Upload LlamaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/n/ml/models/aerner/lm-v2/checkpoint-76000",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "shared_input_output_embedding": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.29.1",
+  "use_cache": false,
+  "use_memorry_efficient_attention": true,
+  "use_stable_embedding": true,
+  "vocab_size": 100000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af5ea94b7d6af2b5c99464086434f26ae3a681d767bd29674ded3b51f22336a
+size 2169864106