commit 867b1b02e22734ef73648a929c7d7be6626a781c Author: ModelHub XC Date: Sun Apr 12 21:17:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..328ff57 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Llama3-8B-Instruct-Replete-Adapted.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-Instruct-Replete-Adapted.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-Instruct-Replete-Adapted.IQ3_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.IQ3_M.gguf new file mode 100644 index 0000000..63a7b41 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912bc0c05fab1f33110d754c4886b59900ac2cbfb3336b66bf0f5d1209a6c3a4 +size 3784823616 diff --git a/Llama3-8B-Instruct-Replete-Adapted.IQ3_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.IQ3_S.gguf new file mode 100644 index 0000000..a2d7a6d --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d350e301ab5bf218113a8c80413f022020aa814ffa0c45cc2aaf625e32a66d00 +size 3682325312 diff --git a/Llama3-8B-Instruct-Replete-Adapted.IQ3_XS.gguf b/Llama3-8B-Instruct-Replete-Adapted.IQ3_XS.gguf new file mode 100644 index 0000000..8e578fd --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f9f50e4c76a2acdf56f67eee95abceef0ba53a11a2e50ad2f10e707a86b95d +size 3518747456 diff --git a/Llama3-8B-Instruct-Replete-Adapted.IQ4_XS.gguf b/Llama3-8B-Instruct-Replete-Adapted.IQ4_XS.gguf new file mode 100644 index 0000000..4994ece --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936a21e546f70754e43ecc7d8e20cd148b2f3427ad17035a1feb5f2035c5246a +size 4484363072 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q2_K.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q2_K.gguf new file mode 100644 index 0000000..dd02875 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750c890f30b1fca3462880b018e2784f509f128b56ae4521448eff2a7d252e98 +size 3179131712 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q3_K_L.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_L.gguf new file mode 100644 index 0000000..ac9d65a --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:667680ab4113adbdc4283548c56761d1fe696da50234789d7ee8ef1e6ff77cc8 +size 4321956672 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q3_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_M.gguf new file mode 100644 index 0000000..909eab4 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56768bd9731c8822931cf6ab9658d2be59bbdf9466cc2ec474b31fe15facab2 +size 4018918208 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q3_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_S.gguf new file mode 100644 index 0000000..dc7cf12 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134d91d5f09532a13225e493698ab9841fe7b2d1d61297e2d01143d021656f52 +size 3664499520 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q4_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q4_K_M.gguf new file mode 100644 index 0000000..73f520a --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3d298181cf2cf2204ff52c66096bf97b6b300839a1096392d5aae156eb1d8f +size 4920734528 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q4_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q4_K_S.gguf new file mode 100644 index 0000000..60ff3d9 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:368c129442c3f22a9e0a912917c420c7d96c2f62474e6a3a1fee30e43497b0b3 +size 4692669248 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q5_K_M.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q5_K_M.gguf new file mode 100644 index 0000000..12a12f8 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d602f154e0d68c0011c4b5db79f8d00a7661fce06cf189a9c9198054191dbe53 +size 5732987712 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q5_K_S.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q5_K_S.gguf new file mode 100644 index 0000000..f5878b6 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da50064545dd1d27a705179a267e81b010d20b56b9c13411771b807ce01d7c9 +size 5599294272 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q6_K.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q6_K.gguf new file mode 100644 index 0000000..35ab8b8 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2a1c3b7b6f00824d9469c97b7052c81c6b1854f23279bb970c57cbe5976d9b +size 6596006720 diff --git a/Llama3-8B-Instruct-Replete-Adapted.Q8_0.gguf b/Llama3-8B-Instruct-Replete-Adapted.Q8_0.gguf new file mode 100644 index 0000000..1ad3b44 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdd4fbf054c20e34ae448cf8cc09aea6211c329cd74aa99474ac96ed19f3930 +size 8540771136 diff --git a/Llama3-8B-Instruct-Replete-Adapted.f16.gguf b/Llama3-8B-Instruct-Replete-Adapted.f16.gguf new file mode 100644 index 0000000..92e47e2 --- /dev/null +++ b/Llama3-8B-Instruct-Replete-Adapted.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d298072b54a393e56edaf4c99a2513abf250f76b3d599ce23fd988ddd16b2e25 +size 16068891456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6a5102f --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +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 + + + + + + +static quants of https://huggingface.co/Replete-AI/Llama3-8B-Instruct-Replete-Adapted + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-i1-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-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-Instruct-Replete-Adapted-GGUF/resolve/main/Llama3-8B-Instruct-Replete-Adapted.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +