Total runs:
8.6K
Run Growth:
299
Growth Rate:
3.50%
Sponsored by
PoYo.AI
Weyaxi / Einstein-v4-phi2
Model's Last Updated: April 23 2024
text-generation
Introduction of Einstein-v4-phi2
Model Details of Einstein-v4-phi2
🔬 Einstein-v4-phi2
This model is a full fine-tuned version of microsoft/phi-2 on diverse datasets.
This model is finetuned using
8xRTX3090
+
1xRTXA6000
using
axolotl
.
This model's training was sponsored by sablo.ai .
See axolotl config
axolotl version:
0.4.0
base_model: microsoft/phi-2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
chat_template: chatml
datasets:
- path: data/merged_all.json
ds_type: json
type: alpaca
conversation: chatml
- path: data/capybara_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/synthia-v1.3_sharegpt_12500.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/slimorca_dedup_filtered_95k_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./Einstein-v4-phi2-model
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project: Einstein
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v4-phi2
save_safetensors: true
gradient_accumulation_steps: 4
micro_batch_size: 3
num_epochs: 2
optimizer: adamw_torch # adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 2 # changed
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 4
debug:
deepspeed: zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|endoftext|>"
tokens:
- "<|im_start|>"
💬 Prompt Template
You can use this prompt template while using the model:
ChatML
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
This prompt template is available as a
chat template
, which means you can format messages using the
tokenizer.apply_chat_template()
method:
messages = [
{"role": "system", "content": "You are helpful AI asistant."},
{"role": "user", "content": "Hello!"}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
🔄 Quantizationed versions
Quantizationed versions of this model is available.
GGUF @bartowski :
Exl2 @bartowski :
🎯 Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 60.77 |
| AI2 Reasoning Challenge (25-Shot) | 59.98 |
| HellaSwag (10-Shot) | 74.07 |
| MMLU (5-Shot) | 56.89 |
| TruthfulQA (0-shot) | 45.80 |
| Winogrande (5-shot) | 73.88 |
| GSM8k (5-shot) | 53.98 |
🤖 Additional information about training
This model is full fine-tuned for 2 epochs.
Total number of steps was 2178.
Loss graph
🤝 Acknowledgments
Thanks to sablo.ai for sponsoring this model.
Thanks to all the dataset authors mentioned in the datasets section.
Thanks to axolotl for making the repository I used to make this model.
Thanks to all open source AI community.
If you would like to support me:
Runs of Weyaxi Einstein-v4-phi2 on huggingface.co
30
Total runs
0
24-hour runs
2
3-day runs
5
7-day runs
6
30-day runs
More Information About Einstein-v4-phi2 huggingface.co Model
Url of Einstein-v4-phi2
Einstein-v4-phi2 huggingface.co Url
Provider of Einstein-v4-phi2 huggingface.co
Other API from Weyaxi
Updated:September 15 2024
Total runs:
8.6K
Run Growth:
337
Growth Rate:
3.93%
Total runs:
8.5K
Run Growth:
326
Growth Rate:
3.82%
Total runs:
923
Run Growth:
-289
Growth Rate:
-31.31%
Total runs:
868
Run Growth:
-128
Growth Rate:
-14.75%
Total runs:
865
Run Growth:
-101
Growth Rate:
-11.68%
Total runs:
862
Run Growth:
-142
Growth Rate:
-16.47%
Total runs:
239
Run Growth:
-255
Growth Rate:
-106.69%
Total runs:
236
Run Growth:
-243
