初始化项目，由ModelHub XC社区提供模型

Model: EpistemeAI/Dolphin-Llama-3.1-8B-orpo-v0.1-4bit-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
+language:
+- en
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+- dpo
+license: llama3.1
+datasets:
+- reciperesearch/dolphin-sft-v0.1-preference
+pipeline_tag: text-generation
+license_name: llama3
+license_link: LICENSE
+model_creator: EpistemeAI
+quantized_by: EpistemeAI
+---
+
+**gguf**:
+- q4_k_m
+- 16-bit
+
+
+This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license.
+
+Fine-tune using ORPO
+
+## Training Details
+
+### Training Data
+
+- dataset: reciperesearch/dolphin-sft-v0.1-preference
+
+### Training Procedure
+ORPO techniques
+
+
+#### Training Hyperparameters
+
+- **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+
+
+TrainOutput(global_step=30, training_loss=4.25380277633667, metrics={'train_runtime': 679.3467, 'train_samples_per_second': 0.353, 'train_steps_per_second': 0.044, 'total_flos': 0.0, 'train_loss': 4.25380277633667, 'epoch': 0.015})

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "llama"
+}

unsloth.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca5db04e79fdf76411b00716dfd878ba81a5cb21565ca9b9de20a8a9556c3ff
+size 16068895712

unsloth.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4683f383ac0a4e58d6d8ddc47ba8ebd11edf203366c44059b7c53fbaa80689cc
+size 4920738784