Commit
•
fe89313
1
Parent(s):
bc63ef3
Upload model
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: llama-code
|
| 8 |
results: []
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,6 +32,18 @@ More information needed
|
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
|
@@ -55,6 +68,7 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
|
|
|
| 58 |
- Transformers 4.32.1
|
| 59 |
- Pytorch 2.0.1
|
| 60 |
- Datasets 2.14.4
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: llama-code
|
| 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
|
|
|
|
| 32 |
|
| 33 |
## Training procedure
|
| 34 |
|
| 35 |
+
|
| 36 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 37 |
+
- quant_method: QuantizationMethod.BITS_AND_BYTES
|
| 38 |
+
- load_in_8bit: False
|
| 39 |
+
- load_in_4bit: True
|
| 40 |
+
- llm_int8_threshold: 6.0
|
| 41 |
+
- llm_int8_skip_modules: None
|
| 42 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 43 |
+
- llm_int8_has_fp16_weight: False
|
| 44 |
+
- bnb_4bit_quant_type: nf4
|
| 45 |
+
- bnb_4bit_use_double_quant: True
|
| 46 |
+
- bnb_4bit_compute_dtype: float32
|
| 47 |
### Training hyperparameters
|
| 48 |
|
| 49 |
The following hyperparameters were used during training:
|
|
|
|
| 68 |
|
| 69 |
### Framework versions
|
| 70 |
|
| 71 |
+
- PEFT 0.6.0.dev0
|
| 72 |
- Transformers 4.32.1
|
| 73 |
- Pytorch 2.0.1
|
| 74 |
- Datasets 2.14.4
|