64 lines
2.8 KiB
Markdown
64 lines
2.8 KiB
Markdown
---
|
||
language:
|
||
- en
|
||
license: llama2
|
||
tags:
|
||
- facebook
|
||
- meta
|
||
- pytorch
|
||
- llama
|
||
- llama-2
|
||
model_name: Llama 2 7B Chat
|
||
arxiv: 2307.09288
|
||
base_model: meta-llama/Llama-2-7b-chat-hf
|
||
inference: false
|
||
model_creator: Meta Llama 2
|
||
model_type: llama
|
||
pipeline_tag: text-generation
|
||
prompt_template: '[INST] <<SYS>>
|
||
You are NutriLife chatbot, you are going to get questions related to food, nutrition, health, and diet by the users from Nepal. Answer them very shortly and accurately if the message is only about food, nutrition, and diet. Otherwise, ignore.
|
||
<</SYS>>
|
||
{prompt}[/INST]
|
||
'
|
||
quantized_by: Dilip Pokhrel
|
||
---
|
||
|
||
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
||
<!-- header end -->
|
||
# Llama 2 7B Chat -- Food and Nutrition
|
||
<br>
|
||
- Model creator: [Meta Llama 2]
|
||
<br>
|
||
- Original model: [Llama 2 7B Chat] <a href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf">Original Model</a>
|
||
<br>
|
||
- Fine Tuned by: [Dilip Pokhrel] <a href="https://dilippokhrel.com.np">Profile</a>
|
||
|
||
|
||
#### Simple example code to load one of these GGUF models
|
||
|
||
```python
|
||
# Load model directly or use qunatization technique if you have low gpu ram
|
||
|
||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained("dilip025/llama-2-7b")
|
||
model = AutoModelForCausalLM.from_pretrained("dilip025/llama-2-7b")
|
||
system_message = 'You are NutriLife chatbot, you are going to get questions related to food, nutrition, health, and diet by the users from Nepal. Answer them very shortly and accurately if the message is only about food, nutrition, and diet. Otherwise, ignore.'
|
||
|
||
prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n Tell me some of the famous Nepali food recipes [/INST]"
|
||
num_new_tokens = 200 # Change to the number of new tokens you want to generate
|
||
|
||
# Count the number of tokens in the prompt
|
||
num_prompt_tokens = len(tokenizer(prompt)['input_ids'])
|
||
|
||
# Calculate the maximum length for the generation
|
||
max_length = num_prompt_tokens + num_new_tokens
|
||
|
||
gen = pipeline('text-generation', model=model, tokenizer=tokenizer, max_length=max_length)
|
||
result = gen(prompt)
|
||
print(result[0]['generated_text'].replace(prompt, ''))
|
||
```
|
||
|
||
## Ethical Considerations and Limitations
|
||
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
|
||
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide) |