Fix links to the tech report and Carbon evals

README.md

@@ -14,7 +14,7 @@ pipeline_tag: text-generation
 ![](figures/carbon-3b-banner.png)
 
 <p align="center">
-  <a href="https://huggingface.co/HuggingFaceBio/Carbon-3B/blob/main/tech-report.pdf"><b>Technical Report</b> 🧬</a>
+  <a href="https://www.biorxiv.org/content/10.64898/2026.05.22.727119v1"><b>Technical Report</b> 🧬</a>
 </p>
 
 # Carbon-3B
@@ -39,8 +39,8 @@ A generative DNA foundation model from the **Carbon** family.
 
 **Carbon-3B** is a 3B-parameter decoder-only autoregressive genomic foundation model trained on DNA and RNA sequences, with a primary focus on eukaryotes. It has a native context length of **32,768 6-mer tokens (≈ 197k DNA base pairs)** and extends to **65,536 tokens (≈ 393 kbp)** at inference time via YaRN. Carbon-3B is designed to be both strong and efficient: on generative tasks (sequence recovery), variant-effect prediction, and motif-perturbation discrimination, it matches the capability of substantially larger single-nucleotide baselines such as Evo2-7B while running several times faster.
 
-Carbon-3B is the **flagship** model of the Carbon family. We also release [**Carbon-8B**](https://huggingface.co/HuggingFaceBio/) for users who need additional capability at higher inference cost, and [**Carbon-500M**](https://huggingface.co/HuggingFaceBio/) — a small generative model intended for speculative decoding alongside Carbon-3B (or Carbon-8B).
-- Technical report: https://github.com/huggingface/carbon/blob/main/tech-report.pdf
+Carbon-3B is the **flagship** model of the Carbon family. We also release [**Carbon-8B**](https://huggingface.co/HuggingFaceBio/Carbon-8B) for users who need additional capability at higher inference cost, and [**Carbon-500M**](https://huggingface.co/HuggingFaceBio/Carbon-500M) — a small generative model intended for speculative decoding alongside Carbon-3B (or Carbon-8B).
+- Technical report: https://www.biorxiv.org/content/10.64898/2026.05.22.727119v1
 - Demo: https://huggingface.co/spaces/HuggingFaceBio/carbon-demo
 
 ### Key features
@@ -144,7 +144,7 @@ def score(seq: str) -> float:
     return logp.mean().item()
 ```
 
-For batched scoring with attention masking and full reproducible evaluation pipelines (sequence recovery, ClinVar / BRCA2 / TraitGym VEP, triplet-expansion / synonymous codon replacement, Genomic-NIAH), use the official scripts in the [Carbon evaluation directory](https://github.com/huggingface/carbon/tree/main/evaluation) — see [`perturbation_tasks.py`](https://github.com/huggingface/carbon/blob/main/evaluation/perturbation_tasks.py) for the canonical `score_hf` implementation and [`README.md`](https://github.com/huggingface/carbon/blob/main/evaluation/README.md) for run instructions across all tasks.
+For batched scoring with attention masking and full reproducible evaluation pipelines (sequence recovery, ClinVar / BRCA2 / TraitGym VEP, triplet-expansion / synonymous codon replacement, Genomic-NIAH), use the official scripts in the [Carbon evaluation directory](https://github.com/huggingface/carbon/tree/main/carbon/evaluation) — see [`perturbation_tasks.py`](https://github.com/huggingface/carbon/blob/main/carbon/evaluation/perturbation_tasks.py) for the canonical `score_hf` implementation and [`README.md`](https://github.com/huggingface/carbon/blob/main/carbon/evaluation/README.md) for run instructions across all tasks.
 
 ### Long context: extending to 65,536 tokens (≈ 393 kbp) with YaRN
 
@@ -273,7 +273,7 @@ print(f"reference preferred: {scores[0] > scores[1]}")
 
 ## Evaluation
 
-All evaluations are zero-shot and use the [public Carbon evaluation pipeline](https://github.com/huggingface/carbon/tree/main/evaluation). The suite covers seven tasks across four capability families:
+All evaluations are zero-shot and use the [public Carbon evaluation pipeline](https://github.com/huggingface/carbon/tree/main/carbon/evaluation). The suite covers seven tasks across four capability families:
 
 | Family | Task | Metric |
 |---|---|---|