GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
simonts
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
simonts
Model Tree
mistralai/Mistral-7B-Instruct-v0.2
Input Modalities
Output Modalities
Supported Functionality
Local source path used for this release:
text
/home/trx/rlm-code/ICLR26/output/mistralai/Mistral-7B-Instruct-v0.2-sft_newdataset_fuxian_finalExpected uploaded files:
config.jsongeneration_config.jsonmodel-00001-of-00003.safetensorsmodel-00002-of-00003.safetensorsmodel-00003-of-00003.safetensorsmodel.safetensors.index.jsontokenizer.jsontokenizer.modeltokenizer_config.jsonspecial_tokens_map.jsonchat_template.jinjaThe closest local result row found during release preparation is:
| Local result | FB Bench | FLASK | MT Bench | Vicuna | Avg | Paper row |
|---|---|---|---|---|---|---|
Mistral-7B-Instruct-v0.2-sft_epoch2 | 0.7822 | 0.3726 | 0.2908 | 0.3429 | 0.4471 | CE avg 0.4494 |
This is close to the paper CE average, but it is not a complete five-seed reproduction artifact.
mistralai/Mistral-7B-Instruct-v0.2 also lists Apache-2.0./home/trx/rlm-code/genre2_main_experiments.