commit 0eee4c6ac17a5f87f3b33ac0fabe95abb7991e85 Author: ModelHub XC Date: Mon Jul 20 02:27:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mpt-7b-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a23c65 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +mpt-7b-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9edbcf0 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: mosaicml/mpt-7b-instruct +datasets: +- mosaicml/dolly_hhrlhf +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Composer +- MosaicML +- llm-foundry +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mosaicml/mpt-7b-instruct + + +static quants are available at https://huggingface.co/mradermacher/mpt-7b-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/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 3.9 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 3.9 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-instruct-i1-GGUF/resolve/main/mpt-7b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | 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..470ae93 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00bef9f51d765232f5f6cec5c90b2bd4324b7ba36e0fc7fb00d8fb99bba9f963 +size 3674395 diff --git a/mpt-7b-instruct.i1-IQ1_M.gguf b/mpt-7b-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..95c8ddb --- /dev/null +++ b/mpt-7b-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3861874ce6c7938f2aa4f7d7c6fc917cda19b5a175320e8bdef69098197281 +size 1604483296 diff --git a/mpt-7b-instruct.i1-IQ1_S.gguf b/mpt-7b-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..942363a --- /dev/null +++ b/mpt-7b-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33396ae19759ad3bec24ec74b5595a9c39d8433ce2278cbfa7aa90a44333828a +size 1472362720 diff --git a/mpt-7b-instruct.i1-IQ2_M.gguf b/mpt-7b-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..1599751 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235e19da432d3d4a757b0748edc3a9b2d33b898728edb4a5dac0d1939e85610c +size 2296543456 diff --git a/mpt-7b-instruct.i1-IQ2_S.gguf b/mpt-7b-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..7dba093 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc44fc42c09c61e6bbe71931940b6dbceeb029af83f84bea11730e6ff238ac18 +size 2120382688 diff --git a/mpt-7b-instruct.i1-IQ2_XS.gguf b/mpt-7b-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2e10381 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e359a8fdcb9b43af8b06d2a5d7dd8ee60f1705f8f0e73370153a2298c06481 +size 2017622240 diff --git a/mpt-7b-instruct.i1-IQ2_XXS.gguf b/mpt-7b-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d08ae97 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23bed103d4acffed6e1fc564cb2305383432bffcc75aa8fb66ff858b1499cac +size 1824684256 diff --git a/mpt-7b-instruct.i1-IQ3_M.gguf b/mpt-7b-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..d068d43 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750a12131211daf428e6c174933e4eaa1fefd84879e817b274fb72dd00ed7a41 +size 3261405408 diff --git a/mpt-7b-instruct.i1-IQ3_S.gguf b/mpt-7b-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..70b9e68 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6d4b806705356343b544442a1b677362c3e74bd0718c8c1dc794aa57dd7f7a +size 2940541152 diff --git a/mpt-7b-instruct.i1-IQ3_XS.gguf b/mpt-7b-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7efdff5 --- /dev/null +++ b/mpt-7b-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b627d58793d162304e20f3c77cd790e651a235b44012d8d22e92f516e470087 +size 2865043680 diff --git a/mpt-7b-instruct.i1-IQ3_XXS.gguf b/mpt-7b-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9ab1bdd --- /dev/null +++ b/mpt-7b-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c278138c38690090bb360ccbf1ed243d2843132402fc1dd0417c6591a95969b3 +size 2636282080 diff --git a/mpt-7b-instruct.i1-IQ4_XS.gguf b/mpt-7b-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3db01da --- /dev/null +++ b/mpt-7b-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e71f64ad3665b45480c2003454d511cffbe6c00547240b19e9a1a0cd798aa5 +size 3594852576 diff --git a/mpt-7b-instruct.i1-Q2_K.gguf b/mpt-7b-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..a3e1c9c --- /dev/null +++ b/mpt-7b-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8801a7685dc1b6eb1d466b6a4bfb5f6a439e614f5c7b133897c15721ee9c423 +size 2558859488 diff --git a/mpt-7b-instruct.i1-Q3_K_L.gguf b/mpt-7b-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4ef7eb2 --- /dev/null +++ b/mpt-7b-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e93fbac6048dad76aa24fe981d54a948036c486a399f9ed97e378170aec495a9 +size 3846510816 diff --git a/mpt-7b-instruct.i1-Q3_K_M.gguf b/mpt-7b-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4c01c9d --- /dev/null +++ b/mpt-7b-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db42d21e10ae60ae2cbcbd7afaf44b9fca2773be8a709e8421fc26bdf7ea1269 +size 3527743712 diff --git a/mpt-7b-instruct.i1-Q3_K_S.gguf b/mpt-7b-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3cee02c --- /dev/null +++ b/mpt-7b-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf79ca691c7c56e0f76939b0b5eabd4e30cc417465e1ccf2d806a6f8c7290b30 +size 2940541152 diff --git a/mpt-7b-instruct.i1-Q4_0.gguf b/mpt-7b-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..7572b91 --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf38806cd520505a58f428692257196f5c7504fb42ad215920a0ac18ed5082f9 +size 3812956384 diff --git a/mpt-7b-instruct.i1-Q4_0_4_4.gguf b/mpt-7b-instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..73f3b9a --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfbb78a589386d05356285a47a447fbd1cfe0e4d37f3fc5c30c0f51baae8774 +size 3796179168 diff --git a/mpt-7b-instruct.i1-Q4_0_4_8.gguf b/mpt-7b-instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..b562dcb --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6033bd8311e5906890bf9e6fc038b422e3ab2791b664ef3562e3419d31df3316 +size 3796179168 diff --git a/mpt-7b-instruct.i1-Q4_0_8_8.gguf b/mpt-7b-instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..28e8b67 --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f92e8585e7dee3b411bc76eaf5eb24e0d0c512f2bd533b41e02ce400e4f1885 +size 3796179168 diff --git a/mpt-7b-instruct.i1-Q4_K_M.gguf b/mpt-7b-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..94ca08b --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c50bf0b790ca99493a1420451f5558978dc67f55bfb2d30161381eb6440a57b +size 4274329824 diff --git a/mpt-7b-instruct.i1-Q4_K_S.gguf b/mpt-7b-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5dcc808 --- /dev/null +++ b/mpt-7b-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972bc90e747924c205d3659e10eccc572ff42b911ebc1150edf65c201c50a0c3 +size 3829733600 diff --git a/mpt-7b-instruct.i1-Q5_K_M.gguf b/mpt-7b-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c872245 --- /dev/null +++ b/mpt-7b-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50e23eed42301f31f5011b308424453a70b11e555aa662e4f7e9b0807d05b2b +size 4958001376 diff --git a/mpt-7b-instruct.i1-Q5_K_S.gguf b/mpt-7b-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d64c9a0 --- /dev/null +++ b/mpt-7b-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d1ec88cfbc81b0853b4e92a8f6ad34d99eebf54e40ebda4acdf7698558d202 +size 4601485536 diff --git a/mpt-7b-instruct.i1-Q6_K.gguf b/mpt-7b-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..af549de --- /dev/null +++ b/mpt-7b-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3a2ea91242ddf9a18b1eb8980473575976930e3786cea668fc7db81c498214 +size 5457123552