Hugging Face's logo

dhmeltzer
/
llama-7b-SFT-qlora-eli5-wiki_DPO_ds_RM_random_1024_r_64_alpha_16

Generated from Trainer
Model card Files Community
dhmeltzer commited on
Commit
bf2828a
·
1 Parent(s): 47d32d6

Training in progress, step 19

Browse files
Files changed (2) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.bin +1 -1
adapter_config.json CHANGED
@@ -14,13 +14,13 @@
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
17
- "up_proj",
18
- "k_proj",
19
- "o_proj",
20
- "v_proj",
21
  "down_proj",
 
 
 
22
  "q_proj",
23
- "gate_proj"
 
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
 
 
 
 
17
  "down_proj",
18
+ "k_proj",
19
+ "up_proj",
20
+ "gate_proj",
21
  "q_proj",
22
+ "o_proj",
23
+ "v_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:208210f9003e912eea6b676f27cfcbcb9bfcbd6f8559756fdbd32c64113adc92
3
  size 639792909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2bbfa48eb76f0fb4830cfd05d9de1c60c587412285e58d7c275faaecdc35b7
3
  size 639792909