metadata
license: apache-2.0
library_name: peft
tags:
- trl
- orpo
- unsloth
- generated_from_trainer
base_model: cognitivecomputations/dolphin-2.9.1-yi-1.5-9b
model-index:
- name: Finance_dolphin-2.9.1-yi-1.5-9b
results: []
This model is a fine-tuned version of cognitivecomputations/dolphin-2.9.1-yi-1.5-9b on an unknown dataset.
This content is strictly for educational purposes and should not be construed as financial advice. Please exercise caution when applying any information provided.
Uploaded model
- Developed by: baconnier
- License: apache-2.0
- Finetuned from model : cognitivecomputations/dolphin-2.9-llama3-8b
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
This model was trained ORPO , using ChatML prompt template format.
<|im_start|>user
Act as an exotic structurator and do not hesitate to merge standard and exotic products.
Currently, inflation is 5% and 1-year swaps are valued at 6%.
I expect inflation to reach 15% by the end of the year.
Can you create the 10 most complicated structured derivative products to handle this scenario?
Rank them by profitability, give me a score for profitability and another for risk from 0 to 10.
Add an explaination for each structured products in maximum of 3 sentences.
Think step by step and give me a concise, bulleted answer.<|im_end|>
<|im_start|>assistant
Example with local TGI:
See the snippet below for usage with local inference:
#Example: reuse your existing OpenAI setup
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8080/v1", api_key="TGI")
completion = client.chat.completions.create(
model="baconnier/Finance_dolphin-2.9.1-yi-1.5-9b",
messages=[
{"role": "system", "content": "Act as a senior banker answering in 3 sentences in bullet points format."},
{"role": "user", "content": " What is CDS compare it to a swap "},
{"role": "assistant", "content": ""}
],
max_tokens=400,
temperature=0.7,
)
print(completion.choices[0].message.content)
Output:
CDS:
- Credit Default Swap (CDS) is a financial derivative contract between two parties (buyer and seller) for insurance against default or credit risk associated with a bond or loan
- Protection buyer pays a premium to protection seller in exchange for the right to receive payment if a credit event occurs
- Protection seller is usually a financial institution, while protection buyer can be an investor or a bank
Swap:
- Swap is an agreement between two parties to exchange cash flows, typically interest payments or principal at a future date
- Common types of swaps include interest rate swaps, currency swaps, and commodity swaps
CDS differs from swaps as it focuses on credit risk protection, while swaps involve cash flow exchange.
Example with Transformers and pipeline:
See the snippet below for usage with Transformers:
import transformers
import torch
model_id = "baconnier/Finance_dolphin-2.9.1-yi-1.5-9b"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda",
)
messages = [
{"role": "user", "content": '''Act as an exotic structurator and do not hesitate to merge standard and exotic products.
Currently, inflation is 5% and 1-year swaps are valued at 6%.
I expect inflation to reach 15% by the end of the year.
Can you create the 10 most complicated structured derivative products to handle this scenario?
Rank them by profitability, give me a score for profitability and another for risk from 0 to 10.
Add an explaination for each structured products in maximum of 3 sentences.
Think step by step and give me a concise, bulleted answer.'''},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
outputs = pipeline(
prompt,
max_new_tokens=256,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
Answer:
To handle the scenario of inflation reaching 15% by the end of the year, I can create the following 10 most complicated structured derivative products, ranked by profitability and risk:
1. Inflation-linked swap spread strategy (Profitability: 9, Risk: 7)
- Buy 1-year swaps and sell 15-year swaps to profit from the expected inflation increase.
- Risk is moderate due to interest rate and inflation rate changes.
2. Inflation-linked bond spread strategy (Profitability: 8, Risk: 6)
- Buy inflation-linked bonds and sell conventional bonds to profit from the inflation increase.
- Risk is lower than the swap spread strategy due to the fixed maturity of bonds.
3. Inflation-linked option strategy (Profitability: 7, Risk: 5)
- Buy call options on inflation-linked bonds to profit from the expected inflation increase.
- Risk is lower than the swap spread strategy due to the limited downside.
4. Inflation-linked credit spread strategy (Profitability: 6, Risk: 4)
- Buy high-yield inflation-linked bonds and sell investment-grade inflation-linked bonds to profit from the expected inflation increase.
- Risk is moderate due to credit risk and interest rate changes.
5. Inflation-linked swap straddle strategy (Profitability: 5, Risk: 3)
- Buy and sell 1-year and 15-year inflation swaps simultaneously to profit from the expected inflation increase.
- Risk is moderate due to interest rate and inflation rate changes.
6. Inflation-linked bond straddle strategy (Profitability: 4, Risk: 2)
- Buy and sell inflation-linked bonds with different maturities to profit from the expected inflation increase.
- Risk is lower than the swap straddle strategy due to the fixed maturity of bonds.
7. Inflation-linked option straddle strategy (Profitability: 3, Risk: 1)
- Buy and sell call options on inflation-linked bonds with different maturities to profit from the expected inflation increase.
- Risk is lower than the swap straddle strategy due to the limited downside.
8. Inflation-linked credit spread straddle strategy (Profitability: 2, Risk: 0)
- Buy and sell high-yield and investment-grade inflation-linked bonds with different maturities to profit from the expected inflation increase.
- Risk is low due to the fixed maturity of bonds and the limited downside.
9. Inflation-linked swap spread strangle strategy (Profitability: 1, Risk: -1)
- Buy and sell 1-year and 15-year inflation swaps with different strike prices to profit from the expected inflation increase.
- Risk is high due to interest rate and inflation rate changes.
10. Inflation-linked bond spread strangle strategy (Profitability: 0, Risk: -2)
- Buy and sell inflation-linked bonds with different strike prices to profit from the expected inflation increase.
- Risk is very high due to the limited downside and the potential for significant losses.
The most profitable strategies are the inflation-linked swap spread strategy and the inflation-linked bond spread strategy, with a profitability score of 9 and 8, respectively.
The least profitable strategy is the inflation-linked bond spread strangle strategy, with a profitability score of 0.
The most risky strategies are the inflation-linked swap spread strangle strategy and the inflation-linked bond spread strangle strategy, with a risk score of -1 and -2, respectively.
The least risky strategy is the inflation-linked credit spread straddle strategy, with a risk score of 0.
The 10 most complicated structured derivative products to handle the scenario of inflation reaching 15% by the end of the year are ranked by profitability and risk.
The most profitable strategies are the inflation-linked swap spread strategy and the inflation-linked bond spread strategy, with a profitability score of 9 and 8, respectively.
The least profitable strategy is the inflation-linked bond spread strangle strategy, with a profitability score of 0.
The most risky strategies are the inflation-linked swap spread strangle strategy and the inflation-linked bond spread strangle strategy, with a risk score of -1 and -2, respectively.
The least risky strategy is the inflation-linked credit spread straddle strategy, with a risk score of 0.
Example with Transformers:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("baconnier/Finance_dolphin-2.9.1-yi-1.5-9b")
model = AutoModelForCausalLM.from_pretrained("baconnier/Finance_dolphin-2.9.1-yi-1.5-9b")
prompt = "What is CDS compare it to a swap"
inputs = tokenizer(prompt, return_tensors="pt")
# Generate
generate_ids = model.generate(inputs.input_ids, max_length=200)
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]