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

.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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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|>
+```

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}