commit 25732924ff1cd3a95fa817597b96768ef4f2a4ef Author: ModelHub XC Date: Mon May 4 17:56:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..68f872c --- /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 +Humanish-Qwen2.5-7B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..169a9cb --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb792c8fb60eacd7818ff241f755b150705b2840a782a77da58d7bd8f378eb8 +size 2042194784 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..1b39222 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc639a491d132840d33518b1f291ef765af3f5ba72f756e26abf8da08f6b03ef +size 1903666016 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..ba7c83e --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3c6f56087451144d1e222f066bd786499c605602ba12527997fb659fb36c28 +size 2780341088 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..f9d03b7 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e431052c117ae35a0443f0540b12400898c274a67dafb9a350a8328b235995 +size 2595636064 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..dbea7e6 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0309378f0290eeebdee9d0b29b5c2d6ad44290f6aad83ec6ff605d9e2d3b34e6 +size 2469020512 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f926c17 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebac6dbbee4e61be0fa5acc9086a772c5ad1ae24433e4c89522dfb182a23dc6f +size 2273076064 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..1406bf4 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b48d99316d2acca7166fc8e8695c4394f35e06df8fe153a892f5563f0e6dba +size 3574010720 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..d6e90e2 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22ce749afdc0394a812567c338bfc101c5711266adb7e9e4db8702ad7c571ab +size 3499191136 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..305869d --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17888c0b58c6d5470300e02a50a6aa205584a45084deb7628eb2ed38cc83b12 +size 3346254688 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f6e1818 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e3f3666e608a6666e83e9a2c6a466a72a405c244f4725067d08145959ff983 +size 3114513248 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0538337 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80729d6cba0aad03bb310f21de54b50101dddc0330cf93c8b570fac7f67f08e +size 4218471264 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q2_K.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..13c4ed8 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4c03e5071e487cd5b80c39654cdc5929ea52ab0960985ac478b23f946db63e +size 3015938912 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c2692e4 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaacb3bf9a8b9b4874101eda66ed5b142915af785248d1e3359d3c21107ee362 +size 4088458080 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..26ca4c2 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236ba70190180f2a4f183e7ca540d74918af91c6244a5aa0b7bbc5c718bf034f +size 3808389984 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a4cb39a --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2057a4d8a27d7247e1e6040bbe624be9dabb813ecb221020906aa345157fd51 +size 3492367200 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..5c32d85 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7d70abcc2389c397afb0205f962a0c8e4649e7a0f20b423f0e9b05d1f17338 +size 4444119904 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..32537dc --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c2f1a5b9a9522e415cd02fce22d549de48d04a13fe88f29c92b3c15ed594ee +size 4431389536 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..d4e70c0 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657e2e90bfb1d495d40ccaa64d3ed9fb4fa6dd2559b92c53f1f85cd6d2ec51a3 +size 4431389536 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..9fbb8cb --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ba1ed2a9f2f4ee42ddc4d265823feea74c3e8a0e7d2810b0097383598babc5 +size 4431389536 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c0dad1b --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f398ee9aa6127d134965250299bd5161bc698131bd2a86b51e9a89e1adc79217 +size 4683072352 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e958115 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e21ec776bd2186e1abf990164ce3f280c9b4f0dcc2b2b2bd30f5b708d80f1c +size 4457767776 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6f5de53 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b67bb0ef6ce5551ebab03b9b4c3666751eafabc039e95379f58cd7afd8fbae +size 5444830048 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..883b926 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40583076642d9b34255d7a80a6e7c45e7a00b044205e7cb16607301b6d92a72 +size 5315175264 diff --git a/Humanish-Qwen2.5-7B-Instruct.i1-Q6_K.gguf b/Humanish-Qwen2.5-7B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..59a2f79 --- /dev/null +++ b/Humanish-Qwen2.5-7B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a126bf5b4ee65a9c1abec3ec527534f1a14f07aed9f86c0874253d0c637548 +size 6254197600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..58b7d76 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct +datasets: +- HumanLLMs/Human-Like-DPO-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- axolotl +- dpo +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/HumanLLMs/Human-Like-Qwen2.5-7B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-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/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-Qwen2.5-7B-Instruct-i1-GGUF/resolve/main/Humanish-Qwen2.5-7B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..cc3eb6e --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9e6842bfd27c24db7790ae8600af50b6e868374552ed9ad55e754cd9371321 +size 4536665