commit 1ad46b38ab70d1635b4986877a41271f34a0f72f Author: ModelHub XC Date: Wed May 6 20:05:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/docsgpt-7b-mistral-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..957fdac --- /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 +docsgpt-7b-mistral.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.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..f22fe1c --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Arc53/docsgpt-7b-mistral +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- rag +- closed-qa +- context +- mistral +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Arc53/docsgpt-7b-mistral + + +static quants are available at https://huggingface.co/mradermacher/docsgpt-7b-mistral-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/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-i1-GGUF/resolve/main/docsgpt-7b-mistral.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | 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/docsgpt-7b-mistral.i1-IQ1_M.gguf b/docsgpt-7b-mistral.i1-IQ1_M.gguf new file mode 100644 index 0000000..56adfb7 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ca6ab1ddc9cf8b3cf8354f1e070aa73debdb4a902145f954d233602d7f9336 +size 1754447136 diff --git a/docsgpt-7b-mistral.i1-IQ1_S.gguf b/docsgpt-7b-mistral.i1-IQ1_S.gguf new file mode 100644 index 0000000..7a71917 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15a37ec2699ecb59b3669bc236871fdd0531757a03a23fd7779358da761a414 +size 1612102944 diff --git a/docsgpt-7b-mistral.i1-IQ2_M.gguf b/docsgpt-7b-mistral.i1-IQ2_M.gguf new file mode 100644 index 0000000..9ca5845 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41dc66d9c41b7fa7d140924d8828b0cd9eb6a36b76422cecba20d7c4613d3705 +size 2500713760 diff --git a/docsgpt-7b-mistral.i1-IQ2_S.gguf b/docsgpt-7b-mistral.i1-IQ2_S.gguf new file mode 100644 index 0000000..e4cfdb3 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c0f76f68505b41d6e1cd31b32d0935ce2900e80569ef8fecbb73dfaeb0197c +size 2310921504 diff --git a/docsgpt-7b-mistral.i1-IQ2_XS.gguf b/docsgpt-7b-mistral.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c93b4f3 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f573cb37d4a33e8f89e7a541c7520eca69760b5e6c72e71c33640551bb3f53 +size 2198256928 diff --git a/docsgpt-7b-mistral.i1-IQ2_XXS.gguf b/docsgpt-7b-mistral.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c0390fa --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb657eda18b662c6e840aec37c361908cc001314a9c3de2e9d4f894cfe3f3eb +size 1991687456 diff --git a/docsgpt-7b-mistral.i1-IQ3_M.gguf b/docsgpt-7b-mistral.i1-IQ3_M.gguf new file mode 100644 index 0000000..67bc106 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1c58deb478f57e995508e94806f160334301106d07e9b23f5dca01c4ddb93a +size 3284892960 diff --git a/docsgpt-7b-mistral.i1-IQ3_S.gguf b/docsgpt-7b-mistral.i1-IQ3_S.gguf new file mode 100644 index 0000000..f11900a --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:505618d84136ae8f5b5da3c806f0cbb9ce4f115f71b6f85f533ba4a2d94bcb55 +size 3182394656 diff --git a/docsgpt-7b-mistral.i1-IQ3_XS.gguf b/docsgpt-7b-mistral.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4d81164 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4da1374f80604444e00b633fd3f5503cf234411a187675984f4d5350526051d +size 3018816800 diff --git a/docsgpt-7b-mistral.i1-IQ3_XXS.gguf b/docsgpt-7b-mistral.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..eb5d112 --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35f0b341c9b4d507372591a337ef131c0186ec8ff0a0fca93238da9dff505989 +size 2827345184 diff --git a/docsgpt-7b-mistral.i1-IQ4_XS.gguf b/docsgpt-7b-mistral.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b6f4afb --- /dev/null +++ b/docsgpt-7b-mistral.