Instructions to use shah-shazid-askary/amd-finance-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shah-shazid-askary/amd-finance-llm with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shah-shazid-askary/amd-finance-llm")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shah-shazid-askary/amd-finance-llm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shah-shazid-askary/amd-finance-llm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shah-shazid-askary/amd-finance-llm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shah-shazid-askary/amd-finance-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shah-shazid-askary/amd-finance-llm

SGLang

How to use shah-shazid-askary/amd-finance-llm 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 "shah-shazid-askary/amd-finance-llm" \
    --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": "shah-shazid-askary/amd-finance-llm",
		"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 "shah-shazid-askary/amd-finance-llm" \
        --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": "shah-shazid-askary/amd-finance-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shah-shazid-askary/amd-finance-llm with Docker Model Runner:
```
docker model run hf.co/shah-shazid-askary/amd-finance-llm
```

shah-shazid-askary commited on May 7

Commit

d501fd4

verified ·

1 Parent(s): dfc5ead

Update ML Intern artifact metadata

Browse files

Files changed (1) hide show

README.md +23 -0

README.md CHANGED Viewed

@@ -1,3 +1,7 @@
 # AMD Finance LLM — Domain-Specialized on ROCm MI300X
 A domain-specific LLM fine-tuned for finance on AMD Instinct MI300X via ROCm, Optimum-AMD, and vLLM.
@@ -15,3 +19,22 @@ A domain-specific LLM fine-tuned for finance on AMD Instinct MI300X via ROCm, Op
 ## Citation

+---
+tags:
+- ml-intern
+---
 # AMD Finance LLM — Domain-Specialized on ROCm MI300X
 A domain-specific LLM fine-tuned for finance on AMD Instinct MI300X via ROCm, Optimum-AMD, and vLLM.
 ## Citation
+<!-- ml-intern-provenance -->
+## Generated by ML Intern
+This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.
+- Try ML Intern: https://smolagents-ml-intern.hf.space
+- Source code: https://github.com/huggingface/ml-intern
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = 'shah-shazid-askary/amd-finance-llm'
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+```
+For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.