-
calm_q3_32b_r16_a32_lr2e-5_e15
This model is Qwen3-32b-Instruct fine-tuned on ~13k Climsight data which are pairs of prompts/completions extracted from climsight pipeline. Below are all the technical specs of the fine-tuning process along with the evaluation used.
tools11 Pulls 1 Tag Updated 2 weeks ago
-
calm_mistral_r64_a128_lr1e-4_e6
This model is Mistral-small-24b-Instruct-2501 fine-tuned on ~13k Climsight data which are pairs of prompts/completions extracted from climsight pipeline. Below are all the technical specs of the fine-tuning process along with the evaluation used.
10 Pulls 1 Tag Updated 3 weeks ago
-
climsight-calm_ft_Q3_13k
This model is Qwen4b-Instruct-2507 fine-tuned on ~13k Climsight data which are pairs of prompts/completions extracted from climsight pipeline. Below are all the technical specs of the fine-tuning process along with the evaluation used.
7 Pulls 1 Tag Updated 3 months ago