Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-8B
+tags:
+- code
+- software-engineering
+- agent
+---
+
+# FIM-8B Inference on SWE-Bench Verified
+
+This guide describes how to run the **FIM-8B** checkpoint on SWE-Bench Verified (and Lite). Unlike FIM-7B and FIM-14B (R2E-Gym scaffold), this model is post-trained on SWE-Lego trajectories and is evaluated with the SWE-Lego setup: OpenHands `CodeActAgent` for inference and the official SWE-bench harness for scoring.
+
+## Model
+
+Local path: `models/FIM-8B/` (checkpoints are gitignored; do not commit them).
+
+- Base model: `Qwen/Qwen3-8B`
+- FIM mid-training: FIM v2/v3 data
+- Post-training: SFT on SWE-Lego trajectories
+
+
+## 1. Serve the model with vLLM
+
+```bash
+CUDA_VISIBLE_DEVICES=0 \
+python -m vllm.entrypoints.openai.api_server \
+  --model models/FIM-8B \
+  --served-model-name FIM-8B \
+  --host 127.0.0.1 \
+  --port 8400 \
+  --tensor-parallel-size 1 \
+  --max-model-len 163840 \
+  --max-num-seqs 16 \
+  --gpu-memory-utilization 0.9 \
+  > vllm_fim8b.log 2>&1 &
+```
+
+The checkpoint ships `max_position_embeddings: 163840` and its own chat template, so no rope or template overrides are needed.
+
+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
+
+Inference uses OpenHands 0.53.0. Define the LLM in `config.toml`:
+
+```toml
+[llm.eval_fim]
+model = "openai/FIM-8B"
+base_url = "http://127.0.0.1:8400/v1"
+api_key = "EMPTY"
+temperature = 0.0
+max_input_tokens = 147456
+max_output_tokens = 16384
+native_tool_calling = false
+```
+
+From the OpenHands checkout:
+
+```bash
+env USE_HINT_TEXT=false \
+    INSTRUCTION_TEMPLATE_NAME=swe_default.j2 \
+    ENABLE_PLAN_MODE=false \
+    ADD_IN_CONTEXT_LEARNING_EXAMPLE=false \
+poetry run python evaluation/benchmarks/swe_bench/run_infer.py \
+  --config-file config.toml \
+  --agent-cls CodeActAgent \
+  --llm-config llm.eval_fim \
+  --max-iterations 100 \
+  --eval-num-workers 1 \
+  --eval-output-dir ./eval_out \
+  --dataset princeton-nlp/SWE-bench_Verified \
+  --split test \
+  --mode swe
+```
+
+For SWE-Bench Lite, use `--dataset princeton-nlp/SWE-bench_Lite`.
+
+## 3. Score with the SWE-bench harness
+
+Convert the OpenHands `output.jsonl` to a predictions file with `evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_swe_json.py`, then evaluate it with the official SWE-bench harness (`python -m swebench.harness.run_evaluation`). The reported score is `resolved_instances / total_instances`.

chat_template.jinja

@@ -0,0 +1,7 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system
+' + system_message + '<|im_end|>
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user
+' + content + '<|im_end|>
+<|im_start|>assistant
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>
+' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,73 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 163840.0,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 40960,
+    "rope_theta": 1000000,
+    "rope_type": "yarn"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a69ce2ed5edd997d442770367c0f767924cefcd5797ef32dbc778116a159ee
+size 16381517208

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}