Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,63 @@
+# FIM-7B Inference on SWE-Bench Verified
+
+This guide describes how to run the **FIM-7B** checkpoint on SWE-Bench Verified (and Lite) with the R2E-Gym agent scaffold in this repository.
+
+## Model
+
+Local path: `models/FIM-7B/` (checkpoints are gitignored; do not commit them).
+
+- Base model: `Qwen/Qwen2.5-Coder-7B-Instruct`
+- FIM mid-training: `train/FIM_Midtrain_7B.yaml`
+- Post-training: SFT on R2E-Gym agent trajectories
+
+
+## 1. Serve the model with vLLM
+
+```bash
+CUDA_VISIBLE_DEVICES=0 \
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
+.venv-vllm/bin/python -m vllm.entrypoints.openai.api_server \
+  --model models/FIM-7B \
+  --served-model-name FIM-7B \
+  --host 127.0.0.1 \
+  --port 8400 \
+  --tensor-parallel-size 1 \
+  --max-model-len 65536 \
+  --hf-overrides '{"max_position_embeddings": 65536}' \
+  --enable-prefix-caching \
+  --gpu-memory-utilization 0.9 \
+  > vllm_fim7b.log 2>&1 &
+```
+
+
+Wait until the server is up (model load takes ~1 minute):
+
+```bash
+curl -s http://127.0.0.1:8400/v1/models
+```
+
+## 2. Run the agent on SWE-Bench Verified
+
+```bash
+export OPENAI_API_KEY=EMPTY
+export LLM_BASE_URL="http://127.0.0.1:8400/v1"
+
+uv run python src/r2egym/agenthub/run/edit.py runagent_multiple \
+  --dataset "R2E-Gym/SWE-Bench-Verified" \
+  --split "test" \
+  --start_idx 0 \
+  --k 500 \
+  --traj_dir "./traj" \
+  --exp_name "FIM-7B_swebench_verified_r1" \
+  --llm_name "openai/FIM-7B" \
+  --scaffold "r2egym" \
+  --backend "docker" \
+  --use_fn_calling False \
+  --temperature 0 \
+  --max_steps 40 \
+  --max_steps_absolute 100 \
+  --max_workers 6 \
+  --max_reward_calc_time 1200 \
+  --max_tokens 65536 \
+  --use_existing True
+```