commit 5905f63751136f143d5b2794c6c299dc9300a9fa Author: ModelHub XC Date: Sun Jun 28 08:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..091229c --- /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 +Codellama-3-8B-Finetuned-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..5ea8108 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f17c4725ae47217a5f3c0a34328c1190d4c5e7ca37624cc67ec9f02f73308b +size 2161973024 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..eb358ee --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb992a28c896a4b88a38576900ec7db61f422fae5b8e4f27027b14fdf02f4561 +size 2019628832 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..9c844c3 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac748ea20b357d6a15d871e9445e4aaf2908bd7cb9ca339c4cb4b10852029115 +size 2948282144 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..173d50a --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cbdc6e3af7dc8020972f59a5a7acb81e669611affea09d4c28bfe1021b30ab6 +size 2758489888 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XS.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ef96ffc --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13fd89a860a1efd39d04a82906c901dc2db30ba70d7e2a77ed4cdfdc8aa6ea7 +size 2605782816 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XXS.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..dc6428d --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a845cde8bdc92bebc7ee5b8f843aa8328fedf00bb3c874482129d5e8e4367d5 +size 2399213344 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..e3dc468 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:192ac4eb2d7a9522c9070167f970b72347d4666c02f5d7186833e5901e2e77e3 +size 3784824608 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..cbcb918 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff6f45784f391866ddbefce934cfafeca5997121665660c68a53a82c72cf007 +size 3682326304 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XS.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..578c287 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb3f8d7e3c14f2e18790d4f762d24dba9310929993f0cd90892fcfe49317f4bd +size 3518748448 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XXS.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3705d3e --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f46ed137d6119ff48258573a2b52bf754d85f577ce601e0032ef8a149d48401 +size 3274913568 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-IQ4_XS.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ce20635 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c07718184652f2718e1151cc40fc14032afded973a084cbe325bb60d2f106a9 +size 4447663904 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q2_K.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..eb6713d --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dfd2afa31a774597866dd13b4b182573a82b838341fde3b4877bb663d58627c +size 3179132704 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_L.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8ffd9e6 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e942043a2f58aba9d35e5f9d8599d0f60a0628b47e0931c84b9e2e992e8a6d9b +size 4321957664 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1aedf24 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103864ac51b68903729782a211e293a668fd429af190332a1a1b5739ee45b428 +size 4018919200 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d1fcd88 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb4d2ad069d8a6e2d77cd1e54a844b977f060248b7612e62688881bbd3d88c8 +size 3664500512 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..3edf591 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1486bc5f74a6888522c6a1b4fed647569da81db521757fd7d4b38fb858a140 +size 4675893024 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_4.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..177a919 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d3702ec89fa54d287f4150e73439b515cc38ebaaa1619426dc800de05b0f75d +size 4661212960 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_8.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..d14d629 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce0f74179c4bcaacfe4ab268cdd843550340c348021f33371c2be2347006158 +size 4661212960 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_8_8.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..b19b75f --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45aba455237c382cfbbda3887616d32b6afa4658c07cef65085d1f379badac20 +size 4661212960 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8aa557a --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a016c2f090c74affa6c7bc8df5f56a45cce8b552b6a6784caf761dd99b55cdf +size 4920735520 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..01dd5d2 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2125aa44d88f0422345be4475ec8e0880755eb673f5d93805dfec0994eeb5c7e +size 4692670240 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2adf391 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487fddc1470270dcb8b4dd830350df720dd065f665f564039ddb885d29c6d72f +size 5732988704 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d5221ef --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b71a531e9ab6379d92250fd851d479f0de31854219c831c65748918dd0b0a8 +size 5599295264 diff --git a/Codellama-3-8B-Finetuned-Instruct.i1-Q6_K.gguf b/Codellama-3-8B-Finetuned-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..4d9bfe5 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da24bdd0066d8d3dd4a5b526314088c8bfcb1058e32eb80403273efe8828074 +size 6596007712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe039ba --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: rombodawg/Llama-3-8B-Instruct-Coder +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Codellama-3-8B-Finetuned-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-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/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.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. 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..64b3da5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e22b51ddb4dc983aeaf7ed7fe60f0b1abb5edc78275ff3d466dcb716c5c777 +size 4988157