Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+license: other
+base_model: moonshotai/Kimi-K2.7-Code
+library_name: transformers
+tags:
+- speculative-decoding
+- eagle3
+- eagle
+- draft-model
+- kimi-k2
+- specforge
+---
+
+# Kimi-K2.7-Code EAGLE3 draft
+
+EAGLE3 speculative-decoding **draft model** for [moonshotai/Kimi-K2.7-Code](https://huggingface.co/moonshotai/Kimi-K2.7-Code),
+trained with [SpecForge](https://github.com/sgl-project/SpecForge) (PR #593) on NVIDIA Nemotron-Post-Training-Dataset-v2 (stem+chat+math+code).
+
+- Single-layer Llama-style EAGLE3 draft (`LlamaForCausalLMEagle3`, hidden 7168); consumes target aux hidden states at layers [1,29,57].
+- Target vocab/tokenizer: Kimi-K2.7-Code (vocab 163840); reduced draft vocab 32000 (t2d/d2t mapping, 97.5% token coverage on the training mix).
+- Checkpoint: epoch_1_step_98000 — **Work-in-progress snapshot (epoch_1_step_98000)** — training still running.
+
+Intended as the EAGLE3 draft in SGLang speculative decoding paired with the Kimi-K2.7-Code target. Trained as an A/B counterpart to the DFlash draft ([cm00cm/Kimi-K2.7-Code-DFlash](https://huggingface.co/cm00cm/Kimi-K2.7-Code-DFlash)).

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 163584,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      29,
+      57
+    ],
+    "use_aux_hidden_state": true
+  },
+  "eos_token_id": 163586,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 40960,
+  "max_position_embeddings": 163840,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "pad_token_id": 163839,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 163840
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3708977c5eb870afbc631a17953682c1855b24abb99e62eb4fcbbfdad922f1
+size 2896121344