Upload folder using huggingface_hub

README.md

@@ -1,3 +1,19 @@
----
-license: mit
----
+---
+license: mit
+---
+
+# kimi-k2.5-eagle3
+
+Post-trained EAGLE3 draft model for [moonshotai/Kimi-K2.5](https://huggingface.co/moonshotai/Kimi-K2.5), based on [lightseekorg/kimi-k2.5-eagle3](https://huggingface.co/lightseekorg/kimi-k2.5-eagle3).
+
+## Overview
+
+This model is a speculative decoding draft model trained using the [EAGLE3](https://arxiv.org/abs/2503.01840) architecture. It can be used to accelerate inference of Kimi-K2.5 by predicting multiple tokens in parallel.
+
+## Training
+
+The base EAGLE3 draft model from [lightseekorg/kimi-k2.5-eagle3](https://huggingface.co/lightseekorg/kimi-k2.5-eagle3) was further post-trained on open-source coding datasets.
+
+## Usage
+
+This model is intended to be used as a draft model with EAGLE3-compatible inference engines such as [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang).

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 163584,
+  "eos_token_id": 163585,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 64.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 50000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 163840,
+  "draft_vocab_size": 163840
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc759152b21b2e5caa932823043fae4b01c7c69fe200ea63651d302010c6469
+size 6356526520