commit 4e7fe1cd5f051a1e7224d249d4afabceed9812c1 Author: ModelHub XC Date: Tue May 19 22:09:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeciLM-6b-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2896043 --- /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 +DeciLM-6b-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeciLM-6b-instruct.i1-IQ1_M.gguf b/DeciLM-6b-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..6dd21d3 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a70f7fc33f867ae236cfeb6b46a41a7288646d3cabe5e2478d0eb4d12bf412e +size 1377850784 diff --git a/DeciLM-6b-instruct.i1-IQ1_S.gguf b/DeciLM-6b-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..ddb0959 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b756f2f5b133f780309779bc2a50b49fb7ad6333c4995428bdd2efa9d0e1c3a +size 1267430816 diff --git a/DeciLM-6b-instruct.i1-IQ2_M.gguf b/DeciLM-6b-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..624c728 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a153b7c701b6095ea20354ad1cee772e6a5e995b66547e8f1d7373def5a5cb1f +size 1980241312 diff --git a/DeciLM-6b-instruct.i1-IQ2_S.gguf b/DeciLM-6b-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..0448722 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58e17010bd1a3f52dbd47360e37baeb464042ad2fc48c19af83d7049f1118cb +size 1833014688 diff --git a/DeciLM-6b-instruct.i1-IQ2_XS.gguf b/DeciLM-6b-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2cd7a82 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9626ad65eab7a7f4ef10fa07a768cdeb612c14bb779455cef3fe2b63209bc88 +size 1725887904 diff --git a/DeciLM-6b-instruct.i1-IQ2_XXS.gguf b/DeciLM-6b-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3611116 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ff171c8b9adaf9f6d870dc75c153ecb52d7b603f2b1b07103bf56ab66d602e +size 1561884064 diff --git a/DeciLM-6b-instruct.i1-IQ3_M.gguf b/DeciLM-6b-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..22c5c9b --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c850fc48afe23c9aef3279ccbf3d820f111641f59d1b59d8495a422893617db6 +size 2608199072 diff --git a/DeciLM-6b-instruct.i1-IQ3_S.gguf b/DeciLM-6b-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..687324d --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016a958360430bfc7af44ddc97313063af59246f6d692bab4ac3ecc2922c2014 +size 2512942496 diff --git a/DeciLM-6b-instruct.i1-IQ3_XS.gguf b/DeciLM-6b-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..dfc591a --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f4c2afb8ed2f4c9ed88776408af86b946cd1058952988e80085997a3aebce3 +size 2385098144 diff --git a/DeciLM-6b-instruct.i1-IQ3_XXS.gguf b/DeciLM-6b-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3c78af3 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44aaf1d54cc3a30316607425fe47b60767e46bb68f2ef1a0e7819badd4629824 +size 2231047584 diff --git a/DeciLM-6b-instruct.i1-IQ4_NL.gguf b/DeciLM-6b-instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4cf88a0 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476dc12804d72e35e6906b5f356fec255d2d353c7f9dffd55ec06d0fb0768a22 +size 3254597024 diff --git a/DeciLM-6b-instruct.i1-IQ4_XS.gguf b/DeciLM-6b-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..cf3a117 --- /dev/null +++ b/DeciLM-6b-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84ad7b8ab8715653d0032686159da2395756f1055bca11ceab3db4efc8e70c0 +size 3080861088 diff --git a/DeciLM-6b-instruct.i1-Q2_K.gguf b/DeciLM-6b-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..e0321d8 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af2ff44945930693c6fe34bfa48c9da9670c8f759eee907304f66f6cc9a4cb3 +size 2149365152 diff --git a/DeciLM-6b-instruct.i1-Q2_K_S.gguf b/DeciLM-6b-instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d243f97 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b6cc2e42ffb6e4df19aff7e5e2cf2f72a098768a6acfcc56a6e2414df80e74 +size 1990571424 diff --git a/DeciLM-6b-instruct.i1-Q3_K_L.gguf b/DeciLM-6b-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..83dfbbe --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4a40f232bf02772cedda96131613d19c74c312600b6f61ed63c414ecdc62e6 +size 3026613664 diff --git a/DeciLM-6b-instruct.i1-Q3_K_M.gguf b/DeciLM-6b-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f84922d --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff12d746c59bd29bbc5dcab1a98606b3e0fce3226a193b611e25b8da32b5fea +size 2787538336 diff --git a/DeciLM-6b-instruct.i1-Q3_K_S.gguf b/DeciLM-6b-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b313555 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ff45d0ac0878b6be92b185e703353ab995e9b7c337512ce38f87ec524931da +size 2509460896 diff --git a/DeciLM-6b-instruct.i1-Q4_0.gguf b/DeciLM-6b-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..b413aeb --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9306d835651aa08d13eb7de776ab82bcc2da65b0cb4e89d3697e61d3f8635739 +size 3262592416 diff --git a/DeciLM-6b-instruct.i1-Q4_1.gguf b/DeciLM-6b-instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..abb1558 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3b5571f11ed49c472b862c6f5d03e7877bcc29eb6d9a630fbb5944fe6b12f4 +size 3600430496 diff --git a/DeciLM-6b-instruct.i1-Q4_K_M.gguf b/DeciLM-6b-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..29595dd --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d45b5237e3eab9afddbc980184f3347e370a8c637ff2270aa1a8545129b3659 +size 3441366432 diff --git a/DeciLM-6b-instruct.i1-Q4_K_S.gguf b/DeciLM-6b-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8f24619 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a054dcc0dc8723d62e7aa0f5ce667723acc66238fec60b260878fd9e878348 +size 3274519968 diff --git a/DeciLM-6b-instruct.i1-Q5_K_M.gguf b/DeciLM-6b-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..46abd8c --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff97a1957ef8afc0bcee882bdbd613f80b22ca91fabc8e08a34f7c89d9573956 +size 4047443360 diff --git a/DeciLM-6b-instruct.i1-Q5_K_S.gguf b/DeciLM-6b-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6913ebb --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec6fb9953383fbdf443617db1beaa350d0aed90dabe9b10884f333b278746dff +size 3949540768 diff --git a/DeciLM-6b-instruct.i1-Q6_K.gguf b/DeciLM-6b-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..fd541a4 --- /dev/null +++ b/DeciLM-6b-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f56fe408cb810c386110fb2a36656e1d0e251bbd045934d756487e3469317c +size 4691400096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a139a42 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Deci/DeciLM-6b-instruct +datasets: +- cerebras/SlimPajama-627B +- Open-Orca/OpenOrca +language: +- en +library_name: transformers +license: +- llama2 +- other +quantized_by: mradermacher +tags: +- Deci AI +- DeciLM +- Instruction +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Deci/DeciLM-6b-instruct + + +static quants are available at https://huggingface.co/mradermacher/DeciLM-6b-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/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 2.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 2.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.4 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 3.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 3.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q4_1.gguf) | i1-Q4_1 | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-i1-GGUF/resolve/main/DeciLM-6b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 4.8 | 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..ae8be5c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1e24df2cc7c3b9ff63115780c23eb6060615948e06d59988076f4819c52695 +size 4562173