初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/Lama-DPOlphin-8B-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
+Lama-DPOlphin-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Lama-DPOlphin-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

Lama-DPOlphin-8B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db677b666188434e70f1dc593588488d0de50ff647e07d10d89de022cb68da1b
+size 3179141600

Lama-DPOlphin-8B.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00aa575234a8ab4fdf1f8367dab11350cb522e1d603c908d857b7bfd6774f1d
+size 4321967392

Lama-DPOlphin-8B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c709c35bc4ec166eb9b6fe74ed138b0d0848d009d0ce99e29f14cdc7e3b3ce8b
+size 4018928928

Lama-DPOlphin-8B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3235890167bc4c852d347052a9569dc8ebdaaff3003010fb2d7f80954c2b4e7d
+size 3664510240

Lama-DPOlphin-8B.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333830fcd7435b2ed090a600c66a925bf3d45993b74deeecde7d9587cd379285
+size 4661223776

Lama-DPOlphin-8B.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03ee3b2eb0050db96c3079a6b7306fd8b73984c4783935db9691349a73f2832
+size 5130265440

Lama-DPOlphin-8B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5720b9f664c2a39db55b59f41a1e62f570bb08b3059fb5556f4851e67dab3a46
+size 4920746336

Lama-DPOlphin-8B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7fc755afb08de622008ba58aea0a3ef3d9c450cfc74fb89c284daedac4f4e91
+size 4692681056

Lama-DPOlphin-8B.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a57e1af695e8722edc52e34b7e125741308f0936d2289942a9ecc2dfc466422
+size 5599307104

Lama-DPOlphin-8B.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820f61d6714174193dec0079b486030b1b4c1de618758d352b6c71ebd7900409
+size 6068348768

Lama-DPOlphin-8B.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d72b78848956cfaaa45b9016abb76849e11e97207929e5c72e95906ed2ab23d
+size 5733000544

Lama-DPOlphin-8B.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84b8c0f550cb62856091aa0bbc0a834973d20f8ab012322a803191db2356aaf
+size 5599307104

Lama-DPOlphin-8B.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53c477e24076797f094ea475fd37d6dc2fcef321e9fc8740098b48083c08d94
+size 6596020640

Lama-DPOlphin-8B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd69d0fb0e689e008aad61c7ee0e5aa3976de7c2cbc5b689e1b5f29cb67f0017
+size 8540789024

README.md

@@ -0,0 +1,106 @@
+
+---
+
+license: apache-2.0
+datasets:
+- mlabonne/orpo-dpo-mix-40k-flat
+language:
+- en
+base_model: cognitivecomputations/dolphin-2.9.4-llama3.1-8b
+pipeline_tag: text-generation
+tags:
+- dpo
+- axolotl
+library_name: transformers
+
+---
+
+![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
+
+# QuantFactory/Lama-DPOlphin-8B-GGUF
+This is quantized version of [CultriX/Lama-DPOlphin-8B](https://huggingface.co/CultriX/Lama-DPOlphin-8B) created using llama.cpp
+
+# Original Model Card
+
+
+## Axolotl configuration:
+```yaml
+
+base_model: cognitivecomputations/dolphin-2.9.4-llama3.1-8b
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+tokenizer:
+  name_or_path: "https://huggingface.co/cognitivecomputations/dolphin-2.9.4-llama3.1-8b/resolve/main/tokenizer.json"
+
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+save_safetensors: true
+bnb_4bit_quant_type: "nf4"
+bnb_4bit_compute_dtype: "bf16"
+bnb_4bit_use_double_quant: true
+
+rl: dpo
+chat_template: chatml
+datasets:
+  - path: mlabonne/orpo-dpo-mix-40k-flat
+    split: train
+    type: chatml.intel
+
+dataset_prepared_path: /workspace/axolotl/dataset-prepared
+val_set_size: 0.0
+output_dir: ./out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: false
+
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+
+wandb_project: axolotl
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+
+gradient_accumulation_steps: 4  # Reduced from 8 to 4 due to large VRAM
+micro_batch_size: 2  # Increased micro-batch size to 2
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 5e-6
+train_on_inputs: false
+group_by_length: false
+
+bf16: true  # Use bf16 as it is optimal for A40 GPUs
+fp16: false
+tf32: true  # TF32 is supported by A40 and improves performance
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+warmup_steps: 100
+evals_per_epoch: 0
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed: deepspeed_configs/zero2.json  # Enable DeepSpeed with ZeRO Stage 2
+weight_decay: 0.0
+special_tokens:
+  pad_token: <|end_of_text|>
+```

configuration.json

@@ -0,0 +1 @@
+{}