Upload LlamaForCausalLM

config.json

@@ -1,8 +1,10 @@
 {
-  "_name_or_path": "bagel-7b-v0.1-workdir/checkpoint-11800",
+  "_name_or_path": "bagel-dpo-7b-v0.1",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -10,16 +12,18 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
-  "model_type": "mistral",
+  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "use_cache": false
 }