Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
kreas
/
MA_benchmarks
like
0
Model card
Files
Files and versions
Community
13ff53e
MA_benchmarks
/
Llama-2-7b-hf
1 contributor
History:
5 commits
kreas
Upload /Llama-2-7b-hf/nf4_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
89e2c62
verified
7 months ago
bf16_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf/bf16_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
7 months ago
fp16_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf/fp16_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
7 months ago
fp4_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf/fp4_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
7 months ago
int8_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf/int8_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
7 months ago
nf4_batch_size_1_sq_len_256_new_tokens_256
Upload /Llama-2-7b-hf/nf4_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub
7 months ago
