Upload LlamaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./training/cfg_level4_rules2_symbols4_seed1/run_v2_more_steps_again",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 120,
+  "initializer_range": 0.02,
+  "intermediate_size": 352,
+  "max_position_embeddings": 512,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 6,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 8
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9135a8b8ae94f96245a32ef89f5784c04d7a91b57388ff7111781370ef762be1
+size 2965216