Instructions to use artificialguybr/OpenHermesV2-PTBR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use artificialguybr/OpenHermesV2-PTBR with Transformers:

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

pipe = pipeline("text-generation", model="artificialguybr/OpenHermesV2-PTBR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("artificialguybr/OpenHermesV2-PTBR")
model = AutoModelForCausalLM.from_pretrained("artificialguybr/OpenHermesV2-PTBR")
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 Settings

vLLM

How to use artificialguybr/OpenHermesV2-PTBR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "artificialguybr/OpenHermesV2-PTBR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "artificialguybr/OpenHermesV2-PTBR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/artificialguybr/OpenHermesV2-PTBR

SGLang

How to use artificialguybr/OpenHermesV2-PTBR 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 "artificialguybr/OpenHermesV2-PTBR" \
    --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": "artificialguybr/OpenHermesV2-PTBR",
		"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 "artificialguybr/OpenHermesV2-PTBR" \
        --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": "artificialguybr/OpenHermesV2-PTBR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use artificialguybr/OpenHermesV2-PTBR with Docker Model Runner:
```
docker model run hf.co/artificialguybr/OpenHermesV2-PTBR
```

Adding the Open Portuguese LLM Leaderboard Evaluation Results

by leaderboard-pt-pr-bot - opened May 28, 2024

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+25

-6

Files changed (1) hide show

README.md +25 -6

README.md CHANGED Viewed

@@ -1,5 +1,8 @@
 ---
-base_model: mistralai/Mistral-7B-v0.1
 tags:
 - mistral
 - instruct
@@ -8,13 +11,10 @@ tags:
 - gpt4
 - synthetic data
 - distillation
 model-index:
 - name: OpenHermes-2-Mistral-7B-PTBR
   results: []
-license: apache-2.0
-language:
-- en
-- pt
 ---
 # OpenHermes 2 - Mistral 7B - PT BR
@@ -103,4 +103,23 @@ To utilize the prompt format without a system prompt, simply leave the line out.
 Currently, I recommend using LM Studio for chatting with Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
 In LM-Studio, simply select the ChatML Prefix on the settings side pane:
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png)

 ---
+language:
+- en
+- pt
+license: apache-2.0
 tags:
 - mistral
 - instruct
 - gpt4
 - synthetic data
 - distillation
+base_model: mistralai/Mistral-7B-v0.1
 model-index:
 - name: OpenHermes-2-Mistral-7B-PTBR
   results: []
 ---
 # OpenHermes 2 - Mistral 7B - PT BR
 Currently, I recommend using LM Studio for chatting with Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
 In LM-Studio, simply select the ChatML Prefix on the settings side pane:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png)
+# Open Portuguese LLM Leaderboard Evaluation Results
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/artificialguybr/OpenHermesV2-PTBR) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**61.94**|
+|ENEM Challenge (No Images)|    59.90|
+|BLUEX (No Images)         |    48.40|
+|OAB Exams                 |    41.41|
+|Assin2 RTE                |    88.89|
+|Assin2 STS                |    67.61|
+|FaQuAD NLI                |    53.06|
+|HateBR Binary             |    74.77|
+|PT Hate Speech Binary     |    64.38|
+|tweetSentBR               |    59.01|