初始化项目，由ModelHub XC社区提供模型

Model: kartikraut09/ecocloud-grpo-qwen Source: Original Platform
2026-06-16 05:32:16 +08:00
commit 06f303562a
8 changed files with 309 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,114 @@
+---
+license: mit
+language:
+- en
+tags:
+- reinforcement-learning
+- grpo
+- cloud-management
+- multi-agent
+- sustainability
+- openenv
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+pipeline_tag: text-generation
+---
+
+# ⚡ CloudEdge GRPO Controller
+
+**A Qwen2.5-0.5B model fine-tuned with Group Relative Policy Optimization (GRPO) to manage cloud infrastructure crises.**
+
+Built for the **Meta PyTorch OpenEnv Hackathon Grand Finale**.
+
+## Model Description
+
+This model is a reinforcement-learning-trained controller for the **CloudEdge** cloud crisis simulator. It learns to select optimal infrastructure actions (scale_up, scale_down, optimize_energy, migrate_region) by balancing three competing objectives:
+
+| Objective | Target | Agent |
+|-----------|--------|-------|
+| Latency | < 150ms | ResourceAgent |
+| Cost | < $400/hr | CostAgent |
+| Carbon | < 220 units | SustainabilityAgent |
+
+### Training Method
+
+- **Algorithm:** GRPO (Group Relative Policy Optimization) via [TRL](https://github.com/huggingface/trl)
+- **Base Model:** [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+- **Training Steps:** 512
+- **Generations per prompt:** 4
+- **Reward Function:** Shaped multi-objective reward with gap closure + worst-metric bonus
+
+### Shaped Reward Function
+
+```
+reward = Σ (gap_closure × weight) + worst_metric_bonus
+```
+
+| Action | Reward (crisis state) | Model Learns |
+|--------|----------------------|-------------|
+| `optimize_energy` | **+7.5** | "Best action — addresses cost + carbon simultaneously" |
+| `scale_down` | **+5.75** | "Good — reduces cost effectively" |
+| `migrate_region` | **+3.75** | "Moderate — helps carbon but hurts cost" |
+| `scale_up` | **+1.5** | "Worst — increases cost and carbon" |
+
+### Training Results
+
+The model converged to selecting `optimize_energy` as the dominant policy when all metrics are above target — which is the mathematically optimal action given the shaped reward function.
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("kartikraut09/ecocloud-grpo-qwen")
+tokenizer = AutoTokenizer.from_pretrained("kartikraut09/ecocloud-grpo-qwen")
+
+prompt = """<|im_start|>system
+You are the CloudEdge controller managing a cloud platform in crisis.
+Pick the BEST single action for the current state. Respond with ONLY the action name.
+
+Actions:
+  scale_up        → latency -40, cost +30, carbon +20
+  scale_down      → latency +25, cost -35, carbon -15
+  optimize_energy → latency +10, cost -20, carbon -40
+  migrate_region  → latency +15, cost +10, carbon -50
+
+Targets: latency<150ms, cost<$400, carbon<220<|im_end|>
+<|im_start|>user
+Cloud state: latency=280ms, cost=$620/hr, carbon=380, load=critical. Best action?<|im_end|>
+<|im_start|>assistant
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=16, temperature=0.1)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# Output: optimize_energy
+```
+
+## Technical Details
+
+- **Architecture:** Qwen2 (0.5B parameters)
+- **Framework:** PyTorch + HuggingFace Transformers + TRL
+- **Environment:** OpenEnv-compatible Gymnasium-style simulator
+- **Training Hardware:** Google Colab T4 GPU
+- **Training Time:** ~15 minutes (512 steps)
+
+## Project Links
+
+- **GitHub:** [KartikRaut09/ecocloud-war-room](https://github.com/KartikRaut09/ecocloud-war-room)
+- **Hackathon:** Meta PyTorch OpenEnv Hackathon Grand Finale
+- **Themes:** Multi-Agent Interactions · Long-Horizon Planning · World Modeling
+
+## Citation
+
+```bibtex
+@misc{cloudedge2026,
+  title={CloudEdge: Multi-Agent LLM Simulator for Sustainable Cloud Crisis Management},
+  author={Kartik Raut},
+  year={2026},
+  url={https://github.com/KartikRaut09/ecocloud-war-room}
+}
+```
+
+## License
+
+MIT License
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.0.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ee3baaaefadcbdd372c850438e531a1ecab63808f3ea7f1087487c133cb0df
+size 988097824
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,29 @@
+{
+  "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,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}