Upload 8 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "scratch",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 4,
+  "pad_token_id": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50570
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "pad_token_id": 4,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e201bbc213ab844876d39eb2c7dce1d3b6053a67725844510e40dcf03a06f07e
+size 321650688

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513c35ca7c8de0c572f4e319f03aa5964689e8f68080a4e40f948f0f2dfaca85
+size 320602112

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc35c5b8c4bb8d2c1ad21d38ce97ad33d244cdde55d91541685ff62502110b3d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e437554de678c7729f101195bc617061384aff84e0dab56717f520bf7408968
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d547f05737711caf45b3e3dbcc49ea198641c98a7f0d169c30e51f2abb529205
+size 4984