gouthamsk/mistral_embedded_c
Browse files- README.md +7 -9
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- tokenizer.model +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,26 +15,24 @@ model-index:
|
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
-
![This is an alt text.](http://biboxlabs.com/wp-content/uploads/2021/07/bibox-labs-logo.png 'Logo.')
|
19 |
|
20 |
-
For more Info vist [Biboxlabs](https://biboxlabs.com/) or [Red Nerd](https://www.therednerds.com/)
|
21 |
# mistral_embedded_c
|
22 |
|
23 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
24 |
-
It has been fine-tuned using LoRa (Long Range) technology, enhancing its capabilities for applications requiring long-range communication.
|
25 |
|
26 |
## Model description
|
27 |
-
|
|
|
28 |
|
29 |
## Intended uses & limitations
|
30 |
-
|
|
|
|
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
34 |
-
Training Data is specifically curated for specific purposes to evaluate the embedded c code.
|
35 |
|
36 |
## Training procedure
|
37 |
-
The training was done on an A100-40GB accelerator.
|
38 |
|
39 |
### Training hyperparameters
|
40 |
|
@@ -46,7 +44,7 @@ The following hyperparameters were used during training:
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: constant
|
48 |
- lr_scheduler_warmup_steps: 0.03
|
49 |
-
- training_steps:
|
50 |
|
51 |
### Training results
|
52 |
|
|
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
18 |
|
|
|
19 |
# mistral_embedded_c
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
|
|
22 |
|
23 |
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
|
27 |
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
## Training and evaluation data
|
32 |
|
33 |
+
More information needed
|
|
|
34 |
|
35 |
## Training procedure
|
|
|
36 |
|
37 |
### Training hyperparameters
|
38 |
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: constant
|
46 |
- lr_scheduler_warmup_steps: 0.03
|
47 |
+
- training_steps: 300
|
48 |
|
49 |
### Training results
|
50 |
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_dora": false,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5b582d51a443321ddf95a24b85586415f9811970e889dc150e572b57f9807ab
|
3 |
size 109069176
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74bfa0c4f571ce7c6291893b7d4a6e8285deb6607e3e98773d1dafefdc0a0757
|
3 |
size 4920
|