pth and safetensors file

out/converted_model/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama_v1.1",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "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": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

out/converted_model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e592a36283b210f9a88d9ad25cd0c7b8cd123db521e5c42835c022aa390185b
+size 219233550

out/converted_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767ba31401cc085a899cc7f38aa6542018291017cce2e2ecadca16cbae7e6eec
+size 4138071216

out/pretrain/final/config.json

@@ -0,0 +1,22 @@
+{
+  "_name_or_path": "tangledgroup/tangled-llama-109m-32k-base-v0.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_size": 512,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}