End of training

README.md

@@ -2,11 +2,13 @@
 license: other
 library_name: peft
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- youndukn/ROLE_PLAY_INSTRUCT
 base_model: Gryphe/MythoMax-L2-13b
 model-index:
 - name: mythomax-13b-sft-lora
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mythomax-13b-sft-lora
 
-This model is a fine-tuned version of [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b) on the generator dataset.
+This model is a fine-tuned version of [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b) on the youndukn/ROLE_PLAY_INSTRUCT dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8712
 

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Gryphe/MythoMax-L2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}