Fix target model references: Qwen3-Next-80B-A3B-Instruct -> Qwen3-Coder-Next; fix narrow tree Terminal-Bench tok/s; remove internal comment

README.md

@@ -3,7 +3,7 @@ library_name: transformers
 license: apache-2.0
 language:
   - en
-base_model: Qwen/Qwen3-Next-80B-A3B-Instruct
+base_model: Qwen/Qwen3-Coder-Next
 pipeline_tag: text-generation
 tags:
   - eagle3
@@ -17,11 +17,9 @@ tags:
   - code
 ---
 
-<!-- Internal: exp-e (gpu/qwen3-coder-next) -->
-
 # EAGLE3 Draft Head — Qwen3-Coder-Next
 
-A lightweight EAGLE3 draft head for [Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct) (80B MoE, 512 experts, 10 active per token, GDN+attention hybrid, 48 layers). Trained with [SpecForge](https://github.com/tails-mpt/SpecForge) on 8x H200 GPUs using the [EAGLE-3](https://arxiv.org/abs/2503.01840) training-time test objective.
+A lightweight EAGLE3 draft head for [Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) (80B MoE, 512 experts, 10 active per token, GDN+attention hybrid, 48 layers). Trained with [SpecForge](https://github.com/tails-mpt/SpecForge) on 8x H200 GPUs using the [EAGLE-3](https://arxiv.org/abs/2503.01840) training-time test objective.
 
 Qwen3-Coder-Next uses a hybrid layer design that interleaves standard multi-head attention with GDN (linear recurrence) layers. Only 12 of 48 layers are attention layers (every 4th: 3, 7, 11, ..., 47). EAGLE3 auxiliary layers must be selected from attention layers only — GDN layers produce recurrent hidden states that are not compatible with EAGLE3. The model code handles this automatically, selecting layers 3, 23, 47 (first, middle, last attention layers).
 
@@ -39,7 +37,7 @@ Requires our [SGLang fork](https://github.com/tails-mpt/sglang) for Qwen3-Coder-
 pip install 'git+https://github.com/tails-mpt/sglang.git#subdirectory=python'
 
 python -m sglang.launch_server \
-    --model-path Qwen/Qwen3-Next-80B-A3B-Instruct \
+    --model-path Qwen/Qwen3-Coder-Next \
     --speculative-algorithm EAGLE3 \
     --speculative-draft-model-path thoughtworks/Qwen3-Coder-Next-Eagle3 \
     --speculative-num-steps 3 \
@@ -55,7 +53,7 @@ python -m sglang.launch_server \
 
 ```bash
 python -m sglang.launch_server \
-    --model-path Qwen/Qwen3-Next-80B-A3B-Instruct \
+    --model-path Qwen/Qwen3-Coder-Next \
     --speculative-algorithm EAGLE3 \
     --speculative-draft-model-path thoughtworks/Qwen3-Coder-Next-Eagle3 \
     --speculative-num-steps 5 \
@@ -133,10 +131,10 @@ GDN (linear recurrence) layers are excluded from auxiliary layer selection becau
 | Dataset | Baseline (tok/s) | EAGLE3 (tok/s) | Speedup |
 |---------|-----------------|----------------|---------|
 | MT-Bench | 1,529.1 | 1,688.6 | **1.10x** |
-| Terminal-Bench | 2,310.5 | 1,785.4 | **1.03x** |
+| Terminal-Bench | 2,310.5 | 2,379.8 | **1.03x** |
 | HumanEval | 1,740.2 | 1,756.3 | **1.01x** |
 | SWEBench-Verified | 2,010.4 | 1,998.7 | **1.00x** |
-| **Mean** | **1,897.5** | **1,807.3** | **1.03x** |
+| **Mean** | **1,897.5** | **1,955.9** | **1.03x** |
 
 *Config: B=1 uses steps=3, topk=4, draft_tokens=8. B=32 narrow uses steps=5, topk=1, draft_tokens=6. Hardware: 4x H200 (TP=4), Triton backend. SGLang commit `63291f7f51`.*
 
@@ -165,7 +163,7 @@ GDN (linear recurrence) layers are excluded from auxiliary layer selection becau
 
 ## License
 
-This draft head is released under Apache 2.0, matching the [Qwen3-Coder-Next license](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct).
+This draft head is released under Apache 2.0, matching the [Qwen3-Coder-Next license](https://huggingface.co/Qwen/Qwen3-Coder-Next).
 
 ## Citation