Training in progress, step 200

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "HyperBitSSMForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 768,
+  "hop": 48,
+  "intermediate_size": 1792,
+  "lowrank": 32,
+  "model_type": "hyper_bit_ssm_98m_v55",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "transformers_version": "5.15.0",
+  "use_cache": false,
+  "vocab_size": 8192,
+  "window": 96
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.15.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dec04aa73633790ed823134db0568c930e8388551718782453273669858d23e
+size 393799132

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c232850a4dbee80edbe61b74faebfee8c9657ad64122625f20b6dc9d16b315
+size 5329