initial upload

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb248996a9dae77a91ea3f766b7a6460841e8532db6d9614d7134b024319cf5
+size 1195470168

dpo.yml

@@ -0,0 +1,88 @@
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+rl: true
+datasets:
+  - path: Intel/orca_dpo_pairs
+    split: train
+    type: intel_apply_chatml
+  - path: allenai/ultrafeedback_binarized_cleaned
+    split: train_prefs
+    type: ultra_apply_chatml
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+output_dir: ./dpopenhermes-rc5/
+save_total_limit: 3
+hub_model_id: openaccess-ai-collective/dpopenhermes-rc5
+
+adapter: lora
+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_modules_to_save:
+  - embed_tokens
+  - lm_head
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project: openhermes-dpo
+wandb_entity: oaaic
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 4
+num_epochs: 1
+optimizer: paged_adamw_8bit
+adam_beta2: 0.95
+adam_epsilion: 0.00001
+lr_scheduler: cosine
+learning_rate: 2e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+eval_steps:
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps: 239
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+save_safetensors: true