size 3856740928 diff --git a/sft-llama7b-qa.Q5_K_M.gguf b/sft-llama7b-qa.Q5_K_M.gguf new file mode 100644 index 0000000..61d42ab --- /dev/null +++ b/sft-llama7b-qa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717fdccabf667689b251a4741f686f70d23bc5757b8503acc4d9794784a2098e +size 4783157824 diff --git a/sft-llama7b-qa.Q5_K_S.gguf b/sft-llama7b-qa.Q5_K_S.gguf new file mode 100644 index 0000000..772c234 --- /dev/null +++ b/sft-llama7b-qa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5a19a28ef3b95734ae89d54c6dff451d206db973ed5bc1fc5239a6b7be873d +size 4651692608 diff --git a/sft-llama7b-qa.Q6_K.gguf b/sft-llama7b-qa.Q6_K.gguf new file mode 100644 index 0000000..5cb1b28 --- /dev/null +++ b/sft-llama7b-qa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4186307c94bc3339f87b5a20ae911801593c4d544cdb28de902d97a81673b7 +size 5529195072 diff --git a/sft-llama7b-qa.Q8_0.gguf b/sft-llama7b-qa.Q8_0.gguf new file mode 100644 index 0000000..8373e9d --- /dev/null +++ b/sft-llama7b-qa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7648c8ddfb56b3cb86dc2009189797199ab3135e93f62a34f570c08e3ed0cd1 +size 7161090624 diff --git a/sft-llama7b-qa.f16.gguf b/sft-llama7b-qa.f16.gguf new file mode 100644 index 0000000..3a21f5e --- /dev/null +++ b/sft-llama7b-qa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fa047d183053df11da7ac8373f46a5b688a10c3cd6c0541df1d28c033fd7c7 +size 13478105664