Instructions to use firef1i/finbasic2-llama2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use firef1i/finbasic2-llama2-13b with Transformers:

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

pipe = pipeline("text-generation", model="firef1i/finbasic2-llama2-13b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("firef1i/finbasic2-llama2-13b")
model = AutoModelForCausalLM.from_pretrained("firef1i/finbasic2-llama2-13b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use firef1i/finbasic2-llama2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "firef1i/finbasic2-llama2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "firef1i/finbasic2-llama2-13b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/firef1i/finbasic2-llama2-13b

SGLang

How to use firef1i/finbasic2-llama2-13b 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 "firef1i/finbasic2-llama2-13b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "firef1i/finbasic2-llama2-13b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "firef1i/finbasic2-llama2-13b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "firef1i/finbasic2-llama2-13b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use firef1i/finbasic2-llama2-13b with Docker Model Runner:
```
docker model run hf.co/firef1i/finbasic2-llama2-13b
```

firef1i commited on Dec 1, 2023

Commit

fb3f7d6

1 Parent(s): 3c99847

Upload LlamaForCausalLM

Browse files

Files changed (11) hide show

model-00001-of-00011.safetensors +1 -1
model-00002-of-00011.safetensors +1 -1
model-00003-of-00011.safetensors +1 -1
model-00004-of-00011.safetensors +1 -1
model-00005-of-00011.safetensors +1 -1
model-00006-of-00011.safetensors +1 -1
model-00007-of-00011.safetensors +1 -1
model-00008-of-00011.safetensors +1 -1
model-00009-of-00011.safetensors +1 -1
model-00010-of-00011.safetensors +1 -1
model-00011-of-00011.safetensors +1 -1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04511b22f8cade2e3702a96eec6ab7d6056bc8e4485229fadce626a1ee7483b2
 size 4881247856

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e6439ff5799d830a0cbf67b20b52593d7cbc0918b189a272f7e8b3b25516a4
 size 4970418112

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85b9f2c8c70007aabb5917e3b831c9a18d58157431f3a5c41d986655a511fbb
 size 4970418120

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a923c8ee80f46eea643b674b99c8cc7c2e990ffae2ddff8d25305ec20e4f7407
 size 4970418144

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e13935b540a77631246a51cccde1406c5245fc9d9189ca305664498d1006d5
 size 4970418144

 version https://git-lfs.github.com/spec/v1
+oid sha256:ab7546cd4dfb9bfb6fd973700ce19d2195d52f6466f8585da2ee350883c0fc0d
 size 4792119040

 version https://git-lfs.github.com/spec/v1
+oid sha256:e027fc30c05e813cd12713fd009eda25a35a38af90d7e7fb09600fe1d7531390
 size 4792160232

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ae5c3c72e309e370e58e2f53ae444835e1074a54ac78afd29dcd21370b65b51
 size 4792160224

 version https://git-lfs.github.com/spec/v1
+oid sha256:83c1ce98ede06bdd45c9de44772da92d16053a131e39d89e8220ab8497595c57
 size 2983303184