Hugging Face's logo

moiduy04
/
Llama-3-6.6B-R-Pruned

Text Generation
Model card Files
xet
Community
VDotMint commited on
Commit
3a4e2e9
·
1 Parent(s): ec59be6

Random-pruned Llama3-6.6B model + 2 epoch finetune

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. LLama-3-6.6B-R-Pruned-checkpoint-24880/adapter_config.json +22 -0
  3. LLama-3-6.6B-R-Pruned-checkpoint-24880/adapter_model.bin +3 -0
  4. LLama-3-6.6B-R-Pruned-checkpoint-24880/optimizer.pt +3 -0
  5. LLama-3-6.6B-R-Pruned-checkpoint-24880/rng_state.pth +3 -0
  6. LLama-3-6.6B-R-Pruned-checkpoint-24880/scheduler.pt +3 -0
  7. LLama-3-6.6B-R-Pruned-checkpoint-24880/trainer_state.json +0 -0
  8. LLama-3-6.6B-R-Pruned-checkpoint-24880/training_args.bin +3 -0
  9. Llama-3-6.6B-R-Prune.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Llama-3-6.6B-R-Prune.bin filter=lfs diff=lfs merge=lfs -text
LLama-3-6.6B-R-Pruned-checkpoint-24880/adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 8,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "k_proj",
15
+ "v_proj",
16
+ "o_proj",
17
+ "gate_proj",
18
+ "down_proj",
19
+ "up_proj"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
LLama-3-6.6B-R-Pruned-checkpoint-24880/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da2c363793cff866059ed848e3a2414d3b7b269a9a051354b259c374a99aa57
3
+ size 72971786
LLama-3-6.6B-R-Pruned-checkpoint-24880/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee834c280f0f8049ff9ce344c258f2593d1760df61fb32b3556ec2898bd935d6
3
+ size 145997906
LLama-3-6.6B-R-Pruned-checkpoint-24880/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf403da2d364b46b904e6467b73466c38947256b66c603beb7758c8df989fdd
3
+ size 14244
LLama-3-6.6B-R-Pruned-checkpoint-24880/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182e664ecbf8f436bc98cecb37aa25110294e2be2976e45b5377895cd67c58e5
3
+ size 1064
LLama-3-6.6B-R-Pruned-checkpoint-24880/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
LLama-3-6.6B-R-Pruned-checkpoint-24880/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb1e74e78dc45303fc44f5c057d5e496217ce709f75181fd3752883489fd70b
3
+ size 5240
Llama-3-6.6B-R-Prune.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527d599d44b4677b0381e6fd14b67b1ce395c3ca9cf10110b49d5e7dfc30840d
3
+ size 13234389214