32 lines
1.1 KiB
YAML
32 lines
1.1 KiB
YAML
repo_id:
|
|
- 'THUDM/chatglm3-6b'
|
|
- 'THUDM/glm-4-9b-chat'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'meta-llama/Llama-2-13b-chat-hf'
|
|
- 'meta-llama/Meta-Llama-3-8B-Instruct'
|
|
- 'mistralai/Mistral-7B-Instruct-v0.2'
|
|
- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
|
|
- '01-ai/Yi-6B-Chat'
|
|
- 'openbmb/MiniCPM-1B-sft-bf16'
|
|
- 'openbmb/MiniCPM-2B-sft-bf16'
|
|
- 'Qwen/Qwen1.5-7B-Chat'
|
|
- 'Qwen/Qwen2-1.5B-Instruct'
|
|
- 'Qwen/Qwen2-7B-Instruct'
|
|
- 'microsoft/Phi-3-mini-4k-instruct'
|
|
- 'microsoft/Phi-3-mini-128k-instruct'
|
|
- 'microsoft/phi-3-vision-128k-instruct'
|
|
- 'openbmb/MiniCPM-V-2_6'
|
|
- 'dummy/dummy-1.5B'
|
|
- 'dummy/dummy-4B'
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 1
|
|
num_trials: 3
|
|
num_beams: 1 # default to greedy search
|
|
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
|
|
batch_size: 1 # default to 1
|
|
in_out_pairs:
|
|
- '4096-512'
|
|
test_api:
|
|
- "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows, use fp16 for non-linear layer
|
|
cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|