README: clarify training stage; remove unattributed benchmark numbers

README.md

@@ -9,20 +9,21 @@ tags:
 
 # QUEST-35B-MT
 
-QUEST **35B-class MoE** checkpoint after **mid-training + SFT** (Qwen3.5-35B-A3B base). This is the +MT stage in the training progression (Vanilla → SFT → **MT+SFT** → RL).
+This is the **mid-training only** checkpoint of QUEST-35B-A3B (`Qwen3_5MoeForConditionalGeneration`). It has **not** been fine-tuned with SFT or RL and therefore **does not** have the instruction-following or tool-use capabilities required to complete deep research tasks.
+
+It is released as an intermediate artifact for research purposes (e.g., initializing further fine-tuning experiments or studying the effect of mid-training). If you need a usable deep research agent, please use [QUEST-35B-MT+SFT](https://huggingface.co/osunlp/QUEST-35B-MT-Plus-SFT) or [QUEST-35B-RL](https://huggingface.co/osunlp/QUEST-35B-RL) instead.
+
+## Training stage
+
+| Stage | Applied |
+| --- | :---: |
+| Mid-training (MT) | ✓ |
+| Supervised fine-tuning (SFT) | ✗ |
+| Reinforcement learning (RL) | ✗ |
 
 ## Benchmark results
 
-| Benchmark | Metric | Score |
-| --- | --- | ---: |
-| BrowseComp | avg@3 | 45.5 |
-| Mind2Web 2 | avg@3 | 29.9 |
-| HLE | avg@3 | 39.74 |
-| DeepResearch Bench | avg@3 | 39.72 |
-| BrowseComp-Plus | avg@3 | 58.6 |
-| WideSearch | Item F1 avg@4 | 62.5 |
-| GAIA | avg@3 | 83.17 |
-| LiveResearchBench | avg@3 | 65.47 |
+Not reported — this model lacks task-completion capability without SFT.
 
 ## Quick start
 
@@ -36,8 +37,6 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 ```
 
-Apply the model's chat template with `tokenizer.apply_chat_template(...)` before passing prompts.
-
 ## License
 
 Released under the **Apache License 2.0**.