Hugging Face's logo

adamo1139
/
Yi-34B-200K-HESOYAM-rawrr_stage2-2306-LoRA

Safetensors
lora
Model card Files Community
adamo1139 commited on
Commit
8a79338
•
1 Parent(s): aa84495

Upload 6 files

Browse files
Files changed (6) hide show
  1. 1-yi-34b-xlctx-uninstruct1-galore-sft/adapter_config.json +29 -0
  2. 1-yi-34b-xlctx-uninstruct1-galore-sft/adapter_model.safetensors +3 -0
  3. 2-yi-34b-xlctx-hesoyam-galore-sft/adapter_config.json +29 -0
  4. 2-yi-34b-xlctx-hesoyam-galore-sft/adapter_model.safetensors +3 -0
  5. 3-yi-34b-xlctx-rawrr-stage2-orpo-galore-intermediate-checkpoint/adapter_config.json +29 -0
  6. 3-yi-34b-xlctx-rawrr-stage2-orpo-galore-intermediate-checkpoint/adapter_model.safetensors +3 -0
1-yi-34b-xlctx-uninstruct1-galore-sft/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "yi-34b-200k-2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": "unsloth",
18
+ "target_modules": [
19
+ "k_proj",
20
+ "o_proj",
21
+ "q_proj",
22
+ "gate_proj",
23
+ "up_proj",
24
+ "v_proj",
25
+ "down_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": true
29
+ }
1-yi-34b-xlctx-uninstruct1-galore-sft/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651ed4ef49d96888abfe8182a2409c0d1e62b54017be54ca3a7817533d8aec42
3
+ size 983153656
2-yi-34b-xlctx-hesoyam-galore-sft/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "yi-34b-200k-xlctx-uninstruct1-1906",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": "unsloth",
18
+ "target_modules": [
19
+ "up_proj",
20
+ "v_proj",
21
+ "k_proj",
22
+ "q_proj",
23
+ "down_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": true
29
+ }
2-yi-34b-xlctx-hesoyam-galore-sft/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d635ce1086e18ca6bd507581dcd7e1578354f49ccf0380ebfd600044295b1b
3
+ size 983153656
3-yi-34b-xlctx-rawrr-stage2-orpo-galore-intermediate-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "yi-34b-200k-xlctx-uninstruct1-hesoyam-2006",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": "unsloth",
18
+ "target_modules": [
19
+ "gate_proj",
20
+ "v_proj",
21
+ "q_proj",
22
+ "down_proj",
23
+ "k_proj",
24
+ "up_proj",
25
+ "o_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": true
29
+ }
3-yi-34b-xlctx-rawrr-stage2-orpo-galore-intermediate-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00396a310c71f214ee49b0b31fa27bb0407999646cf151fe729397a820d1f478
3
+ size 983153656