Instructions to use razielAI/Duchifat-2.3-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use razielAI/Duchifat-2.3-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="razielAI/Duchifat-2.3-Instruct", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("razielAI/Duchifat-2.3-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use razielAI/Duchifat-2.3-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "razielAI/Duchifat-2.3-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "razielAI/Duchifat-2.3-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/razielAI/Duchifat-2.3-Instruct

SGLang

How to use razielAI/Duchifat-2.3-Instruct 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 "razielAI/Duchifat-2.3-Instruct" \
    --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": "razielAI/Duchifat-2.3-Instruct",
		"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 "razielAI/Duchifat-2.3-Instruct" \
        --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": "razielAI/Duchifat-2.3-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use razielAI/Duchifat-2.3-Instruct with Docker Model Runner:
```
docker model run hf.co/razielAI/Duchifat-2.3-Instruct
```

Duchifat-2.3-Instruct / README_METADATA.md

razielAI

Upload README_METADATA.md

b211091 verified 7 months ago

preview code

Raw History Blame Contribute Delete

1.72 kB

metadata

language:
  - he
  - en
tags:
  - topai
  - duchifat
  - instruct
  - roleplay
license: apache-2.0
model-index:
  - name: Duchifat-2.3-Instruct
    results:
      - task:
          type: text-generation
          name: arc_easy
        dataset:
          name: arc_easy
          type: arc_easy
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.2769
      - task:
          type: text-generation
          name: hellaswag
        dataset:
          name: hellaswag
          type: hellaswag
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.2594
      - task:
          type: text-generation
          name: piqa
        dataset:
          name: piqa
          type: piqa
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5365
      - task:
          type: text-generation
          name: winogrande
        dataset:
          name: winogrande
          type: winogrande
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5225

Duchifat-2.3-Instruct

Benchmark Results

Tasks	Version	Filter	Metric		Value		Stderr
arc_easy	1	none	acc	↑	0.2769	±	0.0092
		none	acc_norm	↑	0.2786	±	0.0092
hellaswag	1	none	acc	↑	0.2594	±	0.0044
		none	acc_norm	↑	0.2581	±	0.0044
piqa	1	none	acc	↑	0.5365	±	0.0116
		none	acc_norm	↑	0.5082	±	0.0117
winogrande	1	none	acc	↑	0.5225	±	0.0140