Instructions to use AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk with Transformers:

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

pipe = pipeline("text-generation", model="AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk")
model = AutoModelForMultimodalLM.from_pretrained("AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk")
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 AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk

SGLang

How to use AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk 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 "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk" \
    --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": "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk",
		"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 "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk" \
        --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": "AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk",
    max_seq_length=2048,
)

Docker Model Runner
How to use AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk with Docker Model Runner:
```
docker model run hf.co/AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk
```

Uploaded model

Developed by: AashishKumar
License: apache-2.0
Finetuned from model : cognitivecomputations/dolphin-2.9-llama3-8b

from unsloth.chat_templates import get_chat_template

# Assuming you've initialized your tokenizer and model
tokenizer = get_chat_template(
    tokenizer,
    chat_template="chatml",  # Adjust as per your template needs
    mapping={"role": "from", "content": "value", "user": "human", "assistant": "gpt"},
    map_eos_token=True,
)

FastLanguageModel.for_inference(model)  # Ensure model is optimized for inference

messages = [
    {"from": "system", "value": "you are assistant designed to talk to answer any user question like a normal human would. Make sure any names are in english"},
    {"from": "human", "value": "mujhe kuch acchi movies recommend kro"}  # Example Hinglish input
]

inputs = tokenizer.apply_chat_template(
    messages,
    truncation=True,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
).to("cuda")

outputs = model.generate(
        input_ids=inputs, 
        max_new_tokens=64,
        do_sample=True,
        temperature=0.7,
        top_k=50,
        top_p=0.95,
        use_cache=True,
        no_repeat_ngram_size=3,
        num_return_sequences=1
    )
decoded_outputs = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]

print(decoded_outputs)  # Adjust how you handle outputs based on your application needs

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for AashishKumar/Cn_2_9_Hinglish_llama3_7b_4kAk

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

dphn/dolphin-2.9-llama3-8b

Finetuned

(13)

this model