Growth Rate:
-102.97%
Total runs:
234
Run Growth:
-197
Growth Rate:
-84.19%
Total runs:
145
Run Growth:
-100
Growth Rate:
-68.97%
Total runs:
144
Run Growth:
-309
Growth Rate:
-214.58%
Total runs:
135
Run Growth:
-314
Growth Rate:
-232.59%
Total runs:
117
Run Growth:
-103
Growth Rate:
-88.03%
Total runs:
116
Run Growth:
-104
Growth Rate:
-89.66%
Total runs:
103
Run Growth:
-100
Growth Rate:
-97.09%
Total runs:
100
Run Growth:
1
Growth Rate:
1.00%
Total runs:
100
Run Growth:
1
Growth Rate:
1.00%
Total runs:
100
Run Growth:
-104
Growth Rate:
-104.00%
Total runs:
99
Run Growth:
-339
Growth Rate:
-342.42%
Total runs:
98
Run Growth:
-335
Growth Rate:
-341.84%
Total runs:
97
Run Growth:
-99
Growth Rate:
-102.06%
Total runs:
97
Run Growth:
-98
Growth Rate:
-101.03%
Total runs:
97
Run Growth:
-97
Growth Rate:
-100.00%
Total runs:
97
Run Growth:
3
Growth Rate:
3.09%
Total runs:
97
Run Growth:
-99
Growth Rate:
-102.06%
Total runs:
94
Run Growth:
-101
Growth Rate:
-107.45%
Total runs:
93
Run Growth:
-336
Growth Rate:
-361.29%
Total runs:
89
Run Growth:
2
Growth Rate:
2.25%
Total runs:
85
Run Growth:
-344
Growth Rate:
-404.71%
Total runs:
81
Run Growth:
24
Growth Rate:
29.63%
Total runs:
72
Run Growth:
27
Growth Rate:
37.50%
Total runs:
71
Run Growth:
33
Growth Rate:
46.48%
Total runs:
70
Run Growth:
22
Growth Rate:
31.43%
Total runs:
68
Run Growth:
22
Growth Rate:
32.35%
Total runs:
66
Run Growth:
14
Growth Rate:
21.21%
Total runs:
65
Run Growth:
8
Growth Rate:
12.31%
Total runs:
65
Run Growth:
11
Growth Rate:
16.92%
Total runs:
64
Run Growth:
19
Growth Rate:
29.69%
Total runs:
63
Run Growth:
16
Growth Rate:
25.40%
Total runs:
61
Run Growth:
13
Growth Rate:
21.31%
Total runs:
61
Run Growth:
14
Growth Rate:
22.95%
Total runs:
61
Run Growth:
16
Growth Rate:
26.23%
Total runs:
59
Run Growth:
10
Growth Rate:
16.95%
Total runs:
54
Run Growth:
22
Growth Rate:
40.74%
Total runs:
43
Run Growth:
25
Growth Rate:
58.14%
Total runs:
37
Run Growth:
29
Growth Rate:
78.38%
Total runs:
31
Run Growth:
26
Growth Rate:
83.87%
Total runs:
29
Run Growth:
10
Growth Rate:
35.71%
Total runs:
27
Run Growth:
16
Growth Rate:
61.54%
Total runs:
27
Run Growth:
27
Growth Rate:
100.00%
Total runs:
25
Run Growth:
14
Growth Rate:
60.87%
Total runs:
23
Run Growth:
15
Growth Rate:
68.18%
Total runs:
23
Run Growth:
15
Growth Rate:
65.22%
Total runs:
20
Run Growth:
11
Growth Rate:
57.89%
Total runs:
20
Run Growth:
10
Growth Rate:
52.63%
Total runs:
20
Run Growth:
12
Growth Rate:
63.16%
Total runs:
19
Run Growth:
5
Growth Rate:
27.78%
Total runs:
19
Run Growth:
10
Growth Rate:
55.56%
Total runs:
18
Run Growth:
10
Growth Rate:
58.82%
Total runs:
18
Run Growth:
5
Growth Rate:
27.78%
Total runs:
18
Run Growth:
9
Growth Rate:
52.94%
Total runs:
18
Run Growth:
8
Growth Rate:
44.44%
Total runs:
18
Run Growth:
9
Growth Rate:
50.00%
Total runs:
17
Run Growth:
6
Growth Rate:
35.29%
Total runs:
16
Run Growth:
5
Growth Rate:
33.33%
Total runs:
16
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
4
Growth Rate:
28.57%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
9
Growth Rate:
60.00%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
13
Run Growth:
2
Growth Rate:
15.38%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
11
Run Growth:
2
Growth Rate:
18.18%
Total runs:
11
Run Growth:
1
Growth Rate:
9.09%
Total runs:
10
Run Growth:
4
Growth Rate:
40.00%