Hugging Face's logo

Azazelle
/
L3-Daybreak-8b-lora

Safetensors
Model card Files Community
Azazelle crestf411 commited on
Commit
069f69c
·
verified ·
0 Parent(s):

Duplicate from crestf411/daybreak-peft

Browse files

Co-authored-by: Crestfall <crestf411@users.noreply.huggingface.co>

Files changed (16) hide show
  1. .gitattributes +35 -0
  2. README.md +5 -0
  3. command-r-35b/adapter_config.json +34 -0
  4. command-r-35b/adapter_model.safetensors +3 -0
  5. llama3-70b/CHANGELOG.txt +3 -0
  6. llama3-70b/adapter_config.json +34 -0
  7. llama3-70b/adapter_model.bin +3 -0
  8. llama3-8b/CHANGELOG.md +2 -0
  9. llama3-8b/adapter_config.json +34 -0
  10. llama3-8b/adapter_model.safetensors +3 -0
  11. mistral-7b/adapter_config.json +32 -0
  12. mistral-7b/adapter_model.safetensors +3 -0
  13. mistral-7b/trainer_state.json +0 -0
  14. mixtral-8x7b/adapter_config.json +33 -0
  15. mixtral-8x7b/adapter_model.bin +3 -0
  16. mixtral-8x7b/trainer_state.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ # Daybreak
2
+
3
+ This set of LoRAs differ from the crestfall models due to the addition of on-topic SFW content.
4
+
5
+ The intention is to produce a more intelligent model that is still capable of niche genre ERP.
command-r-35b/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./curr-model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "o_proj",
25
+ "v_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
command-r-35b/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275fd440db994c285e08e01f03bed5f44200c8ebf393f4769e1aca3fa7f4a93c
3
+ size 403777872
llama3-70b/CHANGELOG.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ * 20240525: Pushed v0.4 LoRA, even more deslopping/dataset fixes.
2
+ * 20240521: Pushed v0.3 LoRA, with more deslopping, and dataset fixes. Also uses HQQ quantization instead of QLoRA, which got training up to 8k context size.
3
+ * 20240511: Pushed v0.2 LoRA. Higher context size, and curation/fixes to dataset.
llama3-70b/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": false,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [],
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "down_proj",
25
+ "v_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "o_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
llama3-70b/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d176a06ca24b9945158a6f961d39e7978f2c15b1106a5f5afa0668f41f24f56b
3
+ size 828891458
llama3-8b/CHANGELOG.md ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ * 2024-04-21: v0.1 release. Merge with base instruct gives poor results.
2
+ * 2024-05-07: v0.2 release. Updated with latest dataset. Merge with non-base instruct gives decent results.
llama3-8b/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./curr-model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "k_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
llama3-8b/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2401b5a977aa4bc09b2b40b7a7fa412948d4be5ce0f0ad83e1989db42d8d874f
3
+ size 1342238560
mistral-7b/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./curr-model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.01,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
mistral-7b/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50dee3143bb15c4c2477d00ed274ff62dd7557d04e739603a770039b985ae531
3
+ size 671149168
mistral-7b/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
mixtral-8x7b/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./curr-model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.01,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "w3",
23
+ "w2",
24
+ "w1",
25
+ "gate",
26
+ "q_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_rslora": false
33
+ }
mixtral-8x7b/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efc57848917f36627af0c935a77bfc05050250fb760503339907daa5622ec5f
3
+ size 3876297957
mixtral-8x7b/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff