Llama 3 models trained on the tulu dataset, following https://arxiv.org/abs/2311.10702 (tulu 2) and https://arxiv.org/abs/2406.09279 (tulu 2.5).
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
new activity
about 14 hours ago
allenai/tulu-3-sft-mixture:tulu_v3.9_open_math_2_gsm8k_50k_0 / tulu-3-sft-personas-math-grade
Organizations
Collections
5
models
15
hamishivi/llama-3.1-tulu-2-8b-uf-mean-rm-resized-tokenizer
Updated
•
2
hamishivi/secret_model_2
Updated
•
35
hamishivi/OLMo-1B-0724-SFT-hf
Text Generation
•
Updated
•
7
hamishivi/OLMo-1B-0724-Instruct-hf
Text Generation
•
Updated
•
15
hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm-value
Token Classification
•
Updated
•
17
hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm
Text Generation
•
Updated
•
24
hamishivi/tulu-v2.5-7b-uf-rm
Text Classification
•
Updated
•
21
hamishivi/hypertask_T0_11B
Text2Text Generation
•
Updated
•
7
hamishivi/hypertask_T0_3B
Text2Text Generation
•
Updated
•
10
hamishivi/T0_3Bp
Text2Text Generation
•
Updated
•
19
datasets
10
hamishivi/squad_eval_diffulm
Viewer
•
Updated
•
10.6k
•
48
hamishivi/gsm8k_eval_diffulm
Viewer
•
Updated
•
1.32k
•
21
hamishivi/alpaca_eval_diffulm
Viewer
•
Updated
•
805
•
55
hamishivi/tulu_3.9_bal_rand_939k
Viewer
•
Updated
•
939k
•
12
hamishivi/gsm8k-symbolic
Viewer
•
Updated
•
385k
•
15
hamishivi/alpaca_eval_test_mmft
Viewer
•
Updated
•
805
•
153
hamishivi/tulu_mix_store
Viewer
•
Updated
•
7.54k
•
93
•
1
hamishivi/gsm8k
Viewer
•
Updated
•
7.47k
•
8
hamishivi/test_upload2
Preview
•
Updated
•
8
hamishivi/alpaca-farm-davinci-003-2048-token
Viewer
•
Updated
•
805
•
88
•
2