Falcon-CN

VikrantRamesh/Falcon-CN

Falcon-CN is a feature extraction model from VikrantRamesh. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

7.1B

6.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.4 GB · 100%

Parameter types

How the weights are stored.

U86.2B · 86%

Base models

tiiuae/falcon-7b

Model card

From the Hugging Face model README

Falcon-CN

This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.2484

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
2.5969	0.24	10	2.5105
2.332	0.49	20	2.4691
2.418	0.73	30	2.4289
2.4031	0.98	40	2.4040
2.3109	1.22	50	2.3807
2.3516	1.46	60	2.3600
2.2906	1.71	70	2.3406
2.3594	1.95	80	2.3265
2.2031	2.2	90	2.3151
2.25	2.44	100	2.3039
2.2148	2.68	110	2.2911
2.2594	2.93	120	2.2803
2.1844	3.17	130	2.2752
2.0914	3.41	140	2.2714
2.2008	3.66	150	2.2624
2.2109	3.9	160	2.2586
2.1648	4.15	170	2.2548
2.1484	4.39	180	2.2535
2.193	4.63	190	2.2484
2.1219	4.88	200	2.2484

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Feature Extraction
Library: transformers
Type: falcon
License: apache-2.0
Created: Mar 8, 2024
Updated: Mar 8, 2024