EAGLE3 draft model for sarvam-30b v2 (fixed config, epoch 3, step 95k, acc 0.42)

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      9,
+      17
+    ],
+    "use_aux_hidden_state": true
+  },
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 8000000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3443e5ddcdee95a82b77fbbe051a33a04347f7bfb585066beddec4848fc42926
+size 673738208

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15917376a3948c9ca5baf452d571782910d9ec50ef77c45deb63e23900fb27a6
+size 4183