DPO-7b-beta0.01

README.md

@@ -2,10 +2,14 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - dpo
-- generated_from_trainer
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- updated
+- original
 model-index:
 - name: nash_dpo_rank4_on_vanilla_iter_1
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nash_dpo_rank4_on_vanilla_iter_1
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+This model is a fine-tuned version of [YYYYYYibo/vanilla_dpo_iter_3](https://huggingface.co/YYYYYYibo/vanilla_dpo_iter_3) on the updated and the original datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.6753
 - Rewards/chosen: -0.1174

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}