End of training

README.md

@@ -1,16 +1,19 @@
 ---
+datasets:
+- argilla/dpo-mix-7k
 library_name: transformers
-model_name: mistral-7b-sft-simpo-basic-5e-7-005-v142
+model_name: /home/silvias/alignment-handbook/data/mistral-7b-sft-basic-5e-5-000-v132-full
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - orpo
 licence: license
 ---
 
-# Model Card for mistral-7b-sft-simpo-basic-5e-7-005-v142
+# Model Card for /home/silvias/alignment-handbook/data/mistral-7b-sft-basic-5e-5-000-v132-full
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) 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 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/home/silvias/alignment-handbook/data/mistral-7b-sft-basic-5e-5-000-v132-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}