Instructions to use teknium/OpenHermes-2.5-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teknium/OpenHermes-2.5-Mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="teknium/OpenHermes-2.5-Mistral-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B")
model = AutoModelForCausalLM.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teknium/OpenHermes-2.5-Mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teknium/OpenHermes-2.5-Mistral-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teknium/OpenHermes-2.5-Mistral-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/teknium/OpenHermes-2.5-Mistral-7B

SGLang

How to use teknium/OpenHermes-2.5-Mistral-7B 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 "teknium/OpenHermes-2.5-Mistral-7B" \
    --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": "teknium/OpenHermes-2.5-Mistral-7B",
		"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 "teknium/OpenHermes-2.5-Mistral-7B" \
        --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": "teknium/OpenHermes-2.5-Mistral-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use teknium/OpenHermes-2.5-Mistral-7B with Docker Model Runner:
```
docker model run hf.co/teknium/OpenHermes-2.5-Mistral-7B
```

Axolotl prompt format (sharegpt, chatml) could differ from yours

#13

by timlim123 - opened Dec 7, 2023

Discussion

timlim123

Dec 7, 2023

•

edited Dec 7, 2023

Hi @teknium ,

I believe you trained using axolotl with this dataset config:

datasets:
  - path: /data/chat_data/full_dataset_chat.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: last_run_prepared

Did you realised that Axolotl actually adds an extra linebreak (somehow) and it becomes <|im_end|>\n\n ? or did you create your own custom dataset and dataloader? Hope to see your release of the configuration file and dataset format.

I found out by debugging step-by-step to run through the repo, the last few label tokens will be always be [....., 28766, 321, 28730, 416, 28766, 28767, 13, 13, 2] which when decoded is <|im_end|>\n\n</s>.

Issue could be here (extra \n in sep): https://github.com/OpenAccess-AI-Collective/axolotl/blob/a48dbf6561cc74c275a48070f397334a2c367dd5/src/axolotl/prompt_strategies/sharegpt.py#L16

teknium

Owner Dec 12, 2023

Hi @teknium ,

I believe you trained using axolotl with this dataset config:
datasets:
  - path: /data/chat_data/full_dataset_chat.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: last_run_prepared
Did you realised that Axolotl actually adds an extra linebreak (somehow) and it becomes <|im_end|>\n\n ? or did you create your own custom dataset and dataloader? Hope to see your release of the configuration file and dataset format.

I found out by debugging step-by-step to run through the repo, the last few label tokens will be always be [....., 28766, 321, 28730, 416, 28766, 28767, 13, 13, 2] which when decoded is <|im_end|>\n\n</s>.

Issue could be here (extra \n in sep): https://github.com/OpenAccess-AI-Collective/axolotl/blob/a48dbf6561cc74c275a48070f397334a2c367dd5/src/axolotl/prompt_strategies/sharegpt.py#L16

I believe they changed things for chatml format after this was trained

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment