Instructions to use Kabs-123/clustermind-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Kabs-123/clustermind-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct") model = PeftModel.from_pretrained(base_model, "Kabs-123/clustermind-lora") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Kabs-123/clustermind-lora with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Kabs-123/clustermind-lora to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Kabs-123/clustermind-lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Kabs-123/clustermind-lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Kabs-123/clustermind-lora", max_seq_length=2048, )
Upload trained_results.json with huggingface_hub
Browse files- trained_results.json +167 -0
trained_results.json
ADDED
|
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema": "clustermind.training.llm_lora.v1",
|
| 3 |
+
"base_model": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 4 |
+
"rl_algo": "grpo",
|
| 5 |
+
"rl_algo_note": "auto: trl present -> using episode-level GRPO",
|
| 6 |
+
"grpo_group_size": 2,
|
| 7 |
+
"kl_coef": null,
|
| 8 |
+
"trainable_params": 540672,
|
| 9 |
+
"total_params": 11.973056694274142,
|
| 10 |
+
"frozen_base": true,
|
| 11 |
+
"lora_only": true,
|
| 12 |
+
"rl_rewards": [
|
| 13 |
+
7.3623380156102005,
|
| 14 |
+
7.324068459368606,
|
| 15 |
+
5.009085256229728,
|
| 16 |
+
5.997537994512155,
|
| 17 |
+
5.306195466803626,
|
| 18 |
+
5.882729058663167,
|
| 19 |
+
5.841094427905299,
|
| 20 |
+
6.316085140109829,
|
| 21 |
+
7.19157577343347,
|
| 22 |
+
7.176404877518296,
|
| 23 |
+
4.675205221254337,
|
| 24 |
+
5.8175467043438305,
|
| 25 |
+
6.161179837401156,
|
| 26 |
+
6.219974566383556,
|
| 27 |
+
5.469031354378787,
|
| 28 |
+
7.488493981111494,
|
| 29 |
+
6.494167209716188,
|
| 30 |
+
5.783417275827285,
|
| 31 |
+
6.590633341679483,
|
| 32 |
+
6.373032599540286,
|
| 33 |
+
5.811245130903341,
|
| 34 |
+
6.037221626572529,
|
| 35 |
+
4.933720395338435,
|
| 36 |
+
6.654903324862545
|
| 37 |
+
],
|
| 38 |
+
"rl_losses": [
|
| 39 |
+
-4.590240478515625,
|
| 40 |
+
-12.874017715454102,
|
| 41 |
+
3.526590347290039,
|
| 42 |
+
-9.088369369506836,
|
| 43 |
+
-2.86224365234375,
|
| 44 |
+
9.616931915283203,
|
| 45 |
+
21.691694259643555,
|
| 46 |
+
-1.1098670959472656,
|
| 47 |
+
-0.6167259216308594,
|
| 48 |
+
-5.478660583496094,
|
| 49 |
+
-6.426750183105469,
|
| 50 |
+
-19.008302688598633,
|
| 51 |
+
13.689979553222656,
|
| 52 |
+
-10.206064224243164,
|
| 53 |
+
7.091619491577148,
|
| 54 |
+
1.6778602600097656,
|
| 55 |
+
18.007938385009766,
|
| 56 |
+
15.226968765258789,
|
| 57 |
+
-8.292940139770508,
|
| 58 |
+
-1.3204174041748047,
|
| 59 |
+
16.056020736694336,
|
| 60 |
+
-0.8163185119628906,
|
| 61 |
+
9.09945297241211,
|
| 62 |
+
2.696460723876953
|
| 63 |
+
],
|
| 64 |
+
"sft_episodes": 16,
|
| 65 |
+
"rl_episodes": 24,
|
| 66 |
+
"eval_episodes": 8,
|
| 67 |
+
"eval_records": [
|
| 68 |
+
{
|
| 69 |
+
"scenario": "demand_spike",
|
| 70 |
+
"level": 3,
|
| 71 |
+
"reward": 13.95076124828986,
|
| 72 |
+
