Ataliba Miguel
commited on
Commit
•
6a18a16
1
Parent(s):
0709daa
First model version
Browse files- .gitattributes +3 -0
- README.md +1 -13
- app.py +18 -0
- data/README.md +1 -0
- data/adapter_config.json +31 -0
- data/adapter_model.safetensors +3 -0
- data/configs_hc.yml +91 -0
- data/notfcn_B17.csv +0 -0
- data/notfcn_B17.jsonl +2 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
data/alpaca_synth_queries_healed.jsonl filter=lfs diff=lfs merge=lfs -text
|
37 |
+
adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
38 |
+
*.psd filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,13 +1 @@
|
|
1 |
-
|
2 |
-
title: Shit
|
3 |
-
emoji: ⚡
|
4 |
-
colorFrom: red
|
5 |
-
colorTo: green
|
6 |
-
sdk: streamlit
|
7 |
-
sdk_version: 1.35.0
|
8 |
-
app_file: app.py
|
9 |
-
pinned: false
|
10 |
-
license: apache-2.0
|
11 |
-
---
|
12 |
-
|
13 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
+
This directory contains the jsonl data used to train this model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
app.py
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
4 |
+
|
5 |
+
# Load the model and tokenizer
|
6 |
+
model = AutoModelForSequenceClassification.from_pretrained("./", local_files_only=True)
|
7 |
+
tokenizer = AutoTokenizer.from_pretrained("gpt2")
|
8 |
+
|
9 |
+
def classify_text(text):
|
10 |
+
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
|
11 |
+
with torch.no_grad():
|
12 |
+
outputs = model(**inputs)
|
13 |
+
logits = outputs.logits
|
14 |
+
predicted_class_id = logits.argmax().item()
|
15 |
+
return "Proper Naming Notfcn" if predicted_class_id == 1 else "Wrong Naming Notificn"
|
16 |
+
|
17 |
+
iface = gr.Interface(fn=classify_text, inputs="text", outputs="text", title="Classification Naming", description="Classify naming notifications as proper or wrong.")
|
18 |
+
iface.launch()
|
data/README.md
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
This directory contains the jsonl data used to train this model
|
data/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
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": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"gate_proj",
|
23 |
+
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"k_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
data/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:151496a8692deab90e4393beefaf341e8f67bdda2df9d2c62e2cf913122aeba5
|
3 |
+
size 335604696
|
data/configs_hc.yml
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: mistralai/Mistral-7B-v0.1
|
2 |
+
model_type: MistralForCausalLM
|
3 |
+
tokenizer_type: LlamaTokenizer
|
4 |
+
is_mistral_derived_model: true
|
5 |
+
|
6 |
+
load_in_8bit: false
|
7 |
+
load_in_4bit: true
|
8 |
+
strict: false
|
9 |
+
|
10 |
+
lora_fan_in_fan_out: false
|
11 |
+
data_seed: 49
|
12 |
+
seed: 49
|
13 |
+
|
14 |
+
datasets:
|
15 |
+
- path: /teamspace/studios/this_studio/axolotl/finetune_maven/hc-mistral-alpaca/data/alpaca_synth_queries_healed.jsonl
|
16 |
+
type: sharegpt
|
17 |
+
conversation: alpaca
|
18 |
+
dataset_prepared_path: last_run_prepared
|
19 |
+
val_set_size: 0.1
|
20 |
+
output_dir: ./qlora-alpaca-out
|
21 |
+
hub_model_id: valLabsz/clssfcn-naming
|
22 |
+
#hub_model_id: hamel/hc-mistral-alpaca
|
23 |
+
|
24 |
+
|
25 |
+
adapter: qlora
|
26 |
+
lora_model_dir:
|
27 |
+
|
28 |
+
sequence_len: 896
|
29 |
+
sample_packing: false
|
30 |
+
pad_to_sequence_len: true
|
31 |
+
|
32 |
+
lora_r: 32
|
33 |
+
lora_alpha: 16
|
34 |
+
lora_dropout: 0.05
|
35 |
+
lora_target_linear: true
|
36 |
+
lora_fan_in_fan_out:
|
37 |
+
lora_target_modules:
|
38 |
+
- gate_proj
|
39 |
+
- down_proj
|
40 |
+
- up_proj
|
41 |
+
- q_proj
|
42 |
+
- v_proj
|
43 |
+
- k_proj
|
44 |
+
- o_proj
|
45 |
+
|
46 |
+
#wandb_project: hc-axolotl-mistral
|
47 |
+
#wandb_entity: hamelsmu
|
48 |
+
|
49 |
+
gradient_accumulation_steps: 4
|
50 |
+
micro_batch_size: 16
|
51 |
+
eval_batch_size: 16
|
52 |
+
num_epochs: 3
|
53 |
+
optimizer: adamw_bnb_8bit
|
54 |
+
lr_scheduler: cosine
|
55 |
+
learning_rate: 0.0002
|
56 |
+
max_grad_norm: 1.0
|
57 |
+
adam_beta2: 0.95
|
58 |
+
adam_epsilon: 0.00001
|
59 |
+
save_total_limit: 12
|
60 |
+
|
61 |
+
train_on_inputs: false
|
62 |
+
group_by_length: false
|
63 |
+
bf16: true
|
64 |
+
fp16: false
|
65 |
+
tf32: false
|
66 |
+
|
67 |
+
gradient_checkpointing: true
|
68 |
+
early_stopping_patience:
|
69 |
+
resume_from_checkpoint:
|
70 |
+
local_rank:
|
71 |
+
logging_steps: 1
|
72 |
+
xformers_attention:
|
73 |
+
flash_attention: true
|
74 |
+
|
75 |
+
loss_watchdog_threshold: 5.0
|
76 |
+
loss_watchdog_patience: 3
|
77 |
+
|
78 |
+
warmup_steps: 20
|
79 |
+
evals_per_epoch: 4
|
80 |
+
eval_table_size:
|
81 |
+
eval_table_max_new_tokens: 128
|
82 |
+
saves_per_epoch: 6
|
83 |
+
debug:
|
84 |
+
weight_decay: 0.0
|
85 |
+
fsdp:
|
86 |
+
fsdp_config:
|
87 |
+
special_tokens:
|
88 |
+
bos_token: "<s>"
|
89 |
+
eos_token: "</s>"
|
90 |
+
unk_token: "<unk>"
|
91 |
+
save_safetensors: true
|
data/notfcn_B17.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
data/notfcn_B17.jsonl
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
{"text": "No"}
|
2 |
+
{"text": "Yes"}
|