INemesisI/CodeLlama-7B-Zephyr
Browse files- README.md +56 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- runs/Dec18_04-30-08_cd3116806dd3/events.out.tfevents.1702873843.cd3116806dd3.13874.0 +3 -0
- runs/Dec18_11-08-32_452208b741b1/events.out.tfevents.1702898296.452208b741b1.207.0 +3 -0
- runs/Dec18_14-10-51_9f039cea2ed4/events.out.tfevents.1702908660.9f039cea2ed4.246.0 +3 -0
- runs/Dec18_14-12-38_9f039cea2ed4/events.out.tfevents.1702908760.9f039cea2ed4.246.1 +3 -0
- runs/Dec18_14-14-54_9f039cea2ed4/events.out.tfevents.1702908896.9f039cea2ed4.3379.0 +3 -0
- runs/Dec18_14-14-54_9f039cea2ed4/events.out.tfevents.1702909190.9f039cea2ed4.3379.1 +3 -0
- runs/Dec18_14-26-29_9f039cea2ed4/events.out.tfevents.1702909591.9f039cea2ed4.6523.0 +3 -0
- runs/Dec18_14-27-51_9f039cea2ed4/events.out.tfevents.1702909673.9f039cea2ed4.6523.1 +3 -0
- runs/Dec18_14-32-33_9f039cea2ed4/events.out.tfevents.1702909956.9f039cea2ed4.6523.2 +3 -0
- runs/Dec18_14-50-46_498aff11367c/events.out.tfevents.1702911068.498aff11367c.583.0 +3 -0
- runs/Dec18_16-58-16_498aff11367c/events.out.tfevents.1702918708.498aff11367c.35148.0 +3 -0
- runs/Dec18_19-30-53_936ba234359f/events.out.tfevents.1702927880.936ba234359f.184.0 +3 -0
- runs/Dec18_21-22-50_936ba234359f/events.out.tfevents.1702934583.936ba234359f.29746.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +83 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: codellama/CodeLlama-7b-hf
|
7 |
+
model-index:
|
8 |
+
- name: results
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# results
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
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: 0
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- PEFT 0.7.1
|
53 |
+
- Transformers 4.36.1
|
54 |
+
- Pytorch 2.1.0+cu121
|
55 |
+
- Datasets 2.15.0
|
56 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5cc08eaf46647827f177e855e01c66e8879ee4fa330653305e9942667d98b68
|
3 |
+
size 134235048
|
runs/Dec18_04-30-08_cd3116806dd3/events.out.tfevents.1702873843.cd3116806dd3.13874.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb71d7bb66d08fd2f07413a28d6ce6507fbd761a7c4df9cc464ea760345eb68
|
3 |
+
size 76875
|
runs/Dec18_11-08-32_452208b741b1/events.out.tfevents.1702898296.452208b741b1.207.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a8739e0ec22163311cb37a9710fcfdd62965c9a68c8d610d8b830f0a2250c2d
|
3 |
+
size 49652
|
runs/Dec18_14-10-51_9f039cea2ed4/events.out.tfevents.1702908660.9f039cea2ed4.246.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a1bc9f8173b0311d30975480930fb36585df71a1a0f3588f33ac5b0b033602
|
3 |
+
size 5188
|
runs/Dec18_14-12-38_9f039cea2ed4/events.out.tfevents.1702908760.9f039cea2ed4.246.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9641febba3fc7bfb6a2b1d4babe4356ea42aa056d07fc4696f3d95f18028f075
|
3 |
+
size 5188
|
runs/Dec18_14-14-54_9f039cea2ed4/events.out.tfevents.1702908896.9f039cea2ed4.3379.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0997791226c296bc65b2c7cb6cc8fa9d916e8e2fb87b75c4da77a595afb6ab9
|
3 |
+
size 5188
|
runs/Dec18_14-14-54_9f039cea2ed4/events.out.tfevents.1702909190.9f039cea2ed4.3379.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:561469bc6a7a5d399cbf684e5acd6d8d4991b246527aa6bca2b138221456bf7a
|
3 |
+
size 5188
|
runs/Dec18_14-26-29_9f039cea2ed4/events.out.tfevents.1702909591.9f039cea2ed4.6523.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7fe5ac403076a814d9e588475577696623bdea787c2c204b2e2454a3bffd7c1
|
3 |
+
size 5188
|
runs/Dec18_14-27-51_9f039cea2ed4/events.out.tfevents.1702909673.9f039cea2ed4.6523.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af6cf6755d58cec7a2569c8af5f542f5f1b0be2022e1c737e3f86a5db0c72724
|
3 |
+
size 4830
|
runs/Dec18_14-32-33_9f039cea2ed4/events.out.tfevents.1702909956.9f039cea2ed4.6523.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3262380434f9b6166175fb093b3a279eab230083fabb880ca8b2187799f88e6
|
3 |
+
size 4831
|
runs/Dec18_14-50-46_498aff11367c/events.out.tfevents.1702911068.498aff11367c.583.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44226373cddfc3cab916a5ef75a94fff235c1b392feaf0a2dccc1052d7727652
|
3 |
+
size 31708
|
runs/Dec18_16-58-16_498aff11367c/events.out.tfevents.1702918708.498aff11367c.35148.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:019d7d2ae0f3c0a4887732c8ea5e2b1d7099fdcb05ee8b265fddeab171a69ce7
|
3 |
+
size 50108
|
runs/Dec18_19-30-53_936ba234359f/events.out.tfevents.1702927880.936ba234359f.184.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:560e560b35e23486beaf441291b272d28caa895b6c802a1d7d92e819da4c3e2f
|
3 |
+
size 47428
|
runs/Dec18_21-22-50_936ba234359f/events.out.tfevents.1702934583.936ba234359f.29746.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236d48eb9c60f230bc08791132f59454b5219873b28b152b830ec375704ba618
|
3 |
+
size 5827
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": "</s>",
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32007": {
|
30 |
+
"content": "β<PRE>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32008": {
|
38 |
+
"content": "β<SUF>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32009": {
|
46 |
+
"content": "β<MID>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32010": {
|
54 |
+
"content": "β<EOT>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"β<PRE>",
|
64 |
+
"β<MID>",
|
65 |
+
"β<SUF>",
|
66 |
+
"β<EOT>"
|
67 |
+
],
|
68 |
+
"bos_token": "<s>",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"eot_token": "β<EOT>",
|
72 |
+
"fill_token": "<FILL_ME>",
|
73 |
+
"legacy": null,
|
74 |
+
"middle_token": "β<MID>",
|
75 |
+
"model_max_length": 1000000000000000019884624838656,
|
76 |
+
"pad_token": "</s>",
|
77 |
+
"prefix_token": "β<PRE>",
|
78 |
+
"sp_model_kwargs": {},
|
79 |
+
"suffix_token": "β<SUF>",
|
80 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
81 |
+
"unk_token": "<unk>",
|
82 |
+
"use_default_system_prompt": false
|
83 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc34d153d0e5f0dbac25abac26e7e2af0acfbf9bfad1d7868a492862172f7140
|
3 |
+
size 4728
|