commit eef3e32734bd1742d79715f9537973e0b6df8585 Author: ModelHub XC Date: Mon Jun 22 09:35:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50ddf23 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q2_K.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q2_K.gguf new file mode 100644 index 0000000..fec442c --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022ddcb79fbaaeffdfaf1ee6d6414aa1a854e8ab2653dfb82b8ee23662922d5e +size 3179131424 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_L.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..5a34d4d --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86abf99f2c7a0ba002806e57c3335a558e977e334422f9f4a813cde413ff9e0c +size 4321956384 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..c30c439 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4232af484565f8588a0d8e22f977b827e160e438940d1ec6cb4e7337386465c +size 4018917920 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..94dde3e --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4865ac8a853ce5857c734e20c9ed725d2e6f2c64ac3622c781b4aea9b509e8b8 +size 3664499232 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_0.gguf new file mode 100644 index 0000000..d1baa01 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3637b40ec91cc335c44dd4b70e820dba7eb706475e89052f990b611df636da4e +size 4661211680 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_1.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_1.gguf new file mode 100644 index 0000000..5c3bf74 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f563ee5b0e5d91f8c1ba01a259751dfde5610073925f23b61fa6480ba03994cb +size 5130252832 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..1266241 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae98036f081a889e5de2d6c95f41d42868433f0a6212e8ac9b3dd5ef135f8e46 +size 4920734240 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..1e4ad21 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6249e04f58b25d135ed71536aa6baab74d8cc00d4613ecdfff77399b9ee971b4 +size 4692668960 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_0.gguf new file mode 100644 index 0000000..4adc4ab --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0ef21ce2e9fcd38412fc4269fd35ce0ebc0a3e36f0940390fa1061793a84be +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_1.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_1.gguf new file mode 100644 index 0000000..91f59e1 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580e0db1e50f1116ef9a249231d7cc011611d307b658753c939268fd3d97e4b1 +size 6068335136 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..e510a31 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:115ecd84d1885368f1def9b41ca7b4b62b16eb33035a8dcd0503e6d7089a7b7f +size 5732987424 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..17c53c5 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9332cedbfc3aa6ea385c9b72bcd961858b9267cd5ee14d0b6d3a45b74cfaf1 +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q6_K.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q6_K.gguf new file mode 100644 index 0000000..8968b4a --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26c835780f069f7a576dfda4bcc0087c593d5d4c262a1ae0dbff0d14620203b +size 6596006432 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.2.Q8_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q8_0.gguf new file mode 100644 index 0000000..dbf7da1 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade0434807de66ffce591fe1da006a73429df7d2537f502b5d922fcaf0a1f599 +size 8540770848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b9df21 --- /dev/null +++ b/README.md @@ -0,0 +1,44 @@ +--- +license: llama3 +pipeline_tag: text-generation +base_model: OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 +--- + +# QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.2-GGUF +This is quantized version of [OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2](https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2) created suing llama.cpp + +# Model Description +Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: +https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct + + +This is by far the most completely uncensored Llama 3 8b instruct model. It will literally never refuse anything. +So as a reminder, with great power comes great responsibility. + + +In terms of reasoning and intelligence, this model is probably worse than the OG model because of the decensoring. However, if you have issues with refusals then this will be superior just because it will not refuse. + + +OpenLLM Benchmark: + +![OpenLLM Leaderboard](https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Cumulus-v0.2/blob/main/Screenshot%202024-05-02%20201231.png "OpenLLM Leaderboard") + + +Training: +- 4096 sequence length, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine. +- Training duration is around 3 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights. +- Added DPO fine tuning aside from a more curated dataset for this v0.2 model. + + +Instruct format: +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file