Upload folder using huggingface_hub

README.md

@@ -1,3 +1,7 @@
----
-license: mit
----
+---
+license: mit
+---
+
+# QED-75M
+
+Custom causal LM (SLLM). Use this repo's config and weights with the same model code as the training repo.

config.json

@@ -0,0 +1,18 @@
+{
+  "vocab_size": 49152,
+  "max_seq_len": 8192,
+  "d_model": 384,
+  "n_layers": 32,
+  "n_heads": 6,
+  "ffn_hidden_dim": 1024,
+  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-05,
+  "initializer_range": 0.02,
+  "dropout": 0.0,
+  "tie_word_embeddings": true,
+  "bias": false,
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "model_type": "qed"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7509559cb60b2fcf1dee6defb9442304553a6d9a37bc6d0619b03e126064e634
+size 377814056

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdf6f265fadf05e51ce338ee0373db54ffb7571be4a268f4bac1670539c2188
+size 302398063

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "pad_token": "<pad>",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "vocab_size": 49152,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "unk_token_id": 3
+}