Training in progress, step 1000

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "SmalLmForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "balancing_coef": 0.0001,
+  "bos_token_id": 1,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 0,
+  "expert_size": 576,
+  "gate_noise": false,
+  "head_size": 64,
+  "hidden_size": 512,
+  "high_rotations": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_dropout": 0.1,
+  "low_rotations": 1,
+  "max_seq_len": 1024,
+  "mlp_bias": false,
+  "model_type": "smallm",
+  "moe_bias": false,
+  "moe_period": 2,
+  "moe_type": "default",
+  "no_moe_layers": 10,
+  "noisy_experts": false,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 20,
+  "num_kv_heads": 2,
+  "original_seq_len": 1024,
+  "pad_token_id": 0,
+  "positional_bias_type": "rope",
+  "rms_affine": false,
+  "rms_norm_eps": 1e-06,
+  "rope_base": 100000,
+  "routed_experts": 8,
+  "shared_experts": 1,
+  "sliding_window_attention": true,
+  "sliding_window_context": 1024,
+  "sliding_window_period": 4,
+  "static_residual": false,
+  "token_experts": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "use_moe": false,
+  "vocab_size": 60000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a922d0fb93138543d9c71953a8b445e82ac2e882b91763888dc16d89db4b7c
+size 301235464

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d2cbedeb75b9254fdded4264191ece35eac9f755fa3f4e7a861e2389e2ec8b
+size 6008