umarfarookm commited on
Commit
68f9373
·
verified ·
1 Parent(s): 6038d17

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -54,6 +54,14 @@ Evaluated on 335 held-out test pairs across 8 task categories:
54
  **Best performing:** Transfer analysis (ROUGE-L: 0.90)
55
  **Needs improvement:** GTFS knowledge (ROUGE-L: 0.38) — limited training data (22 pairs)
56
 
 
 
 
 
 
 
 
 
57
  ## Training Data
58
 
59
  The model was trained on synthetic instruction-response pairs generated from **15 real public GTFS feeds** across **10 countries**:
 
54
  **Best performing:** Transfer analysis (ROUGE-L: 0.90)
55
  **Needs improvement:** GTFS knowledge (ROUGE-L: 0.38) — limited training data (22 pairs)
56
 
57
+ ## Available Formats
58
+
59
+ | Format | File | Size | Use Case |
60
+ |--------|------|------|----------|
61
+ | Safetensors | `model.safetensors` | 3.09 GB | Full precision — Transformers/Python |
62
+ | GGUF Q4_K_M | `UmarTransit-1B.Q4_K_M.gguf` | 986 MB | 4-bit — Ollama/llama.cpp (recommended) |
63
+ | GGUF Q8_0 | `UmarTransit-1B.Q8_0.gguf` | 1.65 GB | 8-bit — Ollama/llama.cpp (higher quality) |
64
+
65
  ## Training Data
66
 
67
  The model was trained on synthetic instruction-response pairs generated from **15 real public GTFS feeds** across **10 countries**: