developer_uid: zonemercy
submission_id: chaiml-pony-d3b-mv1-win_84391_v8
model_name: chaiml-pony-d3b-mv1-win_84391_v8
model_group: ChaiML/pony-d3b-mv1-wina
status: deployed
timestamp: 2026-03-28T17:24:55+00:00
num_battles: 5772
num_wins: 2972
celo_rating: 1304.63
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8
model_architecture: Qwen3_5MoeForConditionalGeneration
model_num_parameters: 33753909248.0
best_of: 16
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: chaiml-pony-d3b-mv1-win_84391_v8
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8
model_size: 34B
ranking_group: single
us_pacific_date: 2026-03-28
win_ratio: 0.5148995148995149
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.8, 'frequency_penalty': 0.0, 'stopping_words': ['<|assistant|>', '<|user|>', '</s>', '####', '<|im_end|>'], 'max_input_tokens': 2048, 'best_of': 16, 'max_output_tokens': 80}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s persona: {memory}<|im_end|>\n", 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-pony-d3b-mv1-win-84391-v8-uploader
Waiting for job on chaiml-pony-d3b-mv1-win-84391-v8-uploader to finish
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Using quantization_mode: fp8
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Checking if ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8-FP8 already exists in ChaiML
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Downloading snapshot of ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8-FP8...
2026-03-28T17:15:05.764613+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Downloaded in 37.766s
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Processed model ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8 in 40.564s
chaiml-pony-d3b-mv1-win-84391-v8-uploader: creating bucket guanaco-vllm-models
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v8-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-pony-d3b-mv1-win-84391-v8-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-pony-d3b-mv1-win-84391-v8-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-pony-d3b-mv1-win-84391-v8-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/.gitattributes
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/tokenizer_config.json
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/config.json
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/recipe.yaml
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/generation_config.json
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/chat_template.jinja
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/tokenizer.json
2026-03-28T17:16:05.851647+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
chaiml-pony-d3b-mv1-win-84391-v8-uploader: cp /dev/shm/model_output/model.safetensors s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v8/default/model.safetensors
Job chaiml-pony-d3b-mv1-win-84391-v8-uploader completed after 153.52s with status: succeeded
Stopping job with name chaiml-pony-d3b-mv1-win-84391-v8-uploader
Pipeline stage VLLMUploader completed in 153.95s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.10s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.78s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-pony-d3b-mv1-win-84391-v8
Waiting for inference service chaiml-pony-d3b-mv1-win-84391-v8 to be ready
2026-03-28T17:17:05.948734+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
2026-03-28T17:18:06.044693+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
2026-03-28T17:19:06.140831+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
2026-03-28T17:20:06.236995+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
Inference service chaiml-pony-d3b-mv1-win-84391-v8 ready after 230.31610894203186s
Pipeline stage VLLMDeployer completed in 230.97s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:21:06.334401+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:22:06.432249+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 5.776867389678955s
Received healthy response to inference request in 5.992809295654297s
Received healthy response to inference request in 2.1716115474700928s
Received healthy response to inference request in 5.726691484451294s
Received healthy response to inference request in 2.721240997314453s
Received healthy response to inference request in 2.109314441680908s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 5.834428071975708s
2026-03-28T17:23:06.523640+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
Received healthy response to inference request in 2.7975664138793945s
Received healthy response to inference request in 2.1647188663482666s
Received healthy response to inference request in 2.651421070098877s
Received healthy response to inference request in 2.135556697845459s
Received healthy response to inference request in 2.0883326530456543s
Received healthy response to inference request in 2.1545538902282715s
Received healthy response to inference request in 2.33734393119812s
Received healthy response to inference request in 2.1331534385681152s
Received healthy response to inference request in 2.1069350242614746s
Received healthy response to inference request in 2.185776472091675s
Received healthy response to inference request in 2.3433351516723633s
Received healthy response to inference request in 2.6356201171875s
Received healthy response to inference request in 2.1211369037628174s
Received healthy response to inference request in 2.1061949729919434s
Received healthy response to inference request in 2.17634654045105s
Received healthy response to inference request in 2.2127127647399902s
Received healthy response to inference request in 2.1424739360809326s
30 requests
6 failed requests
5th percentile: 2.1065279960632326
10th percentile: 2.109076499938965
20th percentile: 2.1350760459899902
30th percentile: 2.161669373512268
40th percentile: 2.1820044994354246
50th percentile: 2.3403395414352417
60th percentile: 2.6793490409851075
70th percentile: 5.741744256019592
80th percentile: 8.819292879104655
90th percentile: 20.134274625778197
95th percentile: 20.13629459142685
99th percentile: 20.14028114557266
mean time: 6.320883107185364
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1128089427948s
Received healthy response to inference request in 2.1349213123321533s
Received healthy response to inference request in 2.0914196968078613s
Received healthy response to inference request in 2.2237725257873535s
Received healthy response to inference request in 2.056567668914795s
Received healthy response to inference request in 2.110949754714966s
Received healthy response to inference request in 2.1802523136138916s
Received healthy response to inference request in 2.3171510696411133s
Received healthy response to inference request in 2.148214101791382s
2026-03-28T17:24:06.866629+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v8
Received healthy response to inference request in 2.158824920654297s
Received healthy response to inference request in 2.1193017959594727s
Received healthy response to inference request in 2.0963592529296875s
Received healthy response to inference request in 2.2052769660949707s
Received healthy response to inference request in 2.1325085163116455s
Received healthy response to inference request in 2.1295976638793945s
Received healthy response to inference request in 2.1208584308624268s
Received healthy response to inference request in 2.1306400299072266s
Received healthy response to inference request in 2.1463310718536377s
Received healthy response to inference request in 2.1610076427459717s
Received healthy response to inference request in 2.2307543754577637s
Received healthy response to inference request in 2.117044687271118s
Received healthy response to inference request in 2.0818607807159424s
Received healthy response to inference request in 2.1450774669647217s
Received healthy response to inference request in 2.134671688079834s
Received healthy response to inference request in 2.1241507530212402s
Received healthy response to inference request in 2.1728436946868896s
Received healthy response to inference request in 2.160059928894043s
Received healthy response to inference request in 2.250117063522339s
Received healthy response to inference request in 2.178576946258545s
Received healthy response to inference request in 2.112595558166504s
30 requests
0 failed requests
5th percentile: 2.086162292957306
10th percentile: 2.0958652973175047
20th percentile: 2.1127662658691406
30th percentile: 2.1203914403915407
40th percentile: 2.1302230834960936
50th percentile: 2.1347965002059937
60th percentile: 2.147084283828735
70th percentile: 2.1603442430496216
80th percentile: 2.1789120197296143
90th percentile: 2.2244707107543946
95th percentile: 2.24140385389328
99th percentile: 2.297711207866669
mean time: 2.149483887354533
Pipeline stage StressChecker completed in 259.61s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.32s
Shutdown handler de-registered
chaiml-pony-d3b-mv1-win_84391_v8 status is now deployed due to DeploymentManager action