Instructions to use gradientai/v-alpha-tross with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gradientai/v-alpha-tross with Transformers:

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

pipe = pipeline("text-generation", model="gradientai/v-alpha-tross")

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

tokenizer = AutoTokenizer.from_pretrained("gradientai/v-alpha-tross")
model = AutoModelForCausalLM.from_pretrained("gradientai/v-alpha-tross", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gradientai/v-alpha-tross with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/gradientai/v-alpha-tross

SGLang

How to use gradientai/v-alpha-tross 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 "gradientai/v-alpha-tross" \
    --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": "gradientai/v-alpha-tross",
		"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 "gradientai/v-alpha-tross" \
        --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": "gradientai/v-alpha-tross",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gradientai/v-alpha-tross with Docker Model Runner:
```
docker model run hf.co/gradientai/v-alpha-tross
```

leo-pekelis-gradient commited on Feb 14, 2024

Commit

b308187

verified ·

1 Parent(s): d91ea5b

Update README.md

Browse files

Files changed (1) hide show

README.md +73 -1

README.md CHANGED Viewed

@@ -4,7 +4,79 @@ tags:
 - finance
 model-index:
 - name: completed-model
-  results: []
 license: llama2
 language:
 - en

 - finance
 model-index:
 - name: completed-model
+  results:
+    - task:
+        type: text-generation
+      dataset:
+        name: ai2_arc
+        type: ai2_arc
+      metrics:
+        - name: AI2 Reasoning Challenge (25-Shot)
+          type: AI2 Reasoning Challenge (25-Shot)
+          value: 71.93
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+    - task:
+        type: text-generation
+      dataset:
+        name: hellaswag
+        type: hellaswag
+      metrics:
+        - name: HellaSwag (10-shot)
+          type: HellaSwag (10-shot)
+          value: 86.82
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+    - task:
+        type: text-generation
+      dataset:
+        name: multiple
+        type: miltiple
+      metrics:
+        - name: MMLU (5-shot)
+          type: MMLU (5-shot)
+          value: 70.38
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+    - task:
+        type: text-generation
+      dataset:
+        name: truthful_qa
+        type: truthful_qa
+      metrics:
+        - name: TruthfulQA (0-shot)
+          type: TruthfulQA (0-shot)
+          value: 65.21
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+    - task:
+        type: text-generation
+      dataset:
+        name: winogrande
+        type: winogrande
+      metrics:
+        - name: Winogrande (5-shot)
+          type: Winogrande (5-shot)
+          value: 83.58
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+    - task:
+        type: text-generation
+      dataset:
+        name: gsm8k
+        type: gsm8k
+      metrics:
+        - name: GSM8k (5-shot)
+          type: GSM8k (5-shot)
+          value: 61.79
+      source:
+        name: Open LLM Leaderboard
+        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
 license: llama2
 language:
 - en