commit 40f042a7b26b088bfea538e1e9e25b5bac32d17c Author: ModelHub XC Date: Sun Apr 12 21:34:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InstructLM-500M-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3bfffc3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +InstructLM-500M.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InstructLM-500M.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InstructLM-500M.i1-IQ1_M.gguf b/InstructLM-500M.i1-IQ1_M.gguf new file mode 100644 index 0000000..2d35880 --- /dev/null +++ b/InstructLM-500M.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca4f5f829569c455973f5454dcb627a4bf5c9f8fb2ba7098152b88eb1ff9378 +size 195652640 diff --git a/InstructLM-500M.i1-IQ1_S.gguf b/InstructLM-500M.i1-IQ1_S.gguf new file mode 100644 index 0000000..77a710b --- /dev/null +++ b/InstructLM-500M.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2097df317084f566d81e1bac5476dc54c91c058a47cacde9ea17218a7c0d2dd +size 188906528 diff --git a/InstructLM-500M.i1-IQ2_M.gguf b/InstructLM-500M.i1-IQ2_M.gguf new file mode 100644 index 0000000..383637c --- /dev/null +++ b/InstructLM-500M.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834425f71d24c7dff0b43a97924fa38d45a934814235b2f3c79af8a38695d393 +size 240199712 diff --git a/InstructLM-500M.i1-IQ2_S.gguf b/InstructLM-500M.i1-IQ2_S.gguf new file mode 100644 index 0000000..6063771 --- /dev/null +++ b/InstructLM-500M.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5347cef9f584d0efc8a5aa04bd66f650cba6bec94bb221e4472199ce484c0f1 +size 231204896 diff --git a/InstructLM-500M.i1-IQ2_XS.gguf b/InstructLM-500M.i1-IQ2_XS.gguf new file mode 100644 index 0000000..53b46f7 --- /dev/null +++ b/InstructLM-500M.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6447c25581209b45d261cc97803c558bf6edce8cae37d0f3dd2f5dcf92fbe26f +size 217070624 diff --git a/InstructLM-500M.i1-IQ2_XXS.gguf b/InstructLM-500M.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e006169 --- /dev/null +++ b/InstructLM-500M.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0497ac1b530af60489e00df5c93b60e45e31a3c6579143fb549c1aaec183aa +size 206896160 diff --git a/InstructLM-500M.i1-IQ3_M.gguf b/InstructLM-500M.i1-IQ3_M.gguf new file mode 100644 index 0000000..dc5bf7e --- /dev/null +++ b/InstructLM-500M.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d1b577bf24ed055ea61ed46bd2fa84c765d6ef6359e655942deb2e3022fd47 +size 289895456 diff --git a/InstructLM-500M.i1-IQ3_S.gguf b/InstructLM-500M.i1-IQ3_S.gguf new file mode 100644 index 0000000..cfa3486 --- /dev/null +++ b/InstructLM-500M.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6be900cc3485f70a44c7e4218a01c48c33ee9c699b299ef66eea30da3e2881 +size 278209568 diff --git a/InstructLM-500M.i1-IQ3_XS.gguf b/InstructLM-500M.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1dddcab --- /dev/null +++ b/InstructLM-500M.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41167ac0dd7df2de4a0d3ff692a45b03ee396a0321c86a5bb8863900abc8c733 +size 267205664 diff --git a/InstructLM-500M.i1-IQ3_XXS.gguf b/InstructLM-500M.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4e5a7ca --- /dev/null +++ b/InstructLM-500M.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee2adfc3fc238dd24e0942ba0dfb9a331b2ddbc20a1d7c6381a76f9b35d8572 +size 251701280 diff --git a/InstructLM-500M.i1-IQ4_NL.gguf b/InstructLM-500M.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3e34457 --- /dev/null +++ b/InstructLM-500M.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109e742af29b4adc5d9839af51bda249a4b78d4c7f5fe17b580ab4c2a70c1acf +size 332992544 diff --git a/InstructLM-500M.i1-IQ4_XS.gguf b/InstructLM-500M.i1-IQ4_XS.gguf new file mode 100644 index 0000000..73a7666 --- /dev/null +++ b/InstructLM-500M.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c18797db2a10da78d6ece5f0a4362e0c287d54cd4f746bd87ae2db56b1b233 +size 320102432 diff --git a/InstructLM-500M.i1-Q2_K.gguf b/InstructLM-500M.i1-Q2_K.gguf new file mode 100644 index 0000000..31012b8 --- /dev/null +++ b/InstructLM-500M.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f562f7772251acbc3d0328e8ebb6156df856e04170af560e463b47820abdad3e +size 243984416 diff --git a/InstructLM-500M.i1-Q2_K_S.gguf b/InstructLM-500M.i1-Q2_K_S.gguf new file mode 100644 index 0000000..37e5936 --- /dev/null +++ b/InstructLM-500M.