L
llllvvuu
AI & ML interests
None yet
Organizations
llllvvuu's activity
data issue: two_apples_a_day.out
#4 opened 6 months ago
by
llllvvuu

several lfs uploads are switched
#3 opened 6 months ago
by
llllvvuu

Upload folder using huggingface_hub
2
#1 opened 6 months ago
by
llllvvuu

Upload folder using huggingface_hub
2
#1 opened 6 months ago
by
llllvvuu

Upload folder using huggingface_hub
2
#1 opened 6 months ago
by
llllvvuu

the config class and config.json uses DeepseekConfig, not v2
1
#5 opened 6 months ago
by
winglian

fix config.json
#4 opened 6 months ago
by
llllvvuu

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture
1
#1 opened 7 months ago
by
llllvvuu

Config / model type could probably just be `llama` / `LlamaForCausalLM`
1
#2 opened 7 months ago
by
llllvvuu

Config / model type could probably just be `llama` / `LlamaForCausalLM`
1
#2 opened 7 months ago
by
llllvvuu

Set `model_type` to `llama`
#3 opened 6 months ago
by
llllvvuu

Set `model_type` to `llama`
1
#3 opened 7 months ago
by
llllvvuu

fix config.json
#1 opened 6 months ago
by
llllvvuu

fix config.json
#6 opened 6 months ago
by
llllvvuu

fix config.json
#7 opened 6 months ago
by
llllvvuu

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture
1
#1 opened 7 months ago
by
llllvvuu

Set `model_type` to `llama`
1
#6 opened 7 months ago
by
llllvvuu

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture
1
#1 opened 7 months ago
by
llllvvuu

Set `model_type` to `llama`
1
#3 opened 7 months ago
by
llllvvuu

Config / model type could probably just be `llama` / `LlamaForCausalLM`
1
#2 opened 7 months ago
by
llllvvuu
