Hugging Face's logo

iamPi
/
grads-patch_v0.1.0

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
axolotl
conversational
text-generation-inference
Model card Files
xet
 Community
iamPi commited on
Commit
af373f0
·
verified ·
1 Parent(s): 4a7322a

Add files using upload-large-folder tool

Browse files
Files changed (37) hide show
  1. .gitattributes +5 -0
  2. adapter_model.safetensors +3 -0
  3. checkpoint-20/adapter_model.safetensors +3 -0
  4. checkpoint-20/optimizer.pt +3 -0
  5. checkpoint-20/ref/adapter_model.safetensors +3 -0
  6. checkpoint-20/rng_state_0.pth +3 -0
  7. checkpoint-20/rng_state_1.pth +3 -0
  8. checkpoint-20/scheduler.pt +3 -0
  9. checkpoint-20/tokenizer.json +3 -0
  10. checkpoint-20/training_args.bin +3 -0
  11. checkpoint-40/adapter_model.safetensors +3 -0
  12. checkpoint-40/optimizer.pt +3 -0
  13. checkpoint-40/ref/adapter_config.json +46 -0
  14. checkpoint-40/ref/adapter_model.safetensors +3 -0
  15. checkpoint-40/rng_state_0.pth +3 -0
  16. checkpoint-40/rng_state_1.pth +3 -0
  17. checkpoint-40/scheduler.pt +3 -0
  18. checkpoint-40/tokenizer.json +3 -0
  19. checkpoint-40/training_args.bin +3 -0
  20. checkpoint-60/adapter_model.safetensors +3 -0
  21. checkpoint-60/optimizer.pt +3 -0
  22. checkpoint-60/ref/adapter_model.safetensors +3 -0
  23. checkpoint-60/rng_state_0.pth +3 -0
  24. checkpoint-60/rng_state_1.pth +3 -0
  25. checkpoint-60/scheduler.pt +3 -0
  26. checkpoint-60/tokenizer.json +3 -0
  27. checkpoint-60/training_args.bin +3 -0
  28. checkpoint-64/adapter_model.safetensors +3 -0
  29. checkpoint-64/optimizer.pt +3 -0
  30. checkpoint-64/ref/adapter_model.safetensors +3 -0
  31. checkpoint-64/rng_state_0.pth +3 -0
  32. checkpoint-64/rng_state_1.pth +3 -0
  33. checkpoint-64/scheduler.pt +3 -0
  34. checkpoint-64/tokenizer.json +3 -0
  35. checkpoint-64/training_args.bin +3 -0
  36. ref/adapter_model.safetensors +3 -0
  37. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058aefa9c41a47eac8ec0461b3cf1a467a69fb3edb1a291df6fbdedf2eaffd41
3
+ size 119801528
checkpoint-20/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c8e51a87890d4cfa042f1717af4654cadf826c0d47b9cc0b092641e337ccce
3
+ size 119801528
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2532ac12f46675fd191ed51e0d4bd764fc8721ee85ee0ce6c8db66f542fc5d22
3
+ size 61392581
checkpoint-20/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2ecb1c747e7d52bfcd360ed8c23ffc682c05b1bc51015de4d7ad6daa08a81
3
+ size 59934640
checkpoint-20/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6e78c4c15b6ddf123e5fe74fabf70db469d873e8ec00ce3af2894428929727
3
+ size 14917
checkpoint-20/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732c0243af01ed347f2dbe955fbe6982be51c3da7d7098a177481c19c6ce61c0
3
+ size 14917
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4728fcddf4ace3b689491d0a413b562f80814315c8ceeac70ec47a0bbf55113
3
+ size 1465
checkpoint-20/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0285bd38b0b6a527374caa2aa182b2e7bab2ebe1a065e96a09a199206b11fa0b
3
+ size 9361
checkpoint-40/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab254dbd50b6c27a77232a31a6bbc1baecdfbbabe4cc108791d63e137e38e3bc
3
+ size 119801528
checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aff7a8c307c599bcf6a9e61388f46241703c519838464195957f5933be5c527
3
+ size 61392581
checkpoint-40/ref/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": null,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 16,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "q_proj",
33
+ "v_proj",
34
+ "k_proj",
35
+ "down_proj",
36
+ "o_proj",
37
+ "gate_proj",
38
+ "up_proj"
39
+ ],
40
+ "target_parameters": [],
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-40/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2ecb1c747e7d52bfcd360ed8c23ffc682c05b1bc51015de4d7ad6daa08a81
3
+ size 59934640
checkpoint-40/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293019d2b051e061cb12c4c94d89fc580c749d556b9747a2b8e9e794519cffd5
3
+ size 14917
checkpoint-40/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc52903ea4bca73e2c61a2d2e9816b0793371c25c0c90e1ed9ec15b156a6c3c
3
+ size 14917
checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f14314da2bdd0d659a312c159be8c9d6c42bce8e5a461f52d048fb7847f047f
3
+ size 1465
checkpoint-40/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0285bd38b0b6a527374caa2aa182b2e7bab2ebe1a065e96a09a199206b11fa0b
3
+ size 9361
checkpoint-60/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1339832b6c77959272877e4b90b09daa35301c33a4a5bb9527fa6592243fb1ab
3
+ size 119801528
checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32d4a0dc708ad66e9b91359e40b59e33cc6b618d880158790169dd55c1ff728
3
+ size 61392581
checkpoint-60/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2ecb1c747e7d52bfcd360ed8c23ffc682c05b1bc51015de4d7ad6daa08a81
3
+ size 59934640
checkpoint-60/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a8d7b029b8b9255d97b5c6982348899111072b91ff49aba2eafeeec2c9632f
3
+ size 14917
checkpoint-60/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe4df9d3535e8ef4a3afac5b66246c5bf5d479ccc54be7ef1af86cc8a5a5678
3
+ size 14917
checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6118b3b4205cff460d4ad68d857377c7708206163499baf46bff9063a1529b6
3
+ size 1465
checkpoint-60/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0285bd38b0b6a527374caa2aa182b2e7bab2ebe1a065e96a09a199206b11fa0b
3
+ size 9361
checkpoint-64/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058aefa9c41a47eac8ec0461b3cf1a467a69fb3edb1a291df6fbdedf2eaffd41
3
+ size 119801528
checkpoint-64/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0b29dbbb4e88b558e54147083acc3b37cf60047751bef9911736bccb1b7482
3
+ size 61392581
checkpoint-64/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2ecb1c747e7d52bfcd360ed8c23ffc682c05b1bc51015de4d7ad6daa08a81
3
+ size 59934640
checkpoint-64/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57bc2ac3471c364676494e574d5a90f2a507a7a7e9fc86a2a72c421ffa33d6c
3
+ size 14917
checkpoint-64/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50590840349d7f14b63e1fab2fa34e7108ba9b83d57f96c8990d58b991d0194b
3
+ size 14917
checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c7f1c46c265fdff00f63371cadbf6e333d2901ddbfcba26eaee9fcd6b55c22
3
+ size 1465
checkpoint-64/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-64/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0285bd38b0b6a527374caa2aa182b2e7bab2ebe1a065e96a09a199206b11fa0b
3
+ size 9361
ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2ecb1c747e7d52bfcd360ed8c23ffc682c05b1bc51015de4d7ad6daa08a81
3
+ size 59934640
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896