Upload folder using huggingface_hub

config.json

@@ -5,7 +5,11 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 3072,

config.json.orig

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -1,7 +1,11 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "transformers_version": "4.45.0.dev0",
   "do_sample": true,
   "temperature": 0.6,

generation_config.json.orig

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.45.0.dev0",
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.9
+}

tokenizer_config.json

@@ -2050,6 +2050,8 @@
     }
   },
   "additional_special_tokens": [
+    "<|start_of_thinking|>",
+    "<|end_of_thinking|>",
     "<|start_of_tools|>",
     "<|end_of_tools|>",
     "<|start_of_tool_calls|>",