commit 4efe90e371240bd8a05450427a782704c65aa705 Author: ModelHub XC Date: Sun Oct 4 08:46:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..04ddf8a --- /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 +MegaBeam-Mistral-7B-512k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +MegaBeam-Mistral-7B-512k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ1_M.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ1_M.gguf new file mode 100644 index 0000000..90721cd --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1787f6d95cbba9e817c146602a19b4d640610932cb8595a2d27366fa53ed40 +size 1754447776 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ1_S.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ1_S.gguf new file mode 100644 index 0000000..857763b --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c44f590c20daaf9cfae05bdb89c41323add363a6410b475df3be46d7a262cb +size 1612103584 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ2_M.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ2_M.gguf new file mode 100644 index 0000000..d40f7ff --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53eb08be34f26bff10dbc73e6b1436af17c331425607ff2a6fcd4d8c4119042 +size 2500714400 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ2_S.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ2_S.gguf new file mode 100644 index 0000000..1842ef6 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fb11b8f54917a03093760178f7278f59e06d1b0be8d3c23d910e244bcb20c2 +size 2310922144 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ2_XS.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..652e3ae --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d564d31b50519346be4e0f60b4a7fde88c02ea90fc1fd95dfa67dabfa11917f4 +size 2198257568 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ2_XXS.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..59e1e2e --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb64ffb4df9a47a23e4e77c86a1daba324bacfe5b4a4bf16507a71c7158d32af +size 1991688096 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ3_M.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ3_M.gguf new file mode 100644 index 0000000..391ba0d --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:871352b5c11c3e541c535c5843953b5f7859cb7c0e06467c5b9fb8eb5faf92dc +size 3284893600 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ3_S.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ3_S.gguf new file mode 100644 index 0000000..09d7a19 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03501fd3ddb890fc57b54681c632edebd808aca05c028e9d79d21fab380896e0 +size 3182395296 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ3_XS.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d5b8c67 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8338ccbaddc17ebdc63beea463855992b385906a6c8e68b34c257e4ff826dfbe +size 3018817440 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ3_XXS.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5da6944 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72081f578609a433d634d3b22bd1c3a264464abb2e1e123d5ddbffd31c5c756 +size 2827345824 diff --git a/MegaBeam-Mistral-7B-512k.i1-IQ4_XS.gguf b/MegaBeam-Mistral-7B-512k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e3812cb --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f507d3ec721fc1e54d6243f63c4591256fcecd0bfbb97f280aabf212b0f2787e +size 3907690400 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q2_K.gguf b/MegaBeam-Mistral-7B-512k.i1-Q2_K.gguf new file mode 100644 index 0000000..fe11279 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf97a83584e5de14b2af0e9fd189f9d47ad951fdc5deae8380271a1ab539dba +size 2719244192 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q3_K_L.gguf b/MegaBeam-Mistral-7B-512k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bbe7118 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d578d10785649955782b47d00a2525a3d85eb2b135a3d58029e17a1f25053a16 +size 3822026656 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q3_K_M.gguf b/MegaBeam-Mistral-7B-512k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b39995e --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7740654244b0c61b46409cfcd15bdec03847b6cdbd909c6b45bea0d5bcbb43e9 +size 3518988192 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q3_K_S.gguf b/MegaBeam-Mistral-7B-512k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e4fc1d6 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd276a80367c367e01e291d7ce978f1eea38a957803e35b16e98c2a319dd995 +size 3164569504 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_0.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_0.gguf new file mode 100644 index 0000000..0fa607a --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b29cad63e99d1b6cc83e8349140b0caff61a5801131601d087b47ed82663fb +size 4123598752 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_4.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..69a686c --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b2c23705f172c9b3f7b83c5f4ce4c5aec4f4533a2ffa83988ba368756f73e9 +size 4108918688 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_8.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..65bc285 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10dec21e24b7154f6dad2497b83aace1508706ccc4c11d1f34c8103aa2a72f9a +size 4108918688 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_0_8_8.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..2482a48 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c7281fff799944b205512163bc358e9a9f8c704d3ed4d740b754cbfb94251e +size 4108918688 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_K_M.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..403502b --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff7fae47d2e7f58974758e2d3d396de55deb9486825d38a09b68b6098ec462d +size 4368441248 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q4_K_S.gguf b/MegaBeam-Mistral-7B-512k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..26d187f --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c12155b1e9a173d5a9f582f1e0a85dace1f44b1ae2de0b8f70c01b365a9f96 +size 4140375968 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q5_K_M.gguf b/MegaBeam-Mistral-7B-512k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cb8007d --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610119e756ce5dc63557cd07f520fc01a804a167e30cbf3d9592bb65af4fd3e3 +size 5131411360 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q5_K_S.gguf b/MegaBeam-Mistral-7B-512k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9dc3337 --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b42cca094217ee567cca85ccfdab9efc3f2219b6c25dbebc87296e5fcbb89ec +size 4997717920 diff --git a/MegaBeam-Mistral-7B-512k.i1-Q6_K.gguf b/MegaBeam-Mistral-7B-512k.i1-Q6_K.gguf new file mode 100644 index 0000000..4f1f61e --- /dev/null +++ b/MegaBeam-Mistral-7B-512k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b40714cadaa46659c30d0a07ecb086a27d33cc8fb0436f7363c5726f561451 +size 5942067104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0777a84 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: aws-prototyping/MegaBeam-Mistral-7B-512k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k + + +static quants are available at https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-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/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MegaBeam-Mistral-7B-512k-i1-GGUF/resolve/main/MegaBeam-Mistral-7B-512k.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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..cfd82c5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3cfd0c70a39c85809c4d78ab8718df6f8bc3fc101b595592ac9b55744354cf +size 4988157