Removed the plot assets

README.md

@@ -116,7 +116,7 @@ hardware, wall-clock time, and energy consumption are not documented in the
 current release artifacts. These should be added when verified records become
 available.
 
-![TwiL-LM data creation, training, and evaluation workflow](card_assets/data_workflow_v2.png)
+
 
 ## Evaluation
 
@@ -128,16 +128,11 @@ over the eligible objectives. `mcq_answer` and `procedural` use
 `max(accuracy, loose_match)`. `lean_prove` and perplexity corpora are excluded
 from the macro score.
 
-![Macro accuracy compared with base models](card_assets/macro_vs_bases.png)
-
-![Macro accuracy compared across Base and LoRA models](card_assets/macro_vs_bases_and_lora.png)
 
 The broader comparison includes checkpoints with different parameter counts,
 training procedures, and adaptation methods. It is useful for context but is not
 a controlled architecture or scaling study.
 
-![TwiL-LM compared with SmolLM2-1.7B by objective](card_assets/objectives_vs_smollm2.png)
-
 TwiL-LM performs best on entailment labeling (**0.655**) and improves FOL
 translation (**0.235**, compared with approximately zero for the base). Lean
 formalization, Lean proving, and procedural reasoning remain weak.
@@ -147,22 +142,13 @@ formalization, Lean proving, and procedural reasoning remain weak.
 OOD transfer was measured on GSM8K, ARC-Challenge chain-of-thought,
 ARC-Challenge 25-shot log-likelihood (`acc_norm`), and LogicBench BQA.
 
-![TwiL-LM and SmolLM2-1.7B on OOD benchmarks](card_assets/unseen_benchmarks.png)
-
 Compared with SmolLM2-1.7B, TwiL-LM improves LogicBench BQA
 (**0.590 vs 0.563**) but is lower on GSM8K (**0.380 vs 0.413**), ARC-C
 chain-of-thought (**0.463 vs 0.587**), and ARC-C 25-shot log-likelihood
 (**0.460 vs 0.490**).
 
-![OOD benchmark macro accuracy for Base, FT, and PS variants](card_assets/unseen_macro_no_gsm8k.png)
-
-These results indicate mixed transfer outside the formal-logic training
-distribution. Larger general reasoning models remain stronger on several OOD
-benchmarks.
-
 ### Throughput evaluation
 
-![Aggregate generation throughput](card_assets/throughput.png)
 
 The formal-logic run generated 422,627 tokens in 1,152.34 generation seconds,
 or **366.8 aggregate tokens per second**. The configuration used a maximum of