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:fc5c44603aae709001144ddf1dfe5fe88ca6910b5f3540195307d22a36606649
+size 1282660592

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db630b71af5c02f771385c874e57c2e0e5b1e34dc6f30fef969a8a4e6ba8e2fc
+size 2565425338

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:aa766ef82639f1ed060e8cf267d5050b9461ff300422b97b946e44de58e05758
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dda77eeae0a565b95e140d8f0d5d206abebdaec3ed0c23eec9d3e3e041c8725
+size 4984