Hugging Face's logo

dhmeltzer
/
llama-7b-SFT-qlora-eli5-wiki_DPO_ds_RM_contrast_1024_r_64_alpha_16

Safetensors
Generated from Trainer
Model card Files Community
dhmeltzer commited on
Commit
7f528f0
·
1 Parent(s): d0dd4bb

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
- "gate_proj",
18
- "v_proj",
19
  "up_proj",
20
- "o_proj",
21
  "down_proj",
22
- "q_proj",
23
- "k_proj"
 
 
 
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
 
 
17
  "up_proj",
 
18
  "down_proj",
19
+ "gate_proj",
20
+ "o_proj",
21
+ "v_proj",
22
+ "k_proj",
23
+ "q_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 sha256:0d9e50c73dcebf7aadcfd5386a69d22b5b1db3af87492686d14e82d48b03ec79
3
  size 639792909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6999ed568e5ce2a0075c7b3aae92df8acfc15d5a271e77ec7dac391458d09f9
3
  size 639792909