End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: google/gemma-7b
+datasets:
+- argilla/dpo-mix-7k
 library_name: transformers
-model_name: gemma-7b-slic-basic-5e-5-05-v5
+model_name: google/gemma-7b
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - orpo
 licence: license
 ---
 
-# Model Card for gemma-7b-slic-basic-5e-5-05-v5
+# Model Card for google/gemma-7b
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b).
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the [['argilla/dpo-mix-7k']](https://huggingface.co/datasets/['argilla/dpo-mix-7k']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}