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278a84ef50e0401790a6f2db89eaeed4ac9dfb6394493f52407535006fc6aebf +size 3907689760 diff --git a/docsgpt-7b-mistral.i1-Q2_K.gguf b/docsgpt-7b-mistral.i1-Q2_K.gguf new file mode 100644 index 0000000..8c305df --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f8b04d6aff017fb4fa6159545b8efb3f97719cc536367da8d360316e469e03 +size 2719243552 diff --git a/docsgpt-7b-mistral.i1-Q3_K_L.gguf b/docsgpt-7b-mistral.i1-Q3_K_L.gguf new file mode 100644 index 0000000..da992f3 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0c2364d9b1ef0803ab9f3898b0bdefdf41e61c9777c371c43a198bc8a75085 +size 3822026016 diff --git a/docsgpt-7b-mistral.i1-Q3_K_M.gguf b/docsgpt-7b-mistral.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7cc29cf --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153fb328c9ebb95715657b18c36a5f384799dcd3339c64284b2f3edf2b724777 +size 3518987552 diff --git a/docsgpt-7b-mistral.i1-Q3_K_S.gguf b/docsgpt-7b-mistral.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b647323 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b236e43a68b4dc2e4ce3698e28325aef2cde316cbc2557dccf8e4f681cea601 +size 3164568864 diff --git a/docsgpt-7b-mistral.i1-Q4_0.gguf b/docsgpt-7b-mistral.i1-Q4_0.gguf new file mode 100644 index 0000000..908cfdb --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c4e6932ea726434a54e58bf8ec224173046d9688937c9cebb7cde622836056 +size 4123598112 diff --git a/docsgpt-7b-mistral.i1-Q4_0_4_4.gguf b/docsgpt-7b-mistral.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..e9fd447 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902d43be8aedd9c18798f437d6002405e6a71c0b85aa640f5be1ed4b5fd25923 +size 4108918048 diff --git a/docsgpt-7b-mistral.i1-Q4_0_4_8.gguf b/docsgpt-7b-mistral.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..49a6d61 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7591fbd0db49b3c009c82f70db31980de54f06c64350b6c34e654da708b8ef8d +size 4108918048 diff --git a/docsgpt-7b-mistral.i1-Q4_0_8_8.gguf b/docsgpt-7b-mistral.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..489fc46 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48670cbb49aff18c9cc210a0183adfb89e545f8559e31e478bda1a0043e6fa52 +size 4108918048 diff --git a/docsgpt-7b-mistral.i1-Q4_K_M.gguf b/docsgpt-7b-mistral.i1-Q4_K_M.gguf new file mode 100644 index 0000000..21ee70c --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef065e0586775c135a9fa16ec9ec073e80449e96395ea97efe00e55d3ef3200d +size 4368440608 diff --git a/docsgpt-7b-mistral.i1-Q4_K_S.gguf b/docsgpt-7b-mistral.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c60443c --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6697a35cd40408314fb996e1fcb81442be49908818f92531c3d35c9fd7eed806 +size 4140375328 diff --git a/docsgpt-7b-mistral.i1-Q5_K_M.gguf b/docsgpt-7b-mistral.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f186242 --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23992dd18a28c8fd29e2bddf2f4156dd7c2bc89d95a6a4481f765b16273ca839 +size 5131410720 diff --git a/docsgpt-7b-mistral.i1-Q5_K_S.gguf b/docsgpt-7b-mistral.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fc6505a --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d904f39da2a88a9cb9f4a85d781bf2e40f98bd0dbc11036ef9cfcd2f95e293c +size 4997717280 diff --git a/docsgpt-7b-mistral.i1-Q6_K.gguf b/docsgpt-7b-mistral.i1-Q6_K.gguf new file mode 100644 index 0000000..168d19d --- /dev/null +++ b/docsgpt-7b-mistral.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c676c5cbb58a3b3a3afa0cf097a256ec1c54e5337b3d6201ec92da05aea2d2de +size 5942066464 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..7522e95 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45bf7f5bfc8c9888fed499f5e73d5b369e0f1e6cd5ff8cc1cd02731f9036bfe +size 4988157