chaiml-pony-v1-q32b-2k

developer_uid: richhx

submission_id: chaiml-pony-v1-q32b-2k_v4

model_name: chaiml-pony-v1-q32b-2k_v3

model_group: ChaiML/pony-v1-q32b-2k

status: torndown

timestamp: 2026-03-01T16:41:59+00:00

num_battles: 12926

num_wins: 6537

celo_rating: 1303.67

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/pony-v1-q32b-2k

model_architecture: Qwen3ForCausalLM

model_num_parameters: 30497182720.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 80

reward_model: default

display_name: chaiml-pony-v1-q32b-2k_v3

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/pony-v1-q32b-2k

model_size: 30B

ranking_group: single

us_pacific_date: 2026-02-26

win_ratio: 0.5057248955593378

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|user|>', '</s>', '####', '<|im_end|>', '<|assistant|>'], 'max_input_tokens': 2048, 'best_of': 8, '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-pony-v1-q32b-2k-v4-uploader
Waiting for job on chaiml-pony-v1-q32b-2k-v4-uploader to finish
chaiml-pony-v1-q32b-2k-v4-uploader: Using quantization_mode: none
chaiml-pony-v1-q32b-2k-v4-uploader: Downloading snapshot of ChaiML/pony-v1-q32b-2k...
chaiml-pony-v1-q32b-2k-v4-uploader: Downloaded in 27.477s
chaiml-pony-v1-q32b-2k-v4-uploader: Processed model ChaiML/pony-v1-q32b-2k in 52.163s
chaiml-pony-v1-q32b-2k-v4-uploader: creating bucket guanaco-vllm-models
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q32b-2k-v4-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-pony-v1-q32b-2k-v4-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q32b-2k-v4-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q32b-2k-v4-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q32b-2k-v4-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q32b-2k-v4-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-pony-v1-q32b-2k-v4-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-pony-v1-q32b-2k-v4-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-pony-v1-q32b-2k-v4-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-pony-v1-q32b-2k-v4-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-pony-v1-q32b-2k-v4-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/vocab.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/tokenizer_config.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/trainer_state.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/trainer_state.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/generation_config.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/chat_template.jinja
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/added_tokens.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/merges.txt
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/config.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/tokenizer.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/.gitattributes
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/training_args.bin s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/training_args.bin
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/args.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/args.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/special_tokens_map.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model.safetensors.index.json
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00014-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00014-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00011-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00011-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00002-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00002-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00012-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00012-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00001-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00001-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00005-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00005-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00010-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00010-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00006-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00006-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00004-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00004-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00009-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00009-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00008-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00008-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00013-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00013-of-00014.safetensors
chaiml-pony-v1-q32b-2k-v4-uploader: cp /dev/shm/model_output/model-00007-of-00014.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q32b-2k-v4/default/model-00007-of-00014.safetensors
Job chaiml-pony-v1-q32b-2k-v4-uploader completed after 84.52s with status: succeeded
Stopping job with name chaiml-pony-v1-q32b-2k-v4-uploader
Pipeline stage VLLMUploader completed in 85.37s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-pony-v1-q32b-2k-v4
Waiting for inference service chaiml-pony-v1-q32b-2k-v4 to be ready
Inference service chaiml-pony-v1-q32b-2k-v4 ready after 498.84127926826477s
Pipeline stage VLLMDeployer completed in 499.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.849248170852661s
Received healthy response to inference request in 3.9593470096588135s
Received healthy response to inference request in 3.9298009872436523s
Received healthy response to inference request in 3.9540367126464844s
Received healthy response to inference request in 3.8043477535247803s
Received healthy response to inference request in 3.7685773372650146s
Received healthy response to inference request in 3.841996669769287s
Received healthy response to inference request in 3.8047893047332764s
Received healthy response to inference request in 4.2623984813690186s
Received healthy response to inference request in 3.822563886642456s
Received healthy response to inference request in 4.127885103225708s
Received healthy response to inference request in 3.9229445457458496s
Received healthy response to inference request in 3.9005837440490723s
Received healthy response to inference request in 4.156326770782471s
Received healthy response to inference request in 3.7990407943725586s
Received healthy response to inference request in 3.8935539722442627s
Received healthy response to inference request in 3.985506534576416s
Received healthy response to inference request in 3.8563528060913086s
Received healthy response to inference request in 4.185388565063477s
Received healthy response to inference request in 4.217410564422607s
Received healthy response to inference request in 4.179980516433716s
Received healthy response to inference request in 3.812246322631836s
Received healthy response to inference request in 4.278802156448364s
Received healthy response to inference request in 3.911980628967285s
Received healthy response to inference request in 3.7983317375183105s
Received healthy response to inference request in 3.9196479320526123s
Received healthy response to inference request in 3.80790638923645s
Received healthy response to inference request in 3.8627381324768066s
Received healthy response to inference request in 4.009437561035156s
Received healthy response to inference request in 3.796430826187134s
30 requests
0 failed requests
5th percentile: 3.7972862362861632
10th percentile: 3.7989698886871337
20th percentile: 3.8072829723358153
30th percentile: 3.836166834831238
40th percentile: 3.8601840019226072
50th percentile: 3.9062821865081787
60th percentile: 3.9256871223449705
70th percentile: 3.967194867134094
80th percentile: 4.133573436737061
90th percentile: 4.18859076499939
95th percentile: 4.242153918743133
99th percentile: 4.274045090675354
mean time: 3.947320063908895
Pipeline stage StressChecker completed in 135.18s
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 0.66s
Shutdown handler de-registered
chaiml-pony-v1-q32b-2k_v4 status is now deployed due to DeploymentManager action
chaiml-pony-v1-q32b-2k_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-pony-v1-q32b-2k_v4 status is now torndown due to DeploymentManager action