Upload LlamaForCausalLM

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/home/ryangam/RiC_code/reward_models_unified_new/Meta-Llama-3-8B-Instruct_llama3_len4096trunc_700kdata_fulltrain_nonlinear_sftreg0.01_lr3e-6_3e-06/logs/tmp-checkpoint-1091",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "model.AutoModelForCausalLMWithValueHead",
+    "AutoModelForSequenceClassification": "model.AutoModelForCausalLMWithValueHead"
+  },
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vhead_layer_type": "mlp",
+  "vhead_num_layers": 1,
+  "vhead_num_neurons": 1024,
+  "vocab_size": 128257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5ce445825122c35b713d932ec77ec85199dff7cb5403dd1b6e64896570fb36
+size 1067475556