commit 70da07529367bd169ca00204610ecafe31e18270 Author: ModelHub XC Date: Thu Jun 4 02:08:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c9bf7f5 --- /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-v0.3.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q2_K.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q2_K.gguf new file mode 100644 index 0000000..3aba2af --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e6309aaedd49a9c558b32582399c59c48c2ae214cb96e51ee8027c80295adb +size 3179131424 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_L.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_L.gguf new file mode 100644 index 0000000..559cb3a --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afea624c2c26af1a23ef2f2c929cd96a47d62365e90115c5fc566518f7c891d +size 4321956384 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_M.gguf new file mode 100644 index 0000000..3a6acd4 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f5cf6a9736ed9a898deb0f85fe13e0b05859720ef013404d021abb698dd24c +size 4018917920 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_S.gguf new file mode 100644 index 0000000..e9c1193 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586e202e19605ce77c8226a8e9d215114618909c393765fdeef6a574f5dfb480 +size 3664499232 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_0.gguf new file mode 100644 index 0000000..cac90c0 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b30f5d0bffd815e5537aa9945d2945b7493aa0d5b0b46bad0c8cc035b3c017 +size 4661211680 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_1.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_1.gguf new file mode 100644 index 0000000..00ffd9f --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5e78ed61f809b48bfed625be980ec2e5232ff6719acb131afbad7582cc85d8 +size 5130252832 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_M.gguf new file mode 100644 index 0000000..cc42d61 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcae097fc243854ab563f5ec4e32ac6113593de3e07e4769087639c305fe8293 +size 4920734240 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_S.gguf new file mode 100644 index 0000000..ba0a474 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5989eb5b6374c55a65c0d713fe50bd3b1468e302c514b0f83334418a8ac12b8b +size 4692668960 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_0.gguf new file mode 100644 index 0000000..561fb3f --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8953f88db3d34881e40371d202e28f282050b35c44012da93c4820e5a80243de +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_1.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_1.gguf new file mode 100644 index 0000000..575c775 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8555e38f441668fb8ce7c9bfeb29d53ec784d33cc1c89f80725e5a49ccabcddb +size 6068335136 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_M.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_M.gguf new file mode 100644 index 0000000..6361b42 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8d4e3a0be64ce52f2bd5fd9a42f1b7463cc02ae0c48bfcb972cec56fdf5412 +size 5732987424 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_S.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_S.gguf new file mode 100644 index 0000000..27667d1 --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4845b626311c9f8d658f48d89b63eb1d5a1f9b7355cf009abb5aa0f131a6294 +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q6_K.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q6_K.gguf new file mode 100644 index 0000000..7b4c28f --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788755a2d59e8b10ed10810c03d2d4503160cadad22c237965fe39a3f69e06d6 +size 6596006432 diff --git a/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q8_0.gguf b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q8_0.gguf new file mode 100644 index 0000000..b054fcd --- /dev/null +++ b/ArliAI-Llama-3-8B-Cumulus-v0.3.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01086fa928fbf9e2b1315c0f71a177170b2e613b41214d410828c73af6e28f88 +size 8540770848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..12d4691 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +license: llama3 +pipeline_tag: text-generation +base_model: OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF +--- + +# OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF +This is quantized version of [OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF](https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF) created using 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 v0.3.2 version is even more uncensored thanks to using https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated as the base model. The 0.0.2 is for slight adjustment to the DPO stage. + + +In terms of reasoning and intelligence, this model is probably a bit worse than the OG model because of the decensoring. However, this model is better at long back and forth chats and will refuse less. + + +This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character. + + +Training: +- Full 8192 sequence length. +- Training duration is around 2 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 64-alpha resulting in ~2% trainable weights. + + +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|> +``` + + +Quants: + +FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2 + +GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3.2-GGUF \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{} \ No newline at end of file