Text Generation
Transformers
PyTorch
Safetensors
English
llama
finance
Eval Results (legacy)
text-generation-inference
Instructions to use AdaptLLM/finance-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdaptLLM/finance-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdaptLLM/finance-chat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat") model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdaptLLM/finance-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdaptLLM/finance-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdaptLLM/finance-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdaptLLM/finance-chat
- SGLang
How to use AdaptLLM/finance-chat with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AdaptLLM/finance-chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdaptLLM/finance-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "AdaptLLM/finance-chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdaptLLM/finance-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdaptLLM/finance-chat with Docker Model Runner:
docker model run hf.co/AdaptLLM/finance-chat
debug
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ For example, to chat with the finance model:
|
|
| 23 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 24 |
|
| 25 |
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat")
|
| 26 |
-
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat")
|
| 27 |
|
| 28 |
# Put your input here:
|
| 29 |
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
|
|
@@ -42,7 +42,7 @@ inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_
|
|
| 42 |
outputs = model.generate(input_ids=inputs, max_length=4096)[0]
|
| 43 |
|
| 44 |
answer_start = int(inputs.shape[-1])
|
| 45 |
-
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True
|
| 46 |
|
| 47 |
print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')
|
| 48 |
```
|
|
|
|
| 23 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 24 |
|
| 25 |
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat")
|
| 26 |
+
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat", use_fast=False)
|
| 27 |
|
| 28 |
# Put your input here:
|
| 29 |
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
|
|
|
|
| 42 |
outputs = model.generate(input_ids=inputs, max_length=4096)[0]
|
| 43 |
|
| 44 |
answer_start = int(inputs.shape[-1])
|
| 45 |
+
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)
|
| 46 |
|
| 47 |
print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')
|
| 48 |
```
|