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 Aug 19

Commit

e89ff4c

verified ·

1 Parent(s): c614cae

Upload model.safetensors.index.json with huggingface_hub

Browse files

Files changed (1) hide show

model.safetensors.index.json +44 -1

model.safetensors.index.json CHANGED Viewed

@@ -3,7 +3,50 @@
     "total_size": 29000000000
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-1.safetensors",
     "model.norm.weight": "model-9.safetensors",
     "lm_head.weight": "model-9.safetensors",
     "model.layers.0.self_attn.qkv_proj.weight": "model-1.safetensors",

     "total_size": 29000000000
   },
   "weight_map": {
+    "model.embed_tokens.weight": [
+      "model-1.safetensors",
+      "model-10.safetensors",
+      "model-11.safetensors",
+      "model-12.safetensors",
+      "model-13.safetensors",
+      "model-14.safetensors",
+      "model-15.safetensors",
+      "model-16.safetensors",
+      "model-17.safetensors",
+      "model-18.safetensors",
+      "model-19.safetensors",
+      "model-2.safetensors",
+      "model-20.safetensors",
+      "model-21.safetensors",
+      "model-22.safetensors",
+      "model-23.safetensors",
+      "model-24.safetensors",
+      "model-25.safetensors",
+      "model-26.safetensors",
+      "model-27.safetensors",
+      "model-28.safetensors",
+      "model-29.safetensors",
+      "model-3.safetensors",
+      "model-30.safetensors",
+      "model-31.safetensors",
+      "model-32.safetensors",
+      "model-33.safetensors",
+      "model-34.safetensors",
+      "model-35.safetensors",
+      "model-36.safetensors",
+      "model-37.safetensors",
+      "model-38.safetensors",
+      "model-39.safetensors",
+      "model-4.safetensors",
+      "model-40.safetensors",
+      "model-41.safetensors",
+      "model-42.safetensors",
+      "model-5.safetensors",
+      "model-6.safetensors",
+      "model-7.safetensors",
+      "model-8.safetensors",
+      "model-9.safetensors"
+    ],
     "model.norm.weight": "model-9.safetensors",
     "lm_head.weight": "model-9.safetensors",
     "model.layers.0.self_attn.qkv_proj.weight": "model-1.safetensors",