Model save
Browse files- README.md +4 -4
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -6,14 +6,14 @@ library_name: peft
|
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
-
- name: Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
# Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16) on the red_pajama-data-1_t-sample dataset.
|
| 19 |
|
|
@@ -35,11 +35,11 @@ More information needed
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0002
|
| 38 |
-
- train_batch_size:
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
| 41 |
- gradient_accumulation_steps: 16
|
| 42 |
-
- total_train_batch_size:
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 200
|
|
|
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
+
- name: Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r8_bs4
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r8_bs4
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16) on the red_pajama-data-1_t-sample dataset.
|
| 19 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0002
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
| 41 |
- gradient_accumulation_steps: 16
|
| 42 |
+
- total_train_batch_size: 64
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 200
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4105c8151e3a0b2030988d43b65baf62cb45b8a787696db58f22defb59546108
|
| 3 |
size 83945296
|