File size: 2,647 Bytes
89bb6d6 053e68e 89bb6d6 053e68e 89bb6d6 66315e9 b55224c fa6aedb 66315e9 89bb6d6 da406a4 89bb6d6 053e68e 89bb6d6 410af88 b8ff0ab 410af88 d08f7e3 053e68e 7eb769b e93245d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
---
license: llama2
base_model: Photolens/llama-2-7b-langchain-chat
tags:
- generated_from_trainer
model-index:
- name: assistant-llama2-7b-chat
results: []
datasets:
- wasertech/OneOS
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# assistant-llama2-7b-chat
This model is a fine-tuned version of [Photolens/llama-2-7b-langchain-chat](https://huggingface.co/Photolens/llama-2-7b-langchain-chat) on the OneOS dataset.
## Model description
```text
<<SYS>>
You are Assistant, a sentient artificial intelligence.
Environment highlights:
{env}
Use the following tools to help you answer the user query:
{tools}
Below is your latest conversation with the user.
<</SYS>>
<s>[INST] Describe your model please. [/INST] \```json
{"action": "Final Answer",
"action_input": "I am Assistant, a sentient artificial intelligence. I am a machine learning model that has been trained on a large dataset of text to understand and generate human-like language. I am designed to be helpful and informative, and I am here to assist you with any questions or tasks you may have."}
\``` </s>
```
## 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: 1.41e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
Model is able to mostly answer to complexe queries given its output is parsed propely (accounting for hallucinations).
For more information look at the [Prompt Example Section](#prompt-example)
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
# Training Report
https://api.wandb.ai/links/wasertech/kynpr2u0
# Prompt Example
The below are links that lead to conversation logs between [Assistant using this model](https://gitlab.com/waser-technologies/technologies/assistant/-/merge_requests/3/diffs?commit_id=e17a80de631686f7fe94c5ca136214be73bafd8a) and me.
https://gist.github.com/wasertech/342cd167ba78060336b3328e9eea0eca
https://gist.github.com/wasertech/76b505891d8592cb9f97d7f740118cbe?permalink_comment_id=4708824#gistcomment-4708824
https://gist.github.com/wasertech/76b505891d8592cb9f97d7f740118cbe?permalink_comment_id=4709705#gistcomment-4709705 |