commit 4ecdea8f1b68c4d461cc39318294a7f40fddb87b Author: ModelHub XC Date: Tue Apr 21 22:11:42 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0f067a6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +OpenHermes-Qwen1.5-1.8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Qwen1.5-1.8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ1_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..ab28373 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c8d4340d82aa1387982c219ef24d110343b974fa8edac7137d49891eb86760 +size 695910080 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ1_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..eee0edc --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323b941f991ab4a0fcd2ed1bd2038c7a5bd70fef83b3d1831f7b34c5eba5d035 +size 678510272 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ2_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..a8d86cb --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc851093cd01f7dc1700cd8621a47bfdcb7bc0baeaecc9a0b5a552c7d395255 +size 830376736 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ2_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..fbdfb83 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3bbbddfa6715cbc2cabb99ccccfe14e26b36ce95e2da0ceb29b36c4cca9202a +size 807176992 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XS.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..95c09e7 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e20d8851e9c7ccb1f445d2852d2c710c64556f1c7e95f3963ea7f4a4947c75d +size 751255232 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XXS.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..85ca3ba --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1d909a5cc68663fe10a1efd974abac02abfaa2e24651cf69a353b0ca753a56 +size 724909760 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ3_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..450d4c1 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d44c35eee2023f05fc53590f4a6a522f6f3c26ac2dd9b561cae478ddfbe363 +size 983789312 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ3_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..d01bb53 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d1f2e31d5bdba34f6f1f1d39ecc69f1a7d920a4754fa39af45f287d9ad430f +size 952823552 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XS.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ede51de --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0876bd3fbd47b9530c7ecef835e31ee57d03bacbc1b96aec839f7dc4675bea9 +size 924364544 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XXS.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cf93452 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d8a60a0e2d703c8cb9e6063948f65a6d7948aa91ad16c131cc4bc3230e3c3b +size 859474720 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-IQ4_XS.gguf b/OpenHermes-Qwen1.5-1.8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6d67a74 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21eab181ad95f316ad459a595f92d08326010633aae4738ed513bb3838e9cd9 +size 1080212320 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q2_K.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q2_K.gguf new file mode 100644 index 0000000..a5c14af --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c282cd6f937ba841a17dc20a82cb85f4b3091770ce965e4d26daa6be74ec270c +size 845882016 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q2_K_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..380acbe --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8140420d81a3b2a2b33b16f4d9e0b7d224bdf2ebc7e63c5addd287f4958ac17 +size 829661856 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_L.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bbb6b61 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015c09ae3b7cdbbf6ffa37fd846ce95f8b7097109eb68a9a2c6687f8ae50fd89 +size 1055452928 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cf7183f --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409e172332d7dc9d0beb8cf122a5403ed05a95c298a63bde7c0176ce347e9b79 +size 1015131904 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..275c6aa --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d17fe6595005d92b5f3de0cb01ee860dab143f91c466a3ccc698eae0dd31ae0 +size 952823552 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q4_0.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q4_0.gguf new file mode 100644 index 0000000..4b1700c --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb1f52015ae2b4930740021162e89bef2cbfee257ddce760bff01737d4fd7f9 +size 1121522400 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d8bbc2b --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9183fa70299afc186ec60504098a59dacdaae8897d6bbc59d7a6f2b36a93e255 +size 1216926432 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d2f8d52 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686631d213ce83fe4d0b5d78463bc4e0f1abbf96165ae9843150b1db47fa6b34 +size 1157436128 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_M.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..bcc19d9 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa28c325412aa7f7af9cae91e31ccab140282556a5575db314590fc91459a67 +size 1375875296 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_S.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..50bf9b8 --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425bd0516229a3d314cdcd82a333285221bb5bc2479ecb67da035d9d8c157f04 +size 1326919904 diff --git a/OpenHermes-Qwen1.5-1.8B.i1-Q6_K.gguf b/OpenHermes-Qwen1.5-1.8B.i1-Q6_K.gguf new file mode 100644 index 0000000..e5a79aa --- /dev/null +++ b/OpenHermes-Qwen1.5-1.8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d570970de4865c254e9151b3d5da23f7adebbb9182b0f1a40ce029cc969edf26 +size 1578046656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..09a017f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: vicgalle/OpenHermes-Qwen1.5-1.8B +datasets: +- vicgalle/OpenHermesPreferences-1k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/vicgalle/OpenHermes-Qwen1.5-1.8B + + +static quants are available at https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-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/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Qwen1.5-1.8B-i1-GGUF/resolve/main/OpenHermes-Qwen1.5-1.8B.i1-Q6_K.gguf) | i1-Q6_K | 1.7 | 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..eff7500 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed86117c94b7ac8c3d4f4d94118100cca6257fc533afe50eb31345b47b1d47a +size 1713589