Instructions to use oopere/Llama-FinSent-S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oopere/Llama-FinSent-S with Transformers:

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

pipe = pipeline("text-generation", model="oopere/Llama-FinSent-S")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oopere/Llama-FinSent-S")
model = AutoModelForCausalLM.from_pretrained("oopere/Llama-FinSent-S", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oopere/Llama-FinSent-S with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/oopere/Llama-FinSent-S

SGLang

How to use oopere/Llama-FinSent-S 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 "oopere/Llama-FinSent-S" \
    --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": "oopere/Llama-FinSent-S",
		"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 "oopere/Llama-FinSent-S" \
        --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": "oopere/Llama-FinSent-S",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use oopere/Llama-FinSent-S with Docker Model Runner:
```
docker model run hf.co/oopere/Llama-FinSent-S
```

oopere commited on Feb 2, 2025

Commit

0a34ae8

verified ·

1 Parent(s): ad836f6

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +2 -2
tokenizer_config.json +8 -0

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2501fa8eba4fb3c8aedac0d082a0a83f4e00cc202b0cec96bfc3183d12fc2c
-size 17210090

 version https://git-lfs.github.com/spec/v1
+oid sha256:8a56909fb1196f32c40de7bfc4d8f5220a20c6c9419fa2c0f2f58110ff68d8ee
+size 17210284

tokenizer_config.json CHANGED Viewed

@@ -2047,6 +2047,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",

       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128256": {
+      "content": "<|endofresponse|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "bos_token": "<|begin_of_text|>",