Instructions to use safffrron/25M2111-Week02-Track2-20-Submission01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use safffrron/25M2111-Week02-Track2-20-Submission01 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="safffrron/25M2111-Week02-Track2-20-Submission01")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("safffrron/25M2111-Week02-Track2-20-Submission01", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use safffrron/25M2111-Week02-Track2-20-Submission01 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "safffrron/25M2111-Week02-Track2-20-Submission01" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "safffrron/25M2111-Week02-Track2-20-Submission01", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/safffrron/25M2111-Week02-Track2-20-Submission01
- SGLang
How to use safffrron/25M2111-Week02-Track2-20-Submission01 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "safffrron/25M2111-Week02-Track2-20-Submission01" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "safffrron/25M2111-Week02-Track2-20-Submission01", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "safffrron/25M2111-Week02-Track2-20-Submission01" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "safffrron/25M2111-Week02-Track2-20-Submission01", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use safffrron/25M2111-Week02-Track2-20-Submission01 with Docker Model Runner:
docker model run hf.co/safffrron/25M2111-Week02-Track2-20-Submission01
Upload folder using huggingface_hub
Browse files
results/artifact-manifest.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema": "eaimath-submission-manifest-v2",
|
| 3 |
+
"enrollment": "25M2111",
|
| 4 |
+
"week": 2,
|
| 5 |
+
"track": 2,
|
| 6 |
+
"compression_target": 20,
|
| 7 |
+
"github_url": "https://github.com/safffrron/CS6013/tree/main/25M2111/Week02/Track2_20/Submission01",
|
| 8 |
+
"hf_url": "https://huggingface.co/safffrron/25M2111-Week02-Track2-20-Submission01",
|
| 9 |
+
"selection_commit": "4016f28765aff8bd7ce0d14222f83020476ce543",
|
| 10 |
+
"artifact_location": "Hugging Face repository; model binaries are not stored in Git",
|
| 11 |
+
"candidate": "b_r18_jsd",
|
| 12 |
+
"representation": "packed base plus retained IDs plus rank-8 adapter",
|
| 13 |
+
"charged_bytes": 1657231034,
|
| 14 |
+
"ceiling_bytes": 1682400000,
|
| 15 |
+
"base_artifact": "week02_20_base.ptz",
|
| 16 |
+
"base_sha256": "2b63ba3af765f54baf78536c0b46b4a8ccf9f6ac2b294001b7653e9069410091",
|
| 17 |
+
"keep_ids": "week02_20_keep_ids.json",
|
| 18 |
+
"keep_ids_sha256": "3b4ad01e01b0f72d05c92ae00c4457adc2a85b1d80749837b980039cf107a9a2",
|
| 19 |
+
"adapter": "adapter/"
|
| 20 |
+
}
|
results/round23-matched-evidence.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"round": 23,
|
| 3 |
+
"status": "complete",
|
| 4 |
+
"completed_stages": 28,
|
| 5 |
+
"elapsed_seconds": 15000,
|
| 6 |
+
"settings": {"max_new_tokens": 32768, "repetition_penalty": 1.2},
|
| 7 |
+
"precommitted_selection": {"B": "b_r18_jsd", "C": "c_w01_block64"},
|
| 8 |
+
"candidates": {
|
| 9 |
+
"b_r18_jsd": {"band":"B","bytes":1657231034,"gate_accuracy":0.880,"checkpoint_accuracy":0.871,"checkpoint_parse":0.957,"checkpoint_truncation":0.055,"checkpoint_mean_tokens":7705,"checkpoint_accuracy_when_finished":0.921,"holdout_accuracy":0.444,"holdout_parse":0.794,"holdout_truncation":0.270,"holdout_mean_tokens":21333,"holdout_accuracy_when_finished":0.609},
|
| 10 |
+
"b_r13_base": {"band":"B","bytes":1626680806,"gate_accuracy":0.910,"checkpoint_accuracy":0.850,"checkpoint_parse":0.948,"checkpoint_truncation":0.068,"checkpoint_mean_tokens":7990,"checkpoint_accuracy_when_finished":0.910,"holdout_accuracy":0.460,"holdout_parse":0.778,"holdout_truncation":0.238,"holdout_mean_tokens":20490,"holdout_accuracy_when_finished":0.604},
|
| 11 |
+
"c_r18_tail": {"band":"C","bytes":3359426040,"gate_accuracy":0.940,"checkpoint_accuracy":0.918,"checkpoint_parse":0.943,"checkpoint_truncation":0.064,"checkpoint_mean_tokens":7849,"checkpoint_accuracy_when_finished":0.975,"holdout_accuracy":0.603,"holdout_parse":0.698,"holdout_truncation":0.302,"holdout_mean_tokens":21773,"holdout_accuracy_when_finished":0.864},
|
| 12 |
+
"c_r16_raw": {"band":"C","bytes":3350409198,"gate_accuracy":0.970,"checkpoint_accuracy":0.918,"checkpoint_parse":0.946,"checkpoint_truncation":0.054,"checkpoint_mean_tokens":7656,"checkpoint_accuracy_when_finished":0.970,"holdout_accuracy":0.524,"holdout_parse":0.651,"holdout_truncation":0.349,"holdout_mean_tokens":22188,"holdout_accuracy_when_finished":0.805},
|
| 13 |
+
"c_w01_block64": {"band":"C","bytes":3350387629,"gate_accuracy":0.960,"checkpoint_accuracy":0.929,"checkpoint_parse":0.957,"checkpoint_truncation":0.046,"checkpoint_mean_tokens":7585,"checkpoint_accuracy_when_finished":0.974,"holdout_accuracy":0.492,"holdout_parse":0.540,"holdout_truncation":0.460,"holdout_mean_tokens":22375,"holdout_accuracy_when_finished":0.912}
|
| 14 |
+
},
|
| 15 |
+
"paired": {
|
| 16 |
+
"b_r18_vs_r13_checkpoint": {"selected_only":33,"candidate_only":21,"p":0.133674},
|
| 17 |
+
"b_r18_vs_r13_holdout": {"selected_only":9,"candidate_only":10,"p":1.0},
|
| 18 |
+
"c_w01_vs_r18_checkpoint": {"selected_only":22,"candidate_only":16,"p":0.417692},
|
| 19 |
+
"c_w01_vs_r18_holdout": {"selected_only":1,"candidate_only":8,"p":0.039062},
|
| 20 |
+
"c_w01_vs_r16_checkpoint": {"selected_only":21,"candidate_only":15,"p":0.405032},
|
| 21 |
+
"c_w01_vs_r16_holdout": {"selected_only":6,"candidate_only":8,"p":0.790527}
|
| 22 |
+
},
|
| 23 |
+
"diagnostics": {"critical_errors":0,"notes":"reported diagnostic matches are serialized audit fields named repack_error/scale_storage_error; no failed stages"},
|
| 24 |
+
"decision": "B precommit is stable. C checkpoint precommit and holdout disagree; packaging awaits an explicit protocol-versus-robustness choice."
|
| 25 |
+
}
|
results/week02-results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"candidate": "b_r18_jsd",
|
| 3 |
+
"settings": {"max_new_tokens": 32768, "repetition_penalty": 1.2},
|
| 4 |
+
"gate": {"n": 100, "accuracy": 0.880},
|
| 5 |
+
"checkpoint": {"n": 560, "accuracy": 0.871, "parse_rate": 0.957, "truncation_rate": 0.055, "accuracy_when_finished": 0.921},
|
| 6 |
+
"holdout": {"n": 63, "accuracy": 0.444, "parse_rate": 0.794, "truncation_rate": 0.270, "accuracy_when_finished": 0.609}
|
| 7 |
+
}
|