Upload folder using huggingface_hub

README.md

@@ -22,6 +22,9 @@ A **gpt-oss-120b** version focused on improving practical coding-agent behavior
 > Also available in **[GGUF for llama.cpp / LM Studio / Ollama →](https://huggingface.co/exalandru/GPT-OSS-Coder-GGUF)**
 
 
+# Version 1.1
+> This release adds three focused passes over re-curated data, each targeting a behaviour measured missing in the previous one: writing failure-injection regression tests before closing, iterating on multi-defect repositories past the first green suite, and honouring per-harness completion contracts. Every pass was gated by calibrated probes and a held-out benchmark ladder before being promoted.
+
 ## How it works
 
 It digs deeper into the repository, follows evidence to the root cause, and keeps iterating until the fix holds under real tests instead of stopping at a plausible-looking patch.
@@ -33,6 +36,10 @@ It digs deeper into the repository, follows evidence to the root cause, and keep
 - Reasons about state and invariants across components
 - Continues iterating when the first implementation is incomplete
 - Ends its turns with a real report of what was done — no empty summaries, no truncated turns
+- Writes its own failing test before declaring victory : adds regression tests that fail on the unfixed code, then proves the fix against them
+- Iterates past the first green suite : coupled defects don't survive the second pass
+- Follows each harness's closing convention : a Codex task ends with a final report, a Cline task ends with a proper `attempt_completion` call
+- Tightens what a fix requires : removes deprecated or unauthorized call forms instead of quietly keeping them accepted
 
 The fine-tune also significantly reduced malformed JSON arguments.
 
@@ -40,7 +47,7 @@ Works even better with my **[Adversarial Agent Engineering](https://github.com/e
 
 ## Runtime
 
-<span style="color:orange;">Trained and optimized for Codex.</span>
+<span style="color:orange;">Optimized for Codex.</span>
 
 ### Codex GPT-OSS Server
 
@@ -62,6 +69,11 @@ mlx_lm.generate --model exalandru/GPT-OSS-Coder-MLX --prompt "Hello World!"
 
 **Format:** MLX, MXFP4 experts + bf16 attention, ~61 GB on disk. Weights are consolidated — nothing to fuse or merge. Runs on Apple silicon with 96 GB unified memory; a full agent session peaks around 82 GB.
 
+> **116.8B parameters** (MoE, ~5.1B active per token — which is why it decodes
+> faster than much smaller dense models). The Hub badge shows ~24B because MLX
+> packs eight 4-bit weights per uint32 element and the badge counts elements,
+> not parameters.
+
 ---
 
 ## How it was trained

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bcb1049fef7d8db54681f4e6f2529fef4d359326d5ad242c18ee05ed182a62
+oid sha256:6a4aa4f912819cecc39daf98924e45c5fdbd324a292171a8d5044ef49ca297d4
 size 5244364053

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e7e73a5a189d03720a7df75145c5fb7cb9b07c7f17e9c3bc5b19a649967833
+oid sha256:ca880309ec746517a35b6241b993b4c47daf0ad44ab65f68fda5aaa589f09e2a
 size 5244364043

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9274ca1b754e0d2ebfc0885bb214aa3e61679abfe46ad95ebbd298f4d171f83d
+oid sha256:afcd7bb586b8d4644697491f728c733034aa0a0dd8cd5b30070a690ae5e8b844
 size 5244364039

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0997e608e3732768f9bb5706fdbe768eef273caf86def548499daa11f1bc5b38
+oid sha256:56ba1913391283792fa7b60cc8e8155e4ced59ca5421cdb026ea0feb75a01818
 size 2288530151