commit 44d1d79efdb7e447d326b085b25f32cabef4049c Author: ModelHub XC Date: Sun Apr 26 02:46:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: backyardai/Replete-Coder-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c8da0f --- /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 +Replete-Coder-Llama3-8B.F32.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Replete-Coder-Llama3-8B.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/BackyardAI_Banner.png b/BackyardAI_Banner.png new file mode 100644 index 0000000..89f419a Binary files /dev/null and b/BackyardAI_Banner.png differ diff --git a/BackyardAI_Logo.png b/BackyardAI_Logo.png new file mode 100644 index 0000000..baa6243 Binary files /dev/null and b/BackyardAI_Logo.png differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..5623df3 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +license: other +tags: +- text-generation-inference +- transformers +- unsloth +- llama +base_model: Replete-AI/Replete-Coder-Llama3-8B +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 +model_name: Replete-Coder-Llama3-8B-GGUF +license_name: llama-3 +license_link: https://llama.meta.com/llama3/license/ +quantized_by: brooketh +parameter_count: 8030261248 +--- +Backyard.ai + +**

The official library of GGUF format models for use in the local AI chat app, Backyard AI.

** + +

Download Backyard AI here to get started.

+ +

Request Additional models at r/LLM_Quants.

+ +*** +# Replete Coder Llama3 8B +- **Creator:** [Replete-AI](https://huggingface.co/Replete-AI/) +- **Original:** [Replete Coder Llama3 8B](https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B) +- **Date Created:** 2024-06-24 +- **Trained Context:** 8192 tokens +- **Description:** Replete-Coder-llama3-8b is a general purpose model that is specially trained in coding in over 100 coding languages. The data used to train the model contains 25% non-code instruction data and 75% coding instruction data totaling up to 3.9 million lines, roughly 1 billion tokens, or 7.27gb of instruct data. The data used to train this model was 100% uncensored, then fully deduplicated, before training happened. +*** +## What is a GGUF? +GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware. +GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight. + +*** +Backyard.ai + +## Backyard AI +- Free, local AI chat application. +- One-click installation on Mac and PC. +- Automatically use GPU for maximum speed. +- Built-in model manager. +- High-quality character hub. +- Zero-config desktop-to-mobile tethering. +Backyard AI makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Backyard AI supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable. +**Join us on [Discord](https://discord.gg/SyNN2vC9tQ)** +*** \ No newline at end of file diff --git a/Replete-Coder-Llama3-8B.F32.gguf b/Replete-Coder-Llama3-8B.F32.gguf new file mode 100644 index 0000000..b50bbd3 --- /dev/null +++ b/Replete-Coder-Llama3-8B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2597c0bcf6ddd6a37f6ee7ac387cb77bd7aa784cf2e59a535ae1ce364ee5b414 +size 32128880544 diff --git a/Replete-Coder-Llama3-8B.IQ1_M.gguf b/Replete-Coder-Llama3-8B.IQ1_M.gguf new file mode 100644 index 0000000..8b7f380 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83835f84a212372d183d8724f5a79d171407b8b526c01d7a358512458ddf94e8 +size 2161971328 diff --git a/Replete-Coder-Llama3-8B.IQ1_S.gguf b/Replete-Coder-Llama3-8B.IQ1_S.gguf new file mode 100644 index 0000000..31641c0 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a07db7e42090d4b9e55658ac347bfcb4807800cfca3d4ca081329192ffc3f59 +size 2019627136 diff --git a/Replete-Coder-Llama3-8B.IQ2_M.gguf b/Replete-Coder-Llama3-8B.IQ2_M.gguf new file mode 100644 index 0000000..e80e910 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15503173fe91025ce695e17abd5f69ef712f74152e9c1d23895a2c54f24e4bba +size 2948280448 diff --git a/Replete-Coder-Llama3-8B.IQ2_S.gguf b/Replete-Coder-Llama3-8B.IQ2_S.gguf new file mode 100644 index 0000000..63bb729 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3171161ae54c4bcb9975aef356a18614b12720f8783b0dc6cd9113259f884ec7 +size 2758488192 diff --git a/Replete-Coder-Llama3-8B.IQ2_XS.gguf b/Replete-Coder-Llama3-8B.IQ2_XS.gguf new file mode 100644 index 0000000..e0235b6 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b90775f69dfaa81d7367fb2c57ac066331855556ee70ca6915510f8d6440a54 +size 2605781120 diff --git a/Replete-Coder-Llama3-8B.IQ2_XXS.gguf b/Replete-Coder-Llama3-8B.IQ2_XXS.gguf new file mode 100644 index 0000000..649b2bd --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb3943431ae5570459c75b7e62a4204d56c99d444d16f925b6518ce9d8c9831 +size 2399211648 diff --git a/Replete-Coder-Llama3-8B.IQ3_M.gguf b/Replete-Coder-Llama3-8B.IQ3_M.gguf new file mode 100644 index 0000000..41518f0 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed1df7591e074ebe1c8931a7894cf2dddfa804fb268c5ca774fad714922f941 +size 3784822912 diff --git a/Replete-Coder-Llama3-8B.IQ3_S.gguf b/Replete-Coder-Llama3-8B.IQ3_S.gguf new file mode 100644 index 0000000..628ee1c --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4671e543b05c04c019db0a7a98184c1d5b4cebf5964c91e7268ea52f985b18e1 +size 3682324608 diff --git a/Replete-Coder-Llama3-8B.IQ3_XS.gguf b/Replete-Coder-Llama3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..9a1b3ad --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010095e8402144960b5397f56dd910438e109ff251c773b26924d39d0d583ded +size 3518746752 diff --git a/Replete-Coder-Llama3-8B.IQ3_XXS.gguf b/Replete-Coder-Llama3-8B.IQ3_XXS.gguf new file mode 100644 index 0000000..ae51084 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2455c0fd7f484aaa6217f1e3344ef095d1e273d78c61247659934e8897bdb5 +size 3274911872 diff --git a/Replete-Coder-Llama3-8B.IQ4_XS.gguf b/Replete-Coder-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..6dd0126 --- /dev/null +++ b/Replete-Coder-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4035a37ef23c90a6631220cc0ffd0e8b9a4fc237714c03f1029856fdc8a3cde +size 4447662208 diff --git a/Replete-Coder-Llama3-8B.Q3_K_L.gguf b/Replete-Coder-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..087bc46 --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf95091c829fae1332dc246768cb462289a372635d49e8250de61d6faf96c1c +size 4321955744 diff --git a/Replete-Coder-Llama3-8B.Q3_K_M.gguf b/Replete-Coder-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..a607caa --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f7a670f63a306151f97d52b8664d81b99472b355ca01f4efd83d06614e0078 +size 4018917280 diff --git a/Replete-Coder-Llama3-8B.Q3_K_S.gguf b/Replete-Coder-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..a6fe5cf --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389e161ee19fd967b69ac88e9611fd38682ef50a448d8c62cbff378ac9a8dedf +size 3664498592 diff --git a/Replete-Coder-Llama3-8B.Q4_K_M.gguf b/Replete-Coder-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..cac147d --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169f217b00a55e890ce9870f94db15d112b2dab95c85f6d5689ed44ee2da878c +size 4920733600 diff --git a/Replete-Coder-Llama3-8B.Q4_K_S.gguf b/Replete-Coder-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..4890ac2 --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee447dfe3f821f80c839a37b0aaf923c06afc47e28c69c0f4b59fb2e8dfc5c33 +size 4692668320 diff --git a/Replete-Coder-Llama3-8B.Q5_K_M.gguf b/Replete-Coder-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..89f9f7c --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86bd00a543ea6deadb36380f784865f84c996fe6cde213dc3c3a0d205e32fc45 +size 5732986784 diff --git a/Replete-Coder-Llama3-8B.Q5_K_S.gguf b/Replete-Coder-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..d36033b --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ba5278310160983b779f50ba9a22598b4280f3d2d76da2dade3097b01705ec +size 5599293344 diff --git a/Replete-Coder-Llama3-8B.Q6_K.gguf b/Replete-Coder-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..3a3d788 --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5598c8c03835cdc528e5bf151747980a739cd2cd1408671000efc324e40b395e +size 6596005792 diff --git a/Replete-Coder-Llama3-8B.Q8_0.gguf b/Replete-Coder-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..17973bc --- /dev/null +++ b/Replete-Coder-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf7ff0f96e58400d1c7793c0a3a2a60e8d5338e383004c518e46db1e93f9b51 +size 8540770208 diff --git a/Replete-Coder-Llama3-8B.imatrix b/Replete-Coder-Llama3-8B.imatrix new file mode 100644 index 0000000..77f3619 --- /dev/null +++ b/Replete-Coder-Llama3-8B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edaee6ac8f13bb0bbf11e01c31301fc7b1b733d64d25ab480a215edc49c92c26 +size 4988153