commit 2d6bec8f7ef14d92925dd79c3b70137cb5e9eade Author: ModelHub XC Date: Sat Jun 6 17:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..637e705 --- /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 +Llama3-8B-Instruct-Replete-Adapted.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_M.gguf new file mode 100644 index 0000000..bf607d2 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddcd47f978d2bb8a9b6cb5162f76d1c1a96309baf5fefdb4c1f1891031f80d5d +size 2161972288 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_S.gguf new file mode 100644 index 0000000..c3bd412 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af746245006b374c08945800573031c307ffaf8d32936702c68e17e532d10b31 +size 2019628096 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_M.gguf new file mode 100644 index 0000000..3486e0f --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b1a9db51136a839fad3ba5f17de7dbbcd3c697d225bd5831fe2c4d97dd3752 +size 2948281408 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_S.gguf new file mode 100644 index 0000000..d3b8320 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1468016d6b8de67585570a329fade533c3f58f09f7c9c31b64246bcfbc14acb2 +size 2758489152 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XS.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ade4f08 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9327f7cd83d1c327fb4a0e0ff06aab0de4d685304a025ec944307e72bd6f91 +size 2605782080 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XXS.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..77b9edf --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d8df0eaade07858b73f9242d9f49913afecd235291408d6c7be6d30c1b31e3 +size 2399212608 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_M.gguf new file mode 100644 index 0000000..26059ad --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2607b9820f10f97120eea88a19f2b571a310b9d304fb4559b19d96794641d01 +size 3784823872 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_S.gguf new file mode 100644 index 0000000..f7e61ca --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5965d256d337ac4041aa1a785c77a308ef2ffb886a20d1ceefe7f4290b98e2 +size 3682325568 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XS.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e293190 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d5a85556af41c6ecbc25f0f3d4179a187078a9c1477d1d768e02cbb13c7d23 +size 3518747712 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XXS.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1ec18ab --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffee07c91182524220903d166fcf86da20b2f2448f6ea8d0d36a44bd9e2bccb7 +size 3274912832 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-IQ4_XS.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1bfd249 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32b3a6f36ca0da1db237b8352bc201609eaf465bda521ebc163ae9715d0531c +size 4447663168 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q2_K.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q2_K.gguf new file mode 100644 index 0000000..85bb54b --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96e9007a17f3ccbfec51795d0243f88008c402bf88b9e5a8b0130927d247fc0 +size 3179131968 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_L.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_L.gguf new file mode 100644 index 0000000..238eb3b --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b9d54085bb0162479a11a1e3703c4340fb68469f4008e7de1ce00fba2bc441 +size 4321956928 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0ee2a2e --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4957f85888e2699889982bf96f622b929fd65d712832cb6da297b1f7800a1d7c +size 4018918464 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b7d7493 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2179499d638c2c4632da170cd72534e735d838d65b2419fe203f9bebbb186106 +size 3664499776 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_0.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_0.gguf new file mode 100644 index 0000000..9855490 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf6d35f5d555cfa850a6d1acf61594782e742255180d96d315eeca0b16c9009 +size 4675892288 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b584044 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21bbcea1c1fa2d6dccb33c07ecabe6da5d613ae2020ab4e89e0a46e0efecdea2 +size 4920734784 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ae8f30f --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e915afaab116e21683eb2b580b54ae8722d9bdbf80006e31050c9503a64030a7 +size 4692669504 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2cdb1ce --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cece0571847af5e4faada68573bf03f6e367786b7406ede694518468920a5c4 +size 5732987968 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1c7d9eb --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f55e11625b9dc616184353dad01491af486eb9aabc6ffcf9192b0d5e8097e8 +size 5599294528 diff --git a/Llama3-8B-Instruct-Replete-Adapted.i1-Q6_K.gguf b/Llama3-8B-Instruct-Replete-Adapted.i1-Q6_K.gguf new file mode 100644 index 0000000..144d053 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ebc788f8e0a9082a94ff76746510024feecec2ea7196b5faffd3c04acffcc2 +size 6596006976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4cec588 --- /dev/null +++ b/README.md @@ -0,0 +1,112 @@ +--- +base_model: Replete-AI/Llama3-8B-Instruct-Replete-Adapted +datasets: +- Replete-AI/code_bagel_hermes-2.5 +- Replete-AI/code_bagel +- Replete-AI/OpenHermes-2.5-Uncensored +- teknium/OpenHermes-2.5 +- layoric/tiny-codes-alpaca +- glaiveai/glaive-code-assistant-v3 +- ajibawa-2023/Code-290k-ShareGPT +- TIGER-Lab/MathInstruct +- chargoddard/commitpack-ft-instruct-rated +- iamturun/code_instructions_120k_alpaca +- ise-uiuc/Magicoder-Evol-Instruct-110K +- cognitivecomputations/dolphin-coder +- nickrosh/Evol-Instruct-Code-80k-v1 +- coseal/CodeUltraFeedback_binarized +- glaiveai/glaive-function-calling-v2 +- CyberNative/Code_Vulnerability_Security_DPO +- jondurbin/airoboros-2.2 +- camel-ai +- lmsys/lmsys-chat-1m +- CollectiveCognition/chats-data-2023-09-22 +- CoT-Alpaca-GPT4 +- WizardLM/WizardLM_evol_instruct_70k +- WizardLM/WizardLM_evol_instruct_V2_196k +- teknium/GPT4-LLM-Cleaned +- GPTeacher +- OpenGPT +- meta-math/MetaMathQA +- Open-Orca/SlimOrca +- garage-bAInd/Open-Platypus +- anon8231489123/ShareGPT_Vicuna_unfiltered +- Unnatural-Instructions-GPT4 +language: +- en +library_name: transformers +license: other +license_link: https://llama.meta.com/llama3/license/ +license_name: llama-3 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Replete-AI/Llama3-8B-Instruct-Replete-Adapted + + +static quants are available at https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-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/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.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..ec0f9a2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a24c4ede039f25c78e5731616e65e667012c46bc425dd903e12dde2da1dccef +size 4988161