Instructions to use Tamnemtf/llama-2-7b-vi-oscar_mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tamnemtf/llama-2-7b-vi-oscar_mini with Transformers:

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

pipe = pipeline("text-generation", model="Tamnemtf/llama-2-7b-vi-oscar_mini")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tamnemtf/llama-2-7b-vi-oscar_mini")
model = AutoModelForCausalLM.from_pretrained("Tamnemtf/llama-2-7b-vi-oscar_mini", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tamnemtf/llama-2-7b-vi-oscar_mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tamnemtf/llama-2-7b-vi-oscar_mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tamnemtf/llama-2-7b-vi-oscar_mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tamnemtf/llama-2-7b-vi-oscar_mini

SGLang

How to use Tamnemtf/llama-2-7b-vi-oscar_mini 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 "Tamnemtf/llama-2-7b-vi-oscar_mini" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tamnemtf/llama-2-7b-vi-oscar_mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Tamnemtf/llama-2-7b-vi-oscar_mini" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tamnemtf/llama-2-7b-vi-oscar_mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tamnemtf/llama-2-7b-vi-oscar_mini with Docker Model Runner:
```
docker model run hf.co/Tamnemtf/llama-2-7b-vi-oscar_mini
```

Tamnemtf commited on Feb 4, 2024

Commit

1cb4134

verified ·

1 Parent(s): cbafc7d

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -42

README.md CHANGED Viewed

@@ -22,45 +22,6 @@ tags:
 - Availability: The model checkpoint can be accessed on Hugging Face: Tamnemtf/llama-2-7b-vi-oscar_mini
 - Model trên được train dựa trên model gốc là ngoan/Llama-2-7b-vietnamese-20k
 ## How to Use
-  ```python
-      # Activate 4-bit precision base model loading
-      use_4bit = True
-      # Compute dtype for 4-bit base models
-      bnb_4bit_compute_dtype = "float16"
-      # Quantization type (fp4 or nf4)
-      bnb_4bit_quant_type = "nf4"
-      # Activate nested quantization for 4-bit base models (double quantization)
-      use_nested_quant = False
-      # Load the entire model on the GPU 0
-      device_map = {"": 0}
-  ```
-  ```python
-    compute_dtype = getattr(torch, bnb_4bit_compute_dtype)
-    bnb_config = BitsAndBytesConfig(
-        load_in_4bit=use_4bit,
-        bnb_4bit_quant_type=bnb_4bit_quant_type,
-        bnb_4bit_compute_dtype=compute_dtype,
-        bnb_4bit_use_double_quant=use_nested_quant,
-    )
-  ```
-  ```python
-    model = AutoModelForCausalLM.from_pretrained(
-      'Tamnemtf/llama-2-7b-vi-oscar_mini',
-      quantization_config=bnb_config,
-      device_map=device_map
-    )
-    model.config.use_cache = False
-    model.config.pretraining_tp = 1
-    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-    tokenizer.pad_token = tokenizer.eos_token
-    tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training
-  ```
   ```python
     # Run text generation pipeline with our next model
     prompt = "Canh chua cá lau là món gì ?"
@@ -69,9 +30,6 @@ tags:
     print(result[0]['generated_text'])
   ```
-  Để ưu tiên cho việc dễ dàng tiếp cận với các sinh viên dưới đây là mẫu ví dụ chạy thử model trên colab bằng T4
-  https://colab.research.google.com/drive/1ME_k-gUKSY2NbB7GQRk3sqz56CKsSV5C?usp=sharing
   ## Conntact
   nguyndantdm6@gmail.com

 - Availability: The model checkpoint can be accessed on Hugging Face: Tamnemtf/llama-2-7b-vi-oscar_mini
 - Model trên được train dựa trên model gốc là ngoan/Llama-2-7b-vietnamese-20k
 ## How to Use
   ```python
     # Run text generation pipeline with our next model
     prompt = "Canh chua cá lau là món gì ?"
     print(result[0]['generated_text'])
   ```
   ## Conntact
   nguyndantdm6@gmail.com