update model card README.md
Browse files
README.md
CHANGED
@@ -1,32 +1,54 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
## Training procedure
|
5 |
|
|
|
6 |
|
7 |
-
The following
|
8 |
-
-
|
9 |
-
-
|
10 |
-
-
|
11 |
-
-
|
12 |
-
-
|
13 |
-
-
|
14 |
-
-
|
15 |
-
-
|
16 |
-
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
- load_in_4bit: True
|
21 |
-
- llm_int8_threshold: 6.0
|
22 |
-
- llm_int8_skip_modules: None
|
23 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
24 |
-
- llm_int8_has_fp16_weight: False
|
25 |
-
- bnb_4bit_quant_type: nf4
|
26 |
-
- bnb_4bit_use_double_quant: False
|
27 |
-
- bnb_4bit_compute_dtype: float16
|
28 |
-
### Framework versions
|
29 |
|
30 |
-
- PEFT 0.4.0
|
31 |
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: NousResearch/Llama-2-7b-hf
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: llama-2-7b-int4-python-code-20k
|
7 |
+
results: []
|
8 |
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# llama-2-7b-int4-python-code-20k
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation data
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
## Training procedure
|
30 |
|
31 |
+
### Training hyperparameters
|
32 |
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 0.0002
|
35 |
+
- train_batch_size: 2
|
36 |
+
- eval_batch_size: 8
|
37 |
+
- seed: 42
|
38 |
+
- gradient_accumulation_steps: 2
|
39 |
+
- total_train_batch_size: 4
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine
|
42 |
+
- lr_scheduler_warmup_ratio: 0.03
|
43 |
+
- training_steps: 320
|
44 |
+
|
45 |
+
### Training results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
|
|
47 |
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.31.0
|
52 |
+
- Pytorch 2.2.1+cu121
|
53 |
+
- Datasets 2.13.0
|
54 |
+
- Tokenizers 0.13.3
|