Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "GPTNeoXModel"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": null,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

decoder/config.json

@@ -0,0 +1,16 @@
+{
+    "d_model": 768,
+    "d_intermediate": 0,
+    "n_layer": 24,
+    "vocab_size": 50277,
+    "ssm_cfg": {
+        "layer": "Mamba2"
+    },
+    "attn_layer_idx": [],
+    "attn_cfg": {},
+    "rms_norm": true,
+    "residual_in_fp32": true,
+    "fused_add_norm": true,
+    "pad_vocab_size_multiple": 8,
+    "tie_embeddings": true
+}

decoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcd935cdcffa0833adb2cf460cedabe17d68956a49826b7b39e495782fb5913
+size 258047026

meta.json

@@ -0,0 +1 @@
+{"step": 3000, "tokens_seen": 208947617, "encoder": "EleutherAI/pythia-410m", "gpu_profile": "A100_80GB"}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3f36505da5bbfe089dcab93bb056f6b68a7482261104009701342c8d4f4f7c
+size 707676888

projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db741e4ab322bfc761a05eb2c7441adc796ebe36371566919e6ff9d87edb80f
+size 50332966

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}