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dcca4c45e75a8372123e56a53bb39890490346c82484e2b4ff1834b614a1462 +size 237975584 diff --git a/InstructLM-500M.i1-Q3_K_L.gguf b/InstructLM-500M.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c694938 --- /dev/null +++ b/InstructLM-500M.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628e778835a584f1475f5c0fa7833a4dfd47c7670456112120dbfc66e4463660 +size 317580320 diff --git a/InstructLM-500M.i1-Q3_K_M.gguf b/InstructLM-500M.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0fc17cc --- /dev/null +++ b/InstructLM-500M.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3ec1a6ae65dee441b3dc7dcf6a15da881ac934f5ed5a2ec264e3aaaf2b1821 +size 302512160 diff --git a/InstructLM-500M.i1-Q3_K_S.gguf b/InstructLM-500M.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4b11588 --- /dev/null +++ b/InstructLM-500M.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692e38f9d8f79c5c8e5a2b9de1f3eb89dcf84792195d98bc05236fe5630af30c +size 278209568 diff --git a/InstructLM-500M.i1-Q4_0.gguf b/InstructLM-500M.i1-Q4_0.gguf new file mode 100644 index 0000000..3d9e315 --- /dev/null +++ b/InstructLM-500M.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a199d05ff725b36e3a2d0692dab65c31b5fa51b0e79af57d3e698109eb1984 +size 333821984 diff --git a/InstructLM-500M.i1-Q4_1.gguf b/InstructLM-500M.i1-Q4_1.gguf new file mode 100644 index 0000000..7bfa42b --- /dev/null +++ b/InstructLM-500M.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156dc460ac4bf03788bdebabc84a97332102f2293a20095a8836ac3d6bc10508 +size 365408288 diff --git a/InstructLM-500M.i1-Q4_K_M.gguf b/InstructLM-500M.i1-Q4_K_M.gguf new file mode 100644 index 0000000..09e9b34 --- /dev/null +++ b/InstructLM-500M.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b93c0cf382e3d641fee724b1ef426f2b820172ca96963b62769153127e857e +size 371036192 diff --git a/InstructLM-500M.i1-Q4_K_S.gguf b/InstructLM-500M.i1-Q4_K_S.gguf new file mode 100644 index 0000000..64a328b --- /dev/null +++ b/InstructLM-500M.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146954cd3d8c0b4abcab50dc8aa12737eb54ce67f097ed6694d5d3de73866583 +size 348272672 diff --git a/InstructLM-500M.i1-Q5_K_M.gguf b/InstructLM-500M.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a9e482f --- /dev/null +++ b/InstructLM-500M.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116fb1d44f12e54d926db739240613a9a4c5d6fa7de28974c08c824f24983cbb +size 423555104 diff --git a/InstructLM-500M.i1-Q5_K_S.gguf b/InstructLM-500M.i1-Q5_K_S.gguf new file mode 100644 index 0000000..bc3004b --- /dev/null +++ b/InstructLM-500M.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585766c329d9939cc39a38716af86321feb93261f3817bdf9f2097f2ddc83e67 +size 404459552 diff --git a/InstructLM-500M.i1-Q6_K.gguf b/InstructLM-500M.i1-Q6_K.gguf new file mode 100644 index 0000000..36b209d --- /dev/null +++ b/InstructLM-500M.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f44cadf7b33a1085079bc04487dd2827677cfaa8399436cacdfcf127cf72115 +size 492420128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2378b4 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: instruction-pretrain/InstructLM-500M +datasets: +- tiiuae/falcon-refinedweb +- instruction-pretrain/ft-instruction-synthesizer-collection +- instruction-pretrain/general-instruction-augmented-corpora +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/instruction-pretrain/InstructLM-500M + + +static quants are available at https://huggingface.co/mradermacher/InstructLM-500M-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/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ2_S.gguf) | i1-IQ2_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ2_M.gguf) | i1-IQ2_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q2_K.gguf) | i1-Q2_K | 0.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.4 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q4_0.gguf) | i1-Q4_0 | 0.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InstructLM-500M-i1-GGUF/resolve/main/InstructLM-500M.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..852a7d2 Binary files /dev/null and b/imatrix.dat differ