fix links: GitHub URL + base/sft cross-links

README.md

@@ -14,7 +14,7 @@ library_name: pytorch
 # code-llm-435m · sft — the instruction-tuned variant
 
 The instruction-tuned version of the 435M from-scratch code model whose pretrained weights are in
-[`../base`](../base). Same architecture, same 32,000-token byte-level BPE vocabulary, same 1,024-token
+[`TightX/code-llm-435m-base`](https://huggingface.co/TightX/code-llm-435m-base). Same architecture, same 32,000-token byte-level BPE vocabulary, same 1,024-token
 context — only the weights differ. It reads a plain-English request (*"write a function that checks
 whether a number is prime"*) or continues a bare `def` signature, and writes Python.
 
@@ -24,7 +24,7 @@ that did.
 
 ## Architecture
 
-Identical to [`../base`](../base) — see that card for the full table. In short: 434,680,832
+Identical to [`TightX/code-llm-435m-base`](https://huggingface.co/TightX/code-llm-435m-base) — see that card for the full table. In short: 434,680,832
 parameters, 22 layers, d_model 1,024 / 16 heads, SwiGLU (d_ff 4,096), RoPE (theta 500,000), RMSNorm,
 causal SDPA, untied embeddings, context 1,024, released file in bf16.
 
@@ -44,7 +44,7 @@ causal SDPA, untied embeddings, context 1,024, released file in bf16.
 Roughly 30 post-training runs were evaluated to reach this one. The approaches that did **not** work —
 instruction-free training, teaching the two objectives in two stages, self-distillation, weight
 averaging ("soups"), ratio sweeps — are documented with their numbers, including the mistakes, in the
-GitHub repository.
+GitHub repository at https://github.com/TightXu/Simple_Code_LLM.
 
 ## Results
 
@@ -98,5 +98,5 @@ from the training corpus despite filtering and deduplication.
 ## Links
 
 `DESIGN.md` (decisions and why), `CHALLENGES.md` (every bug and contaminant), the ablation report, the
-post-training log with its corrections, and the evaluation harness are in the GitHub repository. MIT
-licensed.
+post-training log with its corrections, and the evaluation harness are in the GitHub repository at
+https://github.com/TightXu/Simple_Code_LLM. MIT licensed.