Instructions to use vimalnar/aware-ai-2nd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vimalnar/aware-ai-2nd with Transformers:

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

pipe = pipeline("text-generation", model="vimalnar/aware-ai-2nd")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vimalnar/aware-ai-2nd")
model = AutoModelForCausalLM.from_pretrained("vimalnar/aware-ai-2nd")
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]:]))

llama-cpp-python

How to use vimalnar/aware-ai-2nd with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vimalnar/aware-ai-2nd",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use vimalnar/aware-ai-2nd with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vimalnar/aware-ai-2nd:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vimalnar/aware-ai-2nd:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vimalnar/aware-ai-2nd:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vimalnar/aware-ai-2nd:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf vimalnar/aware-ai-2nd:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vimalnar/aware-ai-2nd:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf vimalnar/aware-ai-2nd:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vimalnar/aware-ai-2nd:Q4_K_M

Use Docker

docker model run hf.co/vimalnar/aware-ai-2nd:Q4_K_M

LM Studio
Jan

vLLM

How to use vimalnar/aware-ai-2nd with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vimalnar/aware-ai-2nd"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vimalnar/aware-ai-2nd",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vimalnar/aware-ai-2nd:Q4_K_M

SGLang

How to use vimalnar/aware-ai-2nd 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 "vimalnar/aware-ai-2nd" \
    --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": "vimalnar/aware-ai-2nd",
		"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 "vimalnar/aware-ai-2nd" \
        --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": "vimalnar/aware-ai-2nd",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use vimalnar/aware-ai-2nd with Ollama:
```
ollama run hf.co/vimalnar/aware-ai-2nd:Q4_K_M
```

Unsloth Studio new

How to use vimalnar/aware-ai-2nd 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 vimalnar/aware-ai-2nd 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 vimalnar/aware-ai-2nd to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vimalnar/aware-ai-2nd to start chatting

Docker Model Runner
How to use vimalnar/aware-ai-2nd with Docker Model Runner:
```
docker model run hf.co/vimalnar/aware-ai-2nd:Q4_K_M
```

Lemonade

How to use vimalnar/aware-ai-2nd with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vimalnar/aware-ai-2nd:Q4_K_M

Run and chat with the model

lemonade run user.aware-ai-2nd-Q4_K_M

List all available models

lemonade list

vimalnar commited on Jul 27, 2024

Commit

8152ea9

verified ·

1 Parent(s): d2f81a1

Trained with Unsloth

Browse files

Files changed (2) hide show

config.json +7 -5
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
-    "model_type": "llama",
-   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
@@ -17,13 +17,15 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
-}

 {
+  "_name_or_path": "vimalnar/aware-ai-1st",
+  "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128255,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 128256
+}

generation_config.json CHANGED Viewed

@@ -8,5 +8,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.41.2"
 }

   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.43.3"
 }