jaigouk/ ruby-una-cybertron-7b-v2-bf16

51 Downloads Updated 2 years ago

ollama run jaigouk/ruby-una-cybertron-7b-v2-bf16

curl http://localhost:11434/api/chat \
  -d '{
    "model": "jaigouk/ruby-una-cybertron-7b-v2-bf16",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='jaigouk/ruby-una-cybertron-7b-v2-bf16',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'jaigouk/ruby-una-cybertron-7b-v2-bf16',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

1 model

Size

Context

Input

ruby-una-cybertron-7b-v2-bf16:latest

7.7GB · 32K context window · Text · 2 years ago

ruby-una-cybertron-7b-v2-bf16:latest

7.7GB

32K

Text

Readme

ruby-una-cybertron-7b-v2-bf16

https://huggingface.co/jaigouk/ruby-una-cybertron-7b-v2-bf16

This model is a fine-tuned version of fblgit/una-cybertron-7b-v2-bf16.

It achieves the following results on the evaluation set:

Loss: 0.6878

Model description

intention is to use this with system message for generating ruby codes

Intended uses & limitations

writing rspec / ruby codes

Training and evaluation data

https://huggingface.co/datasets/jaigouk/coding-dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.2904	2.53	100	0.6878

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.14.1

# ruby-una-cybertron-7b-v2-bf16

- https://huggingface.co/jaigouk/ruby-una-cybertron-7b-v2-bf16

This model is a fine-tuned version of [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16).

It achieves the following results on the evaluation set:

- Loss: 0.6878

## Model description

- intention is to use this with system message for generating ruby codes

## Intended uses & limitations

- writing rspec / ruby codes

## Training and evaluation data

- https://huggingface.co/datasets/jaigouk/coding-dataset

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:

- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.2904        | 2.53  | 100  | 0.6878          |

### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.14.1

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)