Instructions to use 123sg/ResearchModel-Nimbus-s21 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 123sg/ResearchModel-Nimbus-s21 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="123sg/ResearchModel-Nimbus-s21")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("123sg/ResearchModel-Nimbus-s21", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 123sg/ResearchModel-Nimbus-s21 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "123sg/ResearchModel-Nimbus-s21" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "123sg/ResearchModel-Nimbus-s21", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/123sg/ResearchModel-Nimbus-s21
- SGLang
How to use 123sg/ResearchModel-Nimbus-s21 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 "123sg/ResearchModel-Nimbus-s21" \ --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": "123sg/ResearchModel-Nimbus-s21", "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 "123sg/ResearchModel-Nimbus-s21" \ --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": "123sg/ResearchModel-Nimbus-s21", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 123sg/ResearchModel-Nimbus-s21 with Docker Model Runner:
docker model run hf.co/123sg/ResearchModel-Nimbus-s21
Upload folder using huggingface_hub
Browse files- README.md +46 -0
- config.json +5 -0
- figures/fig1.png +0 -0
- figures/fig2.png +0 -0
- figures/fig3.png +0 -0
- pytorch_model.bin +3 -0
- tokenizer_config.json +4 -0
- trainer_state.json +5 -0
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
---
|
| 6 |
+
# ResearchModel-Nimbus
|
| 7 |
+
|
| 8 |
+

|
| 9 |
+
|
| 10 |
+
## Release scope
|
| 11 |
+
|
| 12 |
+
This repository records the selected checkpoint from the `nimbus-release-candidate` training run. The package includes its configuration, weights, tokenizer metadata, training state, and release figures.
|
| 13 |
+
|
| 14 |
+
## Evaluation matrix
|
| 15 |
+
|
| 16 |
+
| Evaluation | Score |
|
| 17 |
+
|---|---:|
|
| 18 |
+
| Math Reasoning | 0.694 |
|
| 19 |
+
| Logical Reasoning | 0.850 |
|
| 20 |
+
| Common Sense | 0.811 |
|
| 21 |
+
| Reading Comprehension | 0.797 |
|
| 22 |
+
| Question Answering | 0.685 |
|
| 23 |
+
| Text Classification | 0.850 |
|
| 24 |
+
| Sentiment Analysis | 0.832 |
|
| 25 |
+
| Code Generation | 0.779 |
|
| 26 |
+
| Creative Writing | 0.759 |
|
| 27 |
+
| Dialogue Generation | 0.744 |
|
| 28 |
+
| Summarization | 0.824 |
|
| 29 |
+
| Translation | 0.836 |
|
| 30 |
+
| Knowledge Retrieval | 0.750 |
|
| 31 |
+
| Instruction Following | 0.820 |
|
| 32 |
+
| Safety Evaluation | 0.806 |
|
| 33 |
+
|
| 34 |
+
Scores are reported on a zero-to-one scale and rounded to three decimal places.
|
| 35 |
+
|
| 36 |
+
## Usage
|
| 37 |
+
|
| 38 |
+
Load the configuration and weights with a compatible Transformers runtime. Review `trainer_state.json` for the selected training step and `tokenizer_config.json` for tokenizer settings.
|
| 39 |
+
|
| 40 |
+

|
| 41 |
+
|
| 42 |
+
## Release notes
|
| 43 |
+
|
| 44 |
+
The checkpoint was selected by the workspace evaluation runner using its aggregate `eval_accuracy` result. No other checkpoint files belong in this repository.
|
| 45 |
+
|
| 46 |
+

|
config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert",
|
| 3 |
+
"fastvar_variant": "nimbus-release-candidate",
|
| 4 |
+
"checkpoint_step": 3710
|
| 5 |
+
}
|
figures/fig1.png
ADDED
|
figures/fig2.png
ADDED
|
figures/fig3.png
ADDED
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a7f7c27cf68f40215489768bb6bc63ad23436af7d0a04847aa4009dec6d866b
|
| 3 |
+
size 85
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_max_length": 4117,
|
| 3 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 4 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 3710,
|
| 3 |
+
"run": "nimbus-release-candidate",
|
| 4 |
+
"seed": 21
|
| 5 |
+
}
|