Text Generation
Transformers
Safetensors
English
qwen2
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use M4-ai/NeuralReyna-Mini-1.8B-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use M4-ai/NeuralReyna-Mini-1.8B-v0.3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="M4-ai/NeuralReyna-Mini-1.8B-v0.3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("M4-ai/NeuralReyna-Mini-1.8B-v0.3") model = AutoModelForCausalLM.from_pretrained("M4-ai/NeuralReyna-Mini-1.8B-v0.3", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use M4-ai/NeuralReyna-Mini-1.8B-v0.3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "M4-ai/NeuralReyna-Mini-1.8B-v0.3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "M4-ai/NeuralReyna-Mini-1.8B-v0.3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/M4-ai/NeuralReyna-Mini-1.8B-v0.3
- SGLang
How to use M4-ai/NeuralReyna-Mini-1.8B-v0.3 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 "M4-ai/NeuralReyna-Mini-1.8B-v0.3" \ --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": "M4-ai/NeuralReyna-Mini-1.8B-v0.3", "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 "M4-ai/NeuralReyna-Mini-1.8B-v0.3" \ --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": "M4-ai/NeuralReyna-Mini-1.8B-v0.3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use M4-ai/NeuralReyna-Mini-1.8B-v0.3 with Docker Model Runner:
docker model run hf.co/M4-ai/NeuralReyna-Mini-1.8B-v0.3
|
Download README.md from M4-ai/NeuralReyna-Mini-1.8B-v0.3: direct link, hf CLI and curl.
- Browser
- Download file 4.23 kB
-
https://huggingface.co/M4-ai/NeuralReyna-Mini-1.8B-v0.3/resolve/main/README.md
- Command line
-
hf download hf://M4-ai/NeuralReyna-Mini-1.8B-v0.3/README.md
-
curl -L -o README.md https://huggingface.co/M4-ai/NeuralReyna-Mini-1.8B-v0.3/resolve/main/README.md
4.23 kB
metadata
language:
- en
license: apache-2.0
datasets:
- argilla/OpenHermes2.5-dpo-binarized-alpha
- Locutusque/Hercules-v3.0
inference:
parameters:
do_sample: true
temperature: 0.8
top_p: 0.95
top_k: 40
min_new_tokens: 2
max_new_tokens: 250
repetition_penalty: 1.1
model-index:
- name: NeuralReyna-Mini-1.8B-v0.3
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 35.58
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 61.13
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 44.22
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 41.99
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 60.93
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 6.75
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
name: Open LLM Leaderboard
NeuralReyna-Mini-1.8B-v0.3
Description
Taken aloobun/Reyna-Mini-1.8B-v0.2 and further fine-tuned it using DPO using the argilla/OpenHermes2.5-dpo-binarized-alpha.
This model has capabilities in coding, math, science, roleplay, and function calling.
This model was trained on OpenAI's ChatML prompt format.
Quants
HQQ - https://huggingface.co/twoxfh/NeuralReyna-Mini-hqq-1.8B-v0.3
Evaluation
Coming soon
Contributions
Thanks to @aloobun and @Locutusque for their contributions to this model.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 41.77 |
| AI2 Reasoning Challenge (25-Shot) | 35.58 |
| HellaSwag (10-Shot) | 61.13 |
| MMLU (5-Shot) | 44.22 |
| TruthfulQA (0-shot) | 41.99 |
| Winogrande (5-shot) | 60.93 |
| GSM8k (5-shot) | 6.75 |