Upload LlamaForCausalLM

README.md

@@ -1,13 +1,12 @@
 ---
 language:
 - en
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 tags:
 - unsloth
 - transformers
 - codellama
-
 ---
 
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

config.json

@@ -12,18 +12,18 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 16384,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.0.dev0",
+  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.43.3"
 }