Model save
Browse files- README.md +2 -6
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- tokenizer.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
-
base_model:
|
9 |
model-index:
|
10 |
- name: falcon7binstruct
|
11 |
results: []
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# falcon7binstruct
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,10 +47,6 @@ The following hyperparameters were used during training:
|
|
47 |
- training_steps: 10
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
-
### Training results
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
### Framework versions
|
55 |
|
56 |
- PEFT 0.7.2.dev0
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
+
base_model: vilsonrodrigues/falcon-7b-instruct-sharded
|
9 |
model-index:
|
10 |
- name: falcon7binstruct
|
11 |
results: []
|
|
|
16 |
|
17 |
# falcon7binstruct
|
18 |
|
19 |
+
This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on the None dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
- training_steps: 10
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
|
|
|
|
|
|
|
|
50 |
### Framework versions
|
51 |
|
52 |
- PEFT 0.7.2.dev0
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
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": true,
|
@@ -19,10 +19,10 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
"dense",
|
24 |
"dense_4h_to_h",
|
25 |
-
"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"dense_h_to_4h",
|
23 |
"dense",
|
24 |
"dense_4h_to_h",
|
25 |
+
"query_key_value"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 130583912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5967403586bbf8b5c66aabb2475c8cec61035cf4e1cb75cc2c4cb9c32ad60fcb
|
3 |
size 130583912
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d061ff7501cef667fce3218cf66f5de86959968a038ae3ec253026a3e5ee8545
|
3 |
size 4792
|