chaiml-02f4-69d4-linear-w01

developer_uid: chai_backend_admin

submission_id: chaiml-02f4-69d4-linear-w01_v60

model_name: chaiml-02f4-69d4-linear-w01_v60

model_group: ChaiML/02f4-69d4-linear-

status: inactive

timestamp: 2026-02-17T17:44:36+00:00

num_battles: 1685

num_wins: 849

celo_rating: 9865.21

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/02f4-69d4-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: chaiml-llama31-mer-v2-_44570_v85

display_name: chaiml-02f4-69d4-linear-w01_v60

ineligible_reason: model is not deployable

is_internal_developer: True

language_model: ChaiML/02f4-69d4-linear-w01

model_size: 24B

ranking_group: single

us_pacific_date: 2026-02-17

win_ratio: 0.5038575667655787

generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', '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
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-02f4-69d4-linear-w01-v60-uploader
Waiting for job on chaiml-02f4-69d4-linear-w01-v60-uploader to finish
chaiml-02f4-69d4-linear-w01-v60-uploader: Using quantization_mode: fp8
chaiml-02f4-69d4-linear-w01-v60-uploader: Checking if ChaiML/02f4-69d4-linear-w01-FP8 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v60-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-02f4-69d4-linear-w01-v60-uploader: Downloading snapshot of ChaiML/02f4-69d4-linear-w01-FP8...
chaiml-02f4-69d4-linear-w01-v60-uploader: Downloaded in 12.781s
chaiml-02f4-69d4-linear-w01-v60-uploader: Processed model ChaiML/02f4-69d4-linear-w01 in 16.295s
chaiml-02f4-69d4-linear-w01-v60-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-02f4-69d4-linear-w01-v60-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model.safetensors.index.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/recipe.yaml
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/.gitattributes
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/config.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/tokenizer.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/generation_config.json
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00006-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00006-of-00006.safetensors
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00005-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00005-of-00006.safetensors
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00002-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00002-of-00006.safetensors
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00001-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00001-of-00006.safetensors
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00003-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00003-of-00006.safetensors
chaiml-02f4-69d4-linear-w01-v60-uploader: cp /dev/shm/model_output/model-00004-of-00006.safetensors s3://guanaco-vllm-models/chaiml-02f4-69d4-linear-w01-v60/default/model-00004-of-00006.safetensors
Job chaiml-02f4-69d4-linear-w01-v60-uploader completed after 85.87s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v60-uploader
Pipeline stage VLLMUploader completed in 87.10s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-02f4-69d4-linear-w01-v60
Waiting for inference service chaiml-02f4-69d4-linear-w01-v60 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v60 ready after 162.3330156803131s
Pipeline stage VLLMDeployer completed in 163.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7894670963287354s
Received healthy response to inference request in 1.6565289497375488s
Received healthy response to inference request in 1.4832103252410889s
Received healthy response to inference request in 1.9293162822723389s
Received healthy response to inference request in 1.7921080589294434s
Received healthy response to inference request in 1.8144383430480957s
Received healthy response to inference request in 1.5971481800079346s
Received healthy response to inference request in 1.5539729595184326s
Received healthy response to inference request in 1.7294273376464844s
Received healthy response to inference request in 1.6766672134399414s
Received healthy response to inference request in 1.9069771766662598s
Received healthy response to inference request in 1.9406230449676514s
Received healthy response to inference request in 1.7599127292633057s
Received healthy response to inference request in 1.5345139503479004s
Received healthy response to inference request in 1.6689121723175049s
Received healthy response to inference request in 1.8529586791992188s
Received healthy response to inference request in 1.7045471668243408s
Received healthy response to inference request in 1.56587553024292s
Received healthy response to inference request in 1.5609886646270752s
Received healthy response to inference request in 2.099750518798828s
Received healthy response to inference request in 1.6137194633483887s
Received healthy response to inference request in 1.6377549171447754s
Received healthy response to inference request in 1.9592618942260742s
Received healthy response to inference request in 1.6076395511627197s
Received healthy response to inference request in 1.5574538707733154s
Received healthy response to inference request in 1.6628525257110596s
Received healthy response to inference request in 1.5798120498657227s
Received healthy response to inference request in 1.5856714248657227s
Received healthy response to inference request in 1.8226227760314941s
Received healthy response to inference request in 1.628429651260376s
30 requests
0 failed requests
5th percentile: 1.54327050447464
10th percentile: 1.5571057796478271
20th percentile: 1.5770247459411622
30th percentile: 1.6044921398162841
40th percentile: 1.6340248107910156
50th percentile: 1.6658823490142822
60th percentile: 1.7144992351531982
70th percentile: 1.7902593851089477
80th percentile: 1.8286899566650392
90th percentile: 1.9304469585418702
95th percentile: 1.9508744120597838
99th percentile: 2.0590088176727295
mean time: 1.7090854167938232
Pipeline stage StressChecker completed in 62.81s
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 2.28s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v60 status is now deployed due to DeploymentManager action