commit fb7a0f39cffa2dc232a664ed7fc9ed0d594b7434 Author: ModelHub XC Date: Fri May 8 15:59:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12b4fcf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.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 +Ahma-SlimInstruct-V1-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-SlimInstruct-V1-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ1_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..91e5f61 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212435378e2a9857e170dd7975af2ad9fb9a8f6c3dd6150cb9deb47d843247ac +size 1786047392 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ1_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..276c1aa --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38cfb5dd720e061dec34cb3b3e8a1360d6ae9ddcdc49c4aefd1b93a865e267b +size 1663658912 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ2_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..3447c03 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c948a3a36f6188c57eaf5194a42076267c2a44168a33bee4fda71c36d58ee6 +size 2508245920 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ2_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..ae2dc57 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356d3da6daab4c7d9af623eaff95126943ef68bb9ea601b0c73167e499a04f86 +size 2345061280 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ2_XS.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..268afb7 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc5e14ee67ffe89b2230a08bc5aa70c02e94d3a55936344b55a57cf0131a2f9 +size 2169990048 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1de29d7 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7846827ec0bab807c624a43514d711953bad7e6dee67066256656a631f22bd75 +size 1990028192 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ3_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..ddfacc7 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0822c49432fc248a156b05b079824f690f4d49b3b388d853ee25f241781101 +size 3280907168 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ3_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..b6b2d07 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c816fb8f54841fd42813d23e9f72509c08b2029a0fa885982a0cfd9719c7ae +size 3114347424 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ3_XS.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e237e40 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f24d8a2db3806dd0bb426670b0cf971de4fa2d895b8a88bf02017ce40c33a79 +size 2962566048 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..814735a --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cd4e816fd0ae02fca399ed71fed3daab599ad1f0ae85f8ef7b97892a5830c0 +size 2733886368 diff --git a/Ahma-SlimInstruct-V1-7B.i1-IQ4_XS.gguf b/Ahma-SlimInstruct-V1-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c5f1e95 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1c5a1f303c5bbcb3c7be715194a69db79df6e89351b70d4e978d7ea0ffe52c +size 3798797216 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q2_K.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..043e607 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50dda7984196c871efd08f72867fff8e7e0039d50df6f84fca3da33da89df4c3 +size 2685488032 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q2_K_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8b7f208 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c176b11602f2ee09cf31ab75977a966d26332c6a38098b7a67082edadc7601b8 +size 2472168352 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q3_K_L.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..abb227c --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1abe194c79d85bc0cb300244fc844cdddbf175812aacf41cc5d2dc5f23e6ea30 +size 3763153824 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q3_K_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a6f55f0 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00add9e73110ba34e212f869a4989a560dd27ab4424d6282ec8a923696e9353 +size 3464047520 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q3_K_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e0bd18a --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4074494b267014ce328b69e1b678491a1bd8b6048007bd70bda260d54de4f4 +size 3114347424 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_0.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..fd68883 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072d0540e46e71f520cb2f4fdd803db491adc7705de1385979fb15315cd0b781 +size 4020669344 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_4.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..564b37b --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ff539598250eb5ce29b80c5e316488c90d9d2b954827b67f1b71b399349d04 +size 4009397152 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_8.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..0b49610 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9e2f475616852ace04720ae8117b63ddb1c578db78c0a5e31ab942ca4d8cb3 +size 4009397152 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_0_8_8.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..a85c8ab --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc94ceb34f78a405353a90faef562bd4b8ef0fd943bf24a7bdb599a215d23b68 +size 4009397152 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_K_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8d0ff6e --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c6209cd56379e81b690c5d27abc08effd0982618bc454d2833f528c18d8e73 +size 4264594336 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q4_K_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3059286 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b394813c9a277af507e22693a16b846563498d7ba73b8ca625d149f99246d3 +size 4040330144 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q5_K_M.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..797e124 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314ed7c5051ce6fe2243e64cebe5a66855f9be63b699c4f7514fa59f69e98afa +size 4983262112 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q5_K_S.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1972f4a --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e43d043256af6ddc2562573e3d29cd0b10df6094a486ac7d7599e6cbc2d6866 +size 4851796896 diff --git a/Ahma-SlimInstruct-V1-7B.i1-Q6_K.gguf b/Ahma-SlimInstruct-V1-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..3b56273 --- /dev/null +++ b/Ahma-SlimInstruct-V1-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180e0ad4e6dd87c9b71a147053b4168c5623897a31b5a8aa722577541eb9bc35 +size 5746846624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..42c8c19 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: mpasila/Ahma-SlimInstruct-V1-7B +datasets: +- mpasila/LumiOpenInstruct-GrypheSlimOrca-Mix +- LumiOpen/instruction-collection-fin +- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned +language: +- en +- fi +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mpasila/Ahma-SlimInstruct-V1-7B + + +static quants are available at https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-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/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.1 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.1 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.1 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Ahma-SlimInstruct-V1-7B.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | 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..de7d4b7 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee24740d75e83fc4902c9312ca3e59c48f86ccb164be364bcc24501a27e5d2cb +size 4562173