Instructions to use Jagneshdeveloper/Ekant-14b-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jagneshdeveloper/Ekant-14b-small with Transformers:

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

pipe = pipeline("text-generation", model="Jagneshdeveloper/Ekant-14b-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jagneshdeveloper/Ekant-14b-small")
model = AutoModelForCausalLM.from_pretrained("Jagneshdeveloper/Ekant-14b-small", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jagneshdeveloper/Ekant-14b-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jagneshdeveloper/Ekant-14b-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jagneshdeveloper/Ekant-14b-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jagneshdeveloper/Ekant-14b-small

SGLang

How to use Jagneshdeveloper/Ekant-14b-small 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 "Jagneshdeveloper/Ekant-14b-small" \
    --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": "Jagneshdeveloper/Ekant-14b-small",
		"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 "Jagneshdeveloper/Ekant-14b-small" \
        --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": "Jagneshdeveloper/Ekant-14b-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jagneshdeveloper/Ekant-14b-small with Docker Model Runner:
```
docker model run hf.co/Jagneshdeveloper/Ekant-14b-small
```

Jagneshdeveloper commited on 8 days ago

Commit

e73eb8e

verified ·

1 Parent(s): efbded6

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -49,7 +49,7 @@ Built on top of the powerful **microsoft/phi-4** architecture, this model has be
 ## 🔬 Fusing & Pipeline Lifecycle
 This model was compiled under a strict resource-constrained hardware architecture using custom disk-free sharded watchdog pipelines to guarantee full float precision mapping without accuracy loss:
-1. **LoRA Fine-Tuning**: Initial specialized instruction sets were targeted and compiled into low-rank matrix sub-layers (`akant-adaptet`).
 2. **Base Integration**: Unquantized adapter weights were chemically baked directly back into the core 29.3GB `microsoft/phi-4` tensor layers.
 3. **Vanilla Alignment**: Merged via **SLERP** (Spherical Linear Interpolation) at a calibrated `0.6/0.4` ratio back with the foundational base model to act as a stabilizing anchor and counteract catastrophic forgetting.
 4. **Deep Reasoning Injection**: Fused via **TIES** (Trimming, Electing, and Merging) to combine our custom capabilities directly with reinforcement-learned o3-style logic pathways.
@@ -83,7 +83,7 @@ You can quickly load and deploy **Ekant-14B-small** using the Hugging Face `tran
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-model_name = "Jagneshdeveloper/ultimate-Ekant-14b"
 # Load the optimized tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_name)

 ## 🔬 Fusing & Pipeline Lifecycle
 This model was compiled under a strict resource-constrained hardware architecture using custom disk-free sharded watchdog pipelines to guarantee full float precision mapping without accuracy loss:
+1. **LoRA Fine-Tuning**: Initial specialized instruction sets were targeted and compiled into low-rank matrix sub-layers (`ekant-adapter`).
 2. **Base Integration**: Unquantized adapter weights were chemically baked directly back into the core 29.3GB `microsoft/phi-4` tensor layers.
 3. **Vanilla Alignment**: Merged via **SLERP** (Spherical Linear Interpolation) at a calibrated `0.6/0.4` ratio back with the foundational base model to act as a stabilizing anchor and counteract catastrophic forgetting.
 4. **Deep Reasoning Injection**: Fused via **TIES** (Trimming, Electing, and Merging) to combine our custom capabilities directly with reinforcement-learned o3-style logic pathways.
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+model_name = "Jagneshdeveloper/Ekant-14b-small"
 # Load the optimized tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_name)