commit c1c34dfd06bcb2250f9f3625644f0ba51c164893 Author: ModelHub XC Date: Tue May 12 19:27:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qra-13b-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fcbfb79 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-13b-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qra-13b-instruct.i1-IQ1_M.gguf b/Qra-13b-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..e0a5c83 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d03f97217ae886c8c0b31887fed2881ad41235dd33eb8541c2be78e5ffa79a +size 3138610752 diff --git a/Qra-13b-instruct.i1-IQ1_S.gguf b/Qra-13b-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..eb1f9aa --- /dev/null +++ b/Qra-13b-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387c38b2747bef2e1ac1a93ee23c9050d0fa2a344519179d8f71ef3ee7d64cae +size 2898687552 diff --git a/Qra-13b-instruct.i1-IQ2_M.gguf b/Qra-13b-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..0ac1784 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfdff2258f92c827df4e6910cf386ff2c3223b8c297f5b25199725d670b20e4 +size 4517580352 diff --git a/Qra-13b-instruct.i1-IQ2_S.gguf b/Qra-13b-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..7c14e36 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1ceaead0697d69248024fcfc0810a7c36e28244089e25605917eae2b97c787 +size 4197682752 diff --git a/Qra-13b-instruct.i1-IQ2_XS.gguf b/Qra-13b-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7d4210d --- /dev/null +++ b/Qra-13b-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c980f83f72a2de2541c7d99f7653ebad921ceab400e46ee291f1169ddd29336 +size 3891148352 diff --git a/Qra-13b-instruct.i1-IQ2_XXS.gguf b/Qra-13b-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c450158 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafa357445f915287545e13f1bc24e4a9a36272d28a8ad7b5cb238adcf0c0b49 +size 3538482752 diff --git a/Qra-13b-instruct.i1-IQ3_M.gguf b/Qra-13b-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..01f218a --- /dev/null +++ b/Qra-13b-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab30525e177570247085ffc5a5a8edbbfa7cc0539ee66556050e40358165fca +size 5984511552 diff --git a/Qra-13b-instruct.i1-IQ3_S.gguf b/Qra-13b-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..add45e9 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a911c21bd42126b293bc4f1e205be4834fc148747d776a7b5590caed1d671903 +size 5658981952 diff --git a/Qra-13b-instruct.i1-IQ3_XS.gguf b/Qra-13b-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a510e25 --- /dev/null +++ b/Qra-13b-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbfea1eaa29dbc5ab8d8ac438c99ad6911b33a15600098147a0db61109cef597 +size 5361612352 diff --git a/Qra-13b-instruct.i1-IQ3_XXS.gguf b/Qra-13b-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7b25c0f --- /dev/null +++ b/Qra-13b-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0013615451bbc0e273d6558b13a03fcfceea2804c9d477f7fdf4db68328f6cce +size 4960562752 diff --git a/Qra-13b-instruct.i1-IQ4_XS.gguf b/Qra-13b-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..dfa035c --- /dev/null +++ b/Qra-13b-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daac9126f76c1e3a24eba0c37f67c6300b36abdff412e0f7db1e8b169e3a4d5 +size 6964223552 diff --git a/Qra-13b-instruct.i1-Q2_K.gguf b/Qra-13b-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..f5c3e0d --- /dev/null +++ b/Qra-13b-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd3d8d7b0f125d0a497a605413fd10d9b1ceabdff3409e7593d981e5a57805e +size 4854271552 diff --git a/Qra-13b-instruct.i1-Q3_K_L.gguf b/Qra-13b-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0250c92 --- /dev/null +++ b/Qra-13b-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6667e6e19cb6468219356c5ce638b4c6cf3b40747b203c6636175d6cd8e0426 +size 6929561152 diff --git a/Qra-13b-instruct.i1-Q3_K_M.gguf b/Qra-13b-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b016b54 --- /dev/null +++ b/Qra-13b-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b8b404bca3b7a23b2805ec6e4bc861679f5d7b7942aaf1d714b3d779cbfa4e +size 6337771072 diff --git a/Qra-13b-instruct.i1-Q3_K_S.gguf b/Qra-13b-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..40bcc34 --- /dev/null +++ b/Qra-13b-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d05fe4b1b0d6ad6314584de53d8a8ce6cb5e525dcf2c37337f51a5ef0fd580 +size 5658981952 diff --git a/Qra-13b-instruct.i1-Q4_0.gguf b/Qra-13b-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..f84a609 --- /dev/null +++ b/Qra-13b-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa4c4c92bcaa33bfe91c3f7a9ec576c7be05caa6032d2f0167d4592d1ab4869b +size 7387954752 diff --git a/Qra-13b-instruct.i1-Q4_K_M.gguf b/Qra-13b-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6e4076f --- /dev/null +++ b/Qra-13b-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb367df94385d2d4b41c45e76d5cd99f1b82d1c152650c0d87d1590c64b27b6 +size 7865957952 diff --git a/Qra-13b-instruct.i1-Q4_K_S.gguf b/Qra-13b-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f718a82 --- /dev/null +++ b/Qra-13b-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d5409b6f4580568d73b170fa2277eeda0843b470bc0f0bbe70b1c7e1d6eba3e +size 7423180352 diff --git a/Qra-13b-instruct.i1-Q5_K_M.gguf b/Qra-13b-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..27e9f67 --- /dev/null +++ b/Qra-13b-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e6214f884df75ce37d04453466ebcea439df8f641fd5c70703db2fbf032312 +size 9229925952 diff --git a/Qra-13b-instruct.i1-Q5_K_S.gguf b/Qra-13b-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a0e17ff --- /dev/null +++ b/Qra-13b-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abcfcfe67a727e316a5f9fbe009ff6f0dfdfb6e103b3ef204b313332bba82e1 +size 8972287552 diff --git a/Qra-13b-instruct.i1-Q6_K.gguf b/Qra-13b-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..54a129d --- /dev/null +++ b/Qra-13b-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5ee01d72b80188b2c29b6723618ce01533197f359e942f702c2d68a2865548 +size 10679141952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e56645 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: TeeZee/Qra-13b-instruct +datasets: +- Lbuk/alpaca_data_pl.json +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/TeeZee/Qra-13b-instruct + + +static quants are available at https://huggingface.co/mradermacher/Qra-13b-instruct-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/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-13b-instruct-i1-GGUF/resolve/main/Qra-13b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K | + +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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..2a3ad7c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef556f27a9b698b4fa5c70a11760e72a2b2c8bc6a7698191be1c6570e2608e4 +size 7136325