Upload LlamaForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": "<bos>",
+  "eos_token_id": "<eos>",
+  "fused_bias_fc": false,
+  "fused_dropout_add_ln": false,
+  "fused_mlp": false,
+  "hidden_act": "silu",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 2048,
+  "max_seq_length": 64,
+  "model_name_or_path": "llama_small_FA",
+  "model_type": "llama",
+  "num_attention_heads": 10,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 10,
+  "pretraining_tp": 1,
+  "residual_in_fp32": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "use_flash_attn": true,
+  "vocab_size": 30003
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": "<bos>",
+  "eos_token_id": "<eos>",
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a9bf97f46ab18fd135c1b48c6c90fe0a01871fe1a441dead920fa37dc6a7ae
+size 782957366