---
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
- lora
inference: true
widget:
- messages:
  - role: user
    content: What is your favorite condiment?
---
## Training Details
30k chat sessions with a total of <= 1024 tokens were selected from the [sarvamai/samvaad-hi-v1](https://huggingface.co/datasets/sarvamai/samvaad-hi-v1) dataset, with 2k sessions reserved for the test set. The Lora adapter is utilized and fine-tuned using SFT TRL. 
Test set loss:
| Model                 | Loss |
|-----------------------|------|
| Mistral-Hinglish-Instruct | 0.8  |
| Mistral-Instruct       | 1.8  |

## Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.

E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```

This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("arshadshk/Mistral-Hinglish-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("arshadshk/Mistral-Hinglish-7B-Instruct-v0.2")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```