-
Notifications
You must be signed in to change notification settings - Fork 10.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
make rms_norm_eps a parameter #2374
Conversation
I think this is good enough until we update the model files. |
Perplexity with $ ./perplexity -m models/Llama-2-7B-GGML/llama-2-7b.ggmlv3.q5_K_M.bin -f wikitext-2-raw/wiki.test.raw -t 1 -ngl 99 system_info: n_threads = 1 / 16 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | llama_print_timings: load time = 2575.04 ms $ ./perplexity -m models/Llama-2-7B-GGML/llama-2-7b.ggmlv3.q5_K_M.bin -f wikitext-2-raw/wiki.test.raw -t 1 -ngl 99 -eps 1 system_info: n_threads = 1 / 16 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | llama_print_timings: load time = 3436.11 ms |
Thanks - will take a look tmrw |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Reviewd on the phone 👍
Fixes #2373
Use
-eps 1e-5
with llama 2, defaults to1e-6
(same as current, for llama v1).