Lohit20/fyp_llama-3
Browse files- README.md +13 -0
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -6,6 +6,7 @@ tags:
|
|
6 |
model-index:
|
7 |
- name: fyp_llama-3
|
8 |
results: []
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,6 +30,17 @@ More information needed
|
|
29 |
|
30 |
## Training procedure
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
@@ -47,6 +59,7 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Framework versions
|
49 |
|
|
|
50 |
- Transformers 4.31.0
|
51 |
- Pytorch 2.1.2
|
52 |
- Datasets 2.18.0
|
|
|
6 |
model-index:
|
7 |
- name: fyp_llama-3
|
8 |
results: []
|
9 |
+
library_name: peft
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
## Training procedure
|
32 |
|
33 |
+
|
34 |
+
The following `bitsandbytes` quantization config was used during training:
|
35 |
+
- load_in_8bit: False
|
36 |
+
- load_in_4bit: True
|
37 |
+
- llm_int8_threshold: 6.0
|
38 |
+
- llm_int8_skip_modules: None
|
39 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
40 |
+
- llm_int8_has_fp16_weight: False
|
41 |
+
- bnb_4bit_quant_type: nf4
|
42 |
+
- bnb_4bit_use_double_quant: True
|
43 |
+
- bnb_4bit_compute_dtype: float16
|
44 |
### Training hyperparameters
|
45 |
|
46 |
The following hyperparameters were used during training:
|
|
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
+
- PEFT 0.4.0
|
63 |
- Transformers 4.31.0
|
64 |
- Pytorch 2.1.2
|
65 |
- Datasets 2.18.0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109098378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcd343fc8bb9ce747a099335551697976de106c2446c2f037719d151d9902911
|
3 |
size 109098378
|