Text Generation
Transformers
PyTorch
English
llama
llama-2
instruct
finetune
alpaca
gpt4
synthetic data
distillation
text-generation-inference
Instructions to use teknium/OpenHermes-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teknium/OpenHermes-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="teknium/OpenHermes-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("teknium/OpenHermes-13B") model = AutoModelForCausalLM.from_pretrained("teknium/OpenHermes-13B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use teknium/OpenHermes-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "teknium/OpenHermes-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "teknium/OpenHermes-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/teknium/OpenHermes-13B
- SGLang
How to use teknium/OpenHermes-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 "teknium/OpenHermes-13B" \ --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": "teknium/OpenHermes-13B", "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 "teknium/OpenHermes-13B" \ --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": "teknium/OpenHermes-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use teknium/OpenHermes-13B with Docker Model Runner:
docker model run hf.co/teknium/OpenHermes-13B
Adding Evaluation Results
#2
by AbrorBalxiyev - opened
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- llama-2
|
| 5 |
- instruct
|
|
@@ -8,14 +10,12 @@ tags:
|
|
| 8 |
- gpt4
|
| 9 |
- synthetic data
|
| 10 |
- distillation
|
|
|
|
| 11 |
datasets:
|
| 12 |
- teknium/openhermes
|
| 13 |
model-index:
|
| 14 |
- name: openhermes-13b
|
| 15 |
results: []
|
| 16 |
-
license: mit
|
| 17 |
-
language:
|
| 18 |
-
- en
|
| 19 |
---
|
| 20 |
|
| 21 |
# OpenHermes-13B
|
|
@@ -155,4 +155,17 @@ The following hyperparameters were used during training:
|
|
| 155 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 156 |
- lr_scheduler_type: cosine
|
| 157 |
- lr_scheduler_warmup_steps: 300
|
| 158 |
-
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: mit
|
| 5 |
tags:
|
| 6 |
- llama-2
|
| 7 |
- instruct
|
|
|
|
| 10 |
- gpt4
|
| 11 |
- synthetic data
|
| 12 |
- distillation
|
| 13 |
+
base_model: NousResearch/Llama-2-13b-hf
|
| 14 |
datasets:
|
| 15 |
- teknium/openhermes
|
| 16 |
model-index:
|
| 17 |
- name: openhermes-13b
|
| 18 |
results: []
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# OpenHermes-13B
|
|
|
|
| 155 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 156 |
- lr_scheduler_type: cosine
|
| 157 |
- lr_scheduler_warmup_steps: 300
|
| 158 |
+
- num_epochs: 3
|
| 159 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 160 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/teknium__OpenHermes-13B-details)
|
| 161 |
+
|
| 162 |
+
| Metric |Value|
|
| 163 |
+
|-------------------|----:|
|
| 164 |
+
|Avg. |12.18|
|
| 165 |
+
|IFEval (0-Shot) |26.68|
|
| 166 |
+
|BBH (3-Shot) |18.21|
|
| 167 |
+
|MATH Lvl 5 (4-Shot)| 1.21|
|
| 168 |
+
|GPQA (0-shot) | 3.02|
|
| 169 |
+
|MuSR (0-shot) | 8.53|
|
| 170 |
+
|MMLU-PRO (5-shot) |15.44|
|
| 171 |
+
|