LLama3-Gaja-Hindi-8B-v0.1
Overview
LLama3-Gaja-Hindi-8B-v0.1 is an extension of the Ambari series, a bilingual English/Hindi model developed and released by Cognitivelab.in. This model is specialized for natural language understanding tasks, particularly in the context of instructional pairs. It is built upon the Llama3 8b model, utilizing a fine-tuning process with a curated dataset of translated instructional pairs.
Generate
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import GenerationConfig, TextStreamer , TextIteratorStreamer
model = AutoModelForCausalLM.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1", torch_dtype=torch.bfloat16).to("cuda")
tokenizer = AutoTokenizer.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1", trust_remote_code=True)
# Existing messages list
messages = [
{"role": "system", "content": " You are Gaja, an AI assistant created by Cognitivelab and trained on top of Llama 3 Large language model (LLM), proficient in English and Hindi. You can respond in both languages based on the user's request."},
{"role": "user", "content": "Who are you"}
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
# tokenize=False,
return_tensors="pt"
).to("cuda")
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=tokenizer.convert_tokens_to_ids("<|eot_id|>"),
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
Multi-turn Chat
To use the Ambari-7B-Instruct-v0.1 model, you can follow the example code below:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import GenerationConfig, TextStreamer , TextIteratorStreamer
model = AutoModelForCausalLM.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1", torch_dtype=torch.bfloat16).to("cuda")
tokenizer = AutoTokenizer.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1", trust_remote_code=True)
# Existing messages list
messages = [
{"role": "system", "content": " You are Gaja, an AI assistant created by Cognitivelab and trained on top of Llama 3 Large language model (LLM), proficient in English and Hindi. You can respond in both languages based on the user's request."},
]
# Function to add user input and generate response
def process_user_input(user_input):
global messages
# Add user's input to messages list
messages.append({"role": "user", "content": user_input})
# Prepare the prompt for generation
prompt_formatted_message = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=False
)
# Configure generation parameters
generation_config = GenerationConfig(
repetition_penalty=1.2,
max_new_tokens=8000,
temperature=0.2,
top_p=0.95,
top_k=40,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.convert_tokens_to_ids("<|eot_id|>"),
pad_token_id=tokenizer.pad_token_id,
do_sample=True,
use_cache=True,
return_dict_in_generate=True,
output_attentions=False,
output_hidden_states=False,
output_scores=False,
)
streamer = TextStreamer(tokenizer)
batch = tokenizer(str(prompt_formatted_message.strip()), return_tensors="pt")
print("\033[32mResponse: \033[0m") # Print an empty response
# Generate response
generated = model.generate(
inputs=batch["input_ids"].to("cuda"),
generation_config=generation_config,
streamer=streamer,
)
# Extract and format assistant's response
# print(tokenizer.decode(generated["sequences"].cpu().tolist()[0]))
assistant_response = tokenizer.decode(generated["sequences"].cpu().tolist()[0])
# Find the last occurrence of "assistant" and empty string ("")
assistant_start_index = assistant_response.rfind("<|start_header_id|>assistant<|end_header_id|>")
empty_string_index = assistant_response.rfind("<|eot_id|>")
# Extract the text between the last "assistant" and ""
if assistant_start_index != -1 and empty_string_index != -1:
final_response = assistant_response[assistant_start_index + len("<|start_header_id|>assistant<|end_header_id|>") : empty_string_index]
else:
# final_response = assistant_response # If indices not found, use the whole response
assert "Filed to generate multi turn prompt formate"
# Append the extracted response to the messages list
messages.append({"role": "assistant", "content": final_response})
# messages.append({"role": "assistant", "content": assistant_response})
# Print assistant's response
# print(f"Assistant: {assistant_response}")
# Main interaction loop
while True:
print("=================================================================================")
user_input = input("Input: ") # Prompt user for input
# Check if user_input is empty
if not user_input.strip(): # .strip() removes any leading or trailing whitespace
break # Break out of the loop if input is empty
# Print response placeholder
process_user_input(user_input) # Process user's input and generate response
Prompt formate
system prompt = You are Gaja, an AI assistant created by Cognitivelab and trained on top of Llama 3 Large language model(LLM), proficient in English and Hindi. You can respond in both languages based on the users request.
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Benchmarks
coming soon
Bilingual Instruct Fine-tuning
The model underwent a pivotal stage of supervised fine-tuning with low-rank adaptation, focusing on bilingual instruct fine-tuning. This approach involved training the model to respond adeptly in either English or Hindi based on the language specified in the user prompt or instruction.