github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-07 03:00:26 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: temperature 0 llama3 benchmark (#5806)

Browse Source
This commit is contained in:
wozeparrot
2024-07-30 12:05:36 -07:00
committed by GitHub
parent 03d866b84f
commit eebb1b9922
2 changed files with 18 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.github/workflows/benchmark.yml vendored
View File

@@ -183,11 +183,11 @@ jobs:
- name: Run LLaMA 7B on 6 GPUs
run: NV=1 python3 examples/llama.py --gen 1 --size 7B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_six_gpu.txt
- name: Run LLaMA-3 8B BEAM
run: NV=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 python3 examples/llama3.py --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_beam.txt
run: NV=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 python3 examples/llama3.py --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_beam.txt
- name: Run LLaMA-3 8B on 4 GPUs
run: NV=1 python3 examples/llama3.py --shard 4 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_four_gpu.txt
run: NV=1 python3 examples/llama3.py --shard 4 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_four_gpu.txt
- name: Run LLaMA-3 8B on 6 GPUs
run: NV=1 python3 examples/llama3.py --shard 6 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_six_gpu.txt
run: NV=1 python3 examples/llama3.py --shard 6 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_six_gpu.txt
# - name: Run LLaMA-2 70B
# run: CUDA=1 python3 examples/llama.py --gen 2 --size 70B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_2_70B.txt
- name: Run Mixtral 8x7B
@@ -349,11 +349,11 @@ jobs:
- name: Run LLaMA 7B on 6 GPUs
run: AMD=1 python3 examples/llama.py --gen 1 --size 7B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_six_gpu.txt
- name: Run LLaMA-3 8B BEAM
run: AMD=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 python3 examples/llama3.py --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_beam.txt
run: AMD=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 python3 examples/llama3.py --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_beam.txt
- name: Run LLaMA-3 8B on 4 GPUs
run: AMD=1 python3 examples/llama3.py --shard 4 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_four_gpu.txt
run: AMD=1 python3 examples/llama3.py --shard 4 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_four_gpu.txt
- name: Run LLaMA-3 8B on 6 GPUs
run: AMD=1 python3 examples/llama3.py --shard 6 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark | tee llama3_six_gpu.txt
run: AMD=1 python3 examples/llama3.py --shard 6 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_six_gpu.txt
- name: Run LLaMA-2 70B
run: AMD=1 python3 examples/llama.py --gen 2 --size 70B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_2_70B.txt
- name: Run Mixtral 8x7B