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": "4.39.1",
+  "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": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb483f524730af674ebdee64454f021c9b1da5008bafa851be57a6caf15bbc22
+size 137101312

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ef60205a6789a616dcdb555bbdaef6fa82ed14afd8fad0f74efcd0c1169991
+size 139198464

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f55eade71210cfd5f838c112d35568ec605af8502f63e153af4a8faa685da4e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd43f7fc37ca1282a1c50544339d7b45402ac76da2ca7d3cede08c92c8569d41
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d82bb9684aeb3b6c67f73409cb43b2de17cd694f74d4d9cd144b3d340d556a9
+size 4984