commit 679ae5cef9af757f69ade913c7dc120381eada34 Author: ModelHub XC Date: Wed May 20 05:53:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f286baa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +Llama-3-8B-Irene-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Irene-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ1_M.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..ced08e6 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76744b968d103009b9249069fb654f6e1a2c899b12d85bc670b2f2483e16e134 +size 2161972192 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ1_S.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..79b5308 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffff3e1facadb74c37726731af82786b70c769330f7594498e6df7b53160720e +size 2019628000 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ2_M.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..0d30f26 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814a630bd487bd234f3062b39cc7c5fb50e2fa974ee132f393171d7f4410dee4 +size 2948281312 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ2_S.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..cf0bc1a --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53090e5c465958620c000740cebe416343703f80b2e47472fa2de437f246706f +size 2758489056 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ2_XS.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..265b7d1 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62744e2ee0accc04c68937b00e2b901b784e2f33b8ebb718ad84aaa4397dfa17 +size 2605781984 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ2_XXS.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bd36cad --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493d78f2ace141e448bccae23304484e695f10352c51e8be2be9fe1add5fd93b +size 2399212512 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ3_M.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..9f803e2 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5623148a4bd7aa86e70757d83d1ef065a4e4780dcc5d2377c2590bd2359ade11 +size 3784823776 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ3_S.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..7086554 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c567b13d9ead8d472e4462b5d62c86ca0575a9bbf781649b623bbf84f54a80 +size 3682325472 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ3_XS.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..90a6a74 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de27c73e9f87c4a0f33754cc4f686525e13a0a01e94b2422e9e34aaa955bf074 +size 3518747616 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ3_XXS.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cb064cd --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a1e43a28662f008d315fd89f13f70a4bd0c910af6c2657bebc6c7084cfab21 +size 3274912736 diff --git a/Llama-3-8B-Irene-v0.1.i1-IQ4_XS.gguf b/Llama-3-8B-Irene-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5336cd5 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8635462bed3d334fa203f465e473ad1c0fd0429b9a1c1d5aeae9849a48984a77 +size 4447663072 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q2_K.gguf b/Llama-3-8B-Irene-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..192d5d5 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242d7f398c08eecca7129efde1e9ec2652b7d5f0ad8eef9e5a6e106f111aa0ef +size 3179131872 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q3_K_L.gguf b/Llama-3-8B-Irene-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ad9826e --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a0d6fc85ae2310d60e2f4537b5726afdfaf8f2048bf046f21adde92616f7b3 +size 4321956832 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q3_K_M.gguf b/Llama-3-8B-Irene-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3fcb5d7 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1635a953ae6101e3b462a64fe9bb815073fad1a5f64ef14422fde390f3c3af44 +size 4018918368 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q3_K_S.gguf b/Llama-3-8B-Irene-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ca43868 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d102d270d99bf9b7deebcbc1e3d72530324462a4ee4593c7dda5a601558af74e +size 3664499680 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q4_0.gguf b/Llama-3-8B-Irene-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..a1be4ec --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47657ea1490bccc8ae22bef62d44f907ce84ab326bab61bb486799126436ed0f +size 4675892192 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q4_K_M.gguf b/Llama-3-8B-Irene-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..514f154 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7327311dffcc66a330279960f74701fe6b11b6f2689fd3e867b6b5acfbea220 +size 4920734688 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q4_K_S.gguf b/Llama-3-8B-Irene-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f04374c --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a052ad99f1bf832377d437ff7d2f62f19b0857420e32fe31600dd55c1a8d924 +size 4692669408 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q5_K_M.gguf b/Llama-3-8B-Irene-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e8b6ef1 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a43e4d01b735be68e6376398df33bb0f0bfcf8eb8ebcf2c3fe4ddc0a73fb3a5 +size 5732987872 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q5_K_S.gguf b/Llama-3-8B-Irene-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d2d4c3d --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b07f3302f9833fc7038886204653f5f80b563adcc4a774283854d76582ec3ef +size 5599294432 diff --git a/Llama-3-8B-Irene-v0.1.i1-Q6_K.gguf b/Llama-3-8B-Irene-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..d7b48a3 --- /dev/null +++ b/Llama-3-8B-Irene-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebddd8b6d917b103d0d25082362861e6d7f05205546bbf6bdf94d5b3fe663bc2 +size 6596006880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..42c3e6d --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Virt-io/Llama-3-8B-Irene-v0.1 +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +- facebook +- meta +- pytorch +- llama +- llama-3 +--- +## About + + + + + +weighted/imatrix quants of https://huggingface.co/Virt-io/Llama-3-8B-Irene-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-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/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Irene-v0.1-i1-GGUF/resolve/main/Llama-3-8B-Irene-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ccfdb3a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb85cf049fd9acfede7acd51e2da94df8143423e84ec367d3c3d6961d01c0c2 +size 4988159