developer_uid: zonemercy
submission_id: qwen-qwen3-4b-instruct-2507_v8
model_name: qwen-qwen3-4b-instruct-2507_v7
model_group: Qwen/Qwen3-4B-Instruct-2
status: inactive
timestamp: 2026-02-15T18:47:28+00:00
num_battles: 10756
num_wins: 3568
celo_rating: 1176.13
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: Qwen/Qwen3-4B-Instruct-2507
model_architecture: Qwen3ForCausalLM
model_num_parameters: 4057520640.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
display_name: qwen-qwen3-4b-instruct-2507_v7
is_internal_developer: True
language_model: Qwen/Qwen3-4B-Instruct-2507
model_size: 4B
ranking_group: single
us_pacific_date: 2026-02-15
win_ratio: 0.33172182967645963
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': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {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
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name qwen-qwen3-4b-instruct-2507-v8-uploader
Waiting for job on qwen-qwen3-4b-instruct-2507-v8-uploader to finish
qwen-qwen3-4b-instruct-2507-v8-uploader: Using quantization_mode: none
qwen-qwen3-4b-instruct-2507-v8-uploader: Downloading snapshot of Qwen/Qwen3-4B-Instruct-2507...
qwen-qwen3-4b-instruct-2507-v8-uploader: Downloaded in 3.853s
qwen-qwen3-4b-instruct-2507-v8-uploader: Processed model Qwen/Qwen3-4B-Instruct-2507 in 6.980s
qwen-qwen3-4b-instruct-2507-v8-uploader: creating bucket guanaco-vllm-models
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-4b-instruct-2507-v8-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
qwen-qwen3-4b-instruct-2507-v8-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-4b-instruct-2507-v8-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-4b-instruct-2507-v8-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-4b-instruct-2507-v8-uploader:   if re.search("-\.", bucket, re.UNICODE):
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-4b-instruct-2507-v8-uploader:   if re.search("\.\.", bucket, re.UNICODE):
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
qwen-qwen3-4b-instruct-2507-v8-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
qwen-qwen3-4b-instruct-2507-v8-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
qwen-qwen3-4b-instruct-2507-v8-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/merges.txt
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/tokenizer.json
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/vocab.json
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/model-00003-of-00003.safetensors s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/model-00003-of-00003.safetensors
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/model-00001-of-00003.safetensors s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/model-00001-of-00003.safetensors
qwen-qwen3-4b-instruct-2507-v8-uploader: cp /dev/shm/model_output/model-00002-of-00003.safetensors s3://guanaco-vllm-models/qwen-qwen3-4b-instruct-2507-v8/default/model-00002-of-00003.safetensors
Job qwen-qwen3-4b-instruct-2507-v8-uploader completed after 93.0s with status: succeeded
Stopping job with name qwen-qwen3-4b-instruct-2507-v8-uploader
Pipeline stage VLLMUploader completed in 93.90s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service qwen-qwen3-4b-instruct-2507-v8
Waiting for inference service qwen-qwen3-4b-instruct-2507-v8 to be ready
Failed to get response for submission chaiml-mistral-24b-2048_54327_v6: ('http://chaiml-mistral-24b-2048-54327-v6-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048-_2678_v3: ('http://chaiml-mistral-24b-2048-2678-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service qwen-qwen3-4b-instruct-2507-v8 ready after 161.1451380252838s
Pipeline stage VLLMDeployer completed in 161.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3484480381011963s
Received healthy response to inference request in 1.4309635162353516s
Received healthy response to inference request in 1.1424765586853027s
Received healthy response to inference request in 1.2301361560821533s
Received healthy response to inference request in 1.1461963653564453s
Received healthy response to inference request in 1.038093090057373s
Received healthy response to inference request in 1.360469102859497s
Received healthy response to inference request in 1.3209667205810547s
Received healthy response to inference request in 1.17191743850708s
Received healthy response to inference request in 1.321258544921875s
Received healthy response to inference request in 1.1061909198760986s
Received healthy response to inference request in 1.9929566383361816s
Received healthy response to inference request in 1.141437292098999s
Received healthy response to inference request in 1.2937655448913574s
Received healthy response to inference request in 1.4753572940826416s
Received healthy response to inference request in 1.2847621440887451s
Received healthy response to inference request in 1.3070228099822998s
Received healthy response to inference request in 1.0510551929473877s
Received healthy response to inference request in 1.2157244682312012s
Received healthy response to inference request in 1.27378511428833s
Received healthy response to inference request in 1.794215202331543s
Received healthy response to inference request in 1.2454051971435547s
Received healthy response to inference request in 1.4273643493652344s
Received healthy response to inference request in 1.3227355480194092s
Received healthy response to inference request in 1.2359364032745361s
Received healthy response to inference request in 1.63181471824646s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.4743664264678955s
Received healthy response to inference request in 1.2795464992523193s
Received healthy response to inference request in 1.0459537506103516s
Received healthy response to inference request in 1.339838981628418s
30 requests
0 failed requests
5th percentile: 1.048249399662018
10th percentile: 1.1006773471832276
20th percentile: 1.1454524040222167
30th percentile: 1.2258126497268678
40th percentile: 1.26243314743042
50th percentile: 1.2892638444900513
60th percentile: 1.3210834503173827
70th percentile: 1.3424216985702515
80th percentile: 1.4280841827392579
90th percentile: 1.4910030364990237
95th percentile: 1.721134984493255
99th percentile: 1.9353216218948366
mean time: 1.3150053342183432
Pipeline stage StressChecker completed in 42.90s
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 0.61s
Shutdown handler de-registered
qwen-qwen3-4b-instruct-2507_v8 status is now deployed due to DeploymentManager action
qwen-qwen3-4b-instruct-2507_v8 status is now inactive due to auto deactivation removed underperforming models