Quantizations of https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B

From original readme

Prompt Format

System: {System}

{Context}

User: {Question}

Assistant: {Response}

User: {Question}

Assistant:

How to use

take the whole document as context

This can be applied to the scenario where the whole document can be fitted into the model, so that there is no need to run retrieval over the document.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "nvidia/Llama3-ChatQA-1.5-8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

messages = [
    {"role": "user", "content": "what is the percentage change of the net income from Q4 FY23 to Q4 FY24?"}
]

document = """NVIDIA (NASDAQ: NVDA) today reported revenue for the fourth quarter ended January 28, 2024, of $22.1 billion, up 22% from the previous quarter and up 265% from a year ago.\nFor the quarter, GAAP earnings per diluted share was $4.93, up 33% from the previous quarter and up 765% from a year ago. Non-GAAP earnings per diluted share was $5.16, up 28% from the previous quarter and up 486% from a year ago.\nQ4 Fiscal 2024 Summary\nGAAP\n| $ in millions, except earnings per share | Q4 FY24 | Q3 FY24 | Q4 FY23 | Q/Q | Y/Y |\n| Revenue | $22,103 | $18,120 | $6,051 | Up 22% | Up 265% |\n| Gross margin | 76.0% | 74.0% | 63.3% | Up 2.0 pts | Up 12.7 pts |\n| Operating expenses | $3,176 | $2,983 | $2,576 | Up 6% | Up 23% |\n| Operating income | $13,615 | $10,417 | $1,257 | Up 31% | Up 983% |\n| Net income | $12,285 | $9,243 | $1,414 | Up 33% | Up 769% |\n| Diluted earnings per share | $4.93 | $3.71 | $0.57 | Up 33% | Up 765% |"""

def get_formatted_input(messages, context):
    system = "System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context."
    instruction = "Please give a full and complete answer for the question."

    for item in messages:
        if item['role'] == "user":
            ## only apply this instruction for the first user turn
            item['content'] = instruction + " " + item['content']
            break

    conversation = '\n\n'.join(["User: " + item["content"] if item["role"] == "user" else "Assistant: " + item["content"] for item in messages]) + "\n\nAssistant:"
    formatted_input = system + "\n\n" + context + "\n\n" + conversation
    
    return formatted_input

formatted_input = get_formatted_input(messages, document)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(input_ids=tokenized_prompt.input_ids, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=128, eos_token_id=terminators)

response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

run retrieval to get top-n chunks as context

This can be applied to the scenario when the document is very long, so that it is necessary to run retrieval. Here, we use our Dragon-multiturn retriever which can handle conversatinoal query. In addition, we provide a few documents for users to play with.

from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModel
import torch
import json

## load ChatQA-1.5 tokenizer and model
model_id = "nvidia/Llama3-ChatQA-1.5-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

## load retriever tokenizer and model
retriever_tokenizer = AutoTokenizer.from_pretrained('nvidia/dragon-multiturn-query-encoder')
query_encoder = AutoModel.from_pretrained('nvidia/dragon-multiturn-query-encoder')
context_encoder = AutoModel.from_pretrained('nvidia/dragon-multiturn-context-encoder')

## prepare documents, we take landrover car manual document that we provide as an example
chunk_list = json.load(open("docs.json"))['landrover']

messages = [
    {"role": "user", "content": "how to connect the bluetooth in the car?"}
]

### running retrieval
## convert query into a format as follows:
## user: {user}\nagent: {agent}\nuser: {user}
formatted_query_for_retriever = '\n'.join([turn['role'] + ": " + turn['content'] for turn in messages]).strip()

query_input = retriever_tokenizer(formatted_query_for_retriever, return_tensors='pt')
ctx_input = retriever_tokenizer(chunk_list, padding=True, truncation=True, max_length=512, return_tensors='pt')
query_emb = query_encoder(**query_input).last_hidden_state[:, 0, :]
ctx_emb = context_encoder(**ctx_input).last_hidden_state[:, 0, :]

## Compute similarity scores using dot product and rank the similarity
similarities = query_emb.matmul(ctx_emb.transpose(0, 1)) # (1, num_ctx)
ranked_results = torch.argsort(similarities, dim=-1, descending=True) # (1, num_ctx)

## get top-n chunks (n=5)
retrieved_chunks = [chunk_list[idx] for idx in ranked_results.tolist()[0][:5]]
context = "\n\n".join(retrieved_chunks)

### running text generation
formatted_input = get_formatted_input(messages, context)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(input_ids=tokenized_prompt.input_ids, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=128, eos_token_id=terminators)

response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))