"outage_count": 0,
|
| 73 |
+
"cascade_count": 0,
|
| 74 |
+
"completed_critical": 7,
|
| 75 |
+
"total_critical": 7,
|
| 76 |
+
"guardrail_violations": 2,
|
| 77 |
+
"invalid_actions": 0,
|
| 78 |
+
"cluster_health": 1.0
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"scenario": "cooling_failure",
|
| 82 |
+
"level": 4,
|
| 83 |
+
"reward": 10.213022214479953,
|
| 84 |
+
"outage_count": 3,
|
| 85 |
+
"cascade_count": 1,
|
| 86 |
+
"completed_critical": 4,
|
| 87 |
+
"total_critical": 4,
|
| 88 |
+
"guardrail_violations": 2,
|
| 89 |
+
"invalid_actions": 0,
|
| 90 |
+
"cluster_health": 0.7
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"scenario": "hidden_degradation",
|
| 94 |
+
"level": 5,
|
| 95 |
+
"reward": 12.012206310659073,
|
| 96 |
+
"outage_count": 2,
|
| 97 |
+
"cascade_count": 0,
|
| 98 |
+
"completed_critical": 2,
|
| 99 |
+
"total_critical": 2,
|
| 100 |
+
"guardrail_violations": 1,
|
| 101 |
+
"invalid_actions": 0,
|
| 102 |
+
"cluster_health": 0.8
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"scenario": "cascading_failure",
|
| 106 |
+
"level": 3,
|
| 107 |
+
"reward": 10.896465474005652,
|
| 108 |
+
"outage_count": 4,
|
| 109 |
+
"cascade_count": 1,
|
| 110 |
+
"completed_critical": 4,
|
| 111 |
+
"total_critical": 4,
|
| 112 |
+
"guardrail_violations": 3,
|
| 113 |
+
"invalid_actions": 0,
|
| 114 |
+
"cluster_health": 0.6
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"scenario": "energy_squeeze",
|
| 118 |
+
"level": 4,
|
| 119 |
+
"reward": 4.403711149748195,
|
| 120 |
+
"outage_count": 1,
|
| 121 |
+
"cascade_count": 0,
|
| 122 |
+
"completed_critical": 3,
|
| 123 |
+
"total_critical": 3,
|
| 124 |
+
"guardrail_violations": 2,
|
| 125 |
+
"invalid_actions": 0,
|
| 126 |
+
"cluster_health": 0.9
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"scenario": "vip_job_arrival",
|
| 130 |
+
"level": 5,
|
| 131 |
+
"reward": 12.667476956657236,
|
| 132 |
+
"outage_count": 1,
|
| 133 |
+
"cascade_count": 0,
|
| 134 |
+
"completed_critical": 6,
|
| 135 |
+
"total_critical": 6,
|
| 136 |
+
"guardrail_violations": 5,
|
| 137 |
+
"invalid_actions": 0,
|
| 138 |
+
"cluster_health": 0.9
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"scenario": "triple_crisis",
|
| 142 |
+
"level": 3,
|
| 143 |
+
"reward": 7.574227174276577,
|
| 144 |
+
"outage_count": 6,
|
| 145 |
+
"cascade_count": 4,
|
| 146 |
+
"completed_critical": 8,
|
| 147 |
+
"total_critical": 9,
|
| 148 |
+
"guardrail_violations": 6,
|
| 149 |
+
"invalid_actions": 0,
|
| 150 |
+
"cluster_health": 0.4
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"scenario": "chaos_arena",
|
| 154 |
+
"level": 4,
|
| 155 |
+
"reward": 11.973056694274142,
|
| 156 |
+
"outage_count": 3,
|
| 157 |
+
"cascade_count": 0,
|
| 158 |
+
"completed_critical": 4,
|
| 159 |
+
"total_critical": 4,
|
| 160 |
+
"guardrail_violations": 4,
|
| 161 |
+
"invalid_actions": 0,
|
| 162 |
+
"cluster_health": 0.7
|
| 163 |
+
}
|
| 164 |
+
],
|
| 165 |
+
"eval_mean_reward": 10.461365902798835,
|
| 166 |
+
"quick_mode": true
|
| 167 |
+
}
|