Hugging Face's logo

REILX
/
Llama-3-8B-Instruct-neo_sft_phase2

Text Generation
Safetensors
English
Chinese
text-generation-inference
llama
sft
lora
Model card Files Community
REILX commited on
Commit
a9cd960
•
1 Parent(s): 310b637

Upload 9 files

Browse files
Files changed (9) hide show
  1. neo_sft_phase2_conversations/adapter_config.json +34 -0
  2. neo_sft_phase2_conversations/adapter_model.safetensors +3 -0
  3. neo_sft_phase2_conversations/training_loss.png +0 -0
  4. neo_sft_phase2_multi/adapter_config.json +34 -0
  5. neo_sft_phase2_multi/adapter_model.safetensors +3 -0
  6. neo_sft_phase2_multi/training_loss.png +0 -0
  7. neo_sft_phase2_single/adapter_config.json +34 -0
  8. neo_sft_phase2_single/adapter_model.safetensors +3 -0
  9. neo_sft_phase2_single/training_loss.png +0 -0
neo_sft_phase2_conversations/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/llama3/mode/Meta-Llama-3-8B-Instruct/",
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": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
neo_sft_phase2_conversations/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fec6c0f4aed7479532e712cdcd7ec289d7400f2d9a1d146d55397e9c2194193
3
+ size 83946192
neo_sft_phase2_conversations/training_loss.png ADDED
neo_sft_phase2_multi/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/llama3/mode/Meta-Llama-3-8B-Instruct/",
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": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
neo_sft_phase2_multi/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2a56f99244e5c4deb1f30a5de19f2bb266dcc271b661da1b7f3ee1ee5064a2
3
+ size 83946192
neo_sft_phase2_multi/training_loss.png ADDED
neo_sft_phase2_single/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/llama3/mode/Meta-Llama-3-8B-Instruct/",
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": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
neo_sft_phase2_single/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbd68f2d3f89843faf6f0dae56fa9c6ba0fb4b78cb0523cbf385c116cdc5e1c
3
+ size 83946192
neo_sft_phase2_single/training_loss.png ADDED