Run 4. Outer Step 0. Inner Step 6.

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distributed/llama-1b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "block_list": [
+    4494477,
+    4494484,
+    4494491,
+    4494497,
+    4494504
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "inner_step": 5,
+  "intermediate_size": 5632,
+  "last_allreduce_block": 5517501,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3",
+  "use_cache": false
+}

inner_optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3641aaf9f9179e343ecd420377e328931ce5493622c0c616b23e437e7faa66
+size 8800564012

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818b5ca6363bbb24d7990fbe6b0b4e57c2ae37731f960bf5f32549090224de99
+size 4400216536