Hugging Face's logo

emendes3
/
llava_13b_country_synthetic

PEFT
Safetensors
llava_llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
emendes3 commited on
Commit
6b86623
•
1 Parent(s): df08165

Model save

Browse files
Files changed (8) hide show
  1. README.md +6 -6
  2. adapter_model.safetensors +1 -1
  3. num_examples=200/llava-v1.5-13b_5.0/adapter_config.json +3 -3
  4. num_examples=200/llava-v1.5-13b_5.0/adapter_model.safetensors +1 -1
  5. num_examples=200/llava-v1.5-13b_5.0/training_args.bin +1 -1
  6. num_examples=400/llava-v1.5-13b_15.0/adapter_config.json +3 -3
  7. num_examples=400/llava-v1.5-13b_15.0/adapter_model.safetensors +1 -1
  8. num_examples=400/llava-v1.5-13b_15.0/training_args.bin +2 -2
README.md CHANGED
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.0146
19
- - eval_runtime: 79.6898
20
- - eval_samples_per_second: 12.185
21
- - eval_steps_per_second: 0.389
22
- - epoch: 3.0
23
- - step: 93
24
 
25
  ## Model description
26
 
 
15
 
16
  This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.0076
19
+ - eval_runtime: 79.4929
20
+ - eval_samples_per_second: 12.215
21
+ - eval_steps_per_second: 0.39
22
+ - epoch: 4.0
23
+ - step: 124
24
 
25
  ## Model description
26
 
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:030e64839210fd10671e480d7ed85b47a37326c696030bc0a42988839a13b580
3
  size 1001466944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a050739eb338b97eacf245976f67a23da4511a6bf0d0732e5e8f147373c09159
3
  size 1001466944
num_examples=200/llava-v1.5-13b_5.0/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "down_proj",
24
  "q_proj",
 
25
  "up_proj",
26
- "v_proj",
27
  "k_proj",
28
- "o_proj",
29
- "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
  "down_proj",
25
  "q_proj",
26
+ "gate_proj",
27
  "up_proj",
 
28
  "k_proj",
29
+ "o_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
num_examples=200/llava-v1.5-13b_5.0/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8903008fd557bd51a405e54df627c534c6066cb0120cefeaa6183a15fbca62ed
3
  size 1001466944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a050739eb338b97eacf245976f67a23da4511a6bf0d0732e5e8f147373c09159
3
  size 1001466944
num_examples=200/llava-v1.5-13b_5.0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3be191b9be5bb56af1e96bde1cac7b666919579566695cca06f53a795b8a3339
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8ece4a32d2e41df2f7ca3870dc7df2a8a6960250f6ec9c3425800aefdb26f8
3
  size 6776
num_examples=400/llava-v1.5-13b_15.0/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
  "gate_proj",
25
  "v_proj",
 
 
26
  "up_proj",
27
  "down_proj",
28
- "o_proj",
29
- "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "gate_proj",
24
  "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
  "up_proj",
28
  "down_proj",
29
+ "q_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
num_examples=400/llava-v1.5-13b_15.0/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77eacace6e043b1afc4ff2696fee41850683b70f96a19ff25ddee1d8bfca35f4
3
  size 1001466944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf4f83fea6eeee639e511be532147712c33d5b6d870b2cdb5a5416e76c07061
3
  size 1001466944
num_examples=400/llava-v1.5-13b_15.0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50476a6620e24c13693a66bd6f4fa0636cc1c5d4573336ea3ca371870780f42a
3
- size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc5d6efc84c20cbf928bdaf87d895c7faf9735594fe0d155c210fe04be92e57
3
+ size 6840