Instructions to use edumunozsala/llama-2-7b-int4-python-code-20k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use edumunozsala/llama-2-7b-int4-python-code-20k with Transformers:

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

pipe = pipeline("text-generation", model="edumunozsala/llama-2-7b-int4-python-code-20k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("edumunozsala/llama-2-7b-int4-python-code-20k")
model = AutoModelForCausalLM.from_pretrained("edumunozsala/llama-2-7b-int4-python-code-20k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use edumunozsala/llama-2-7b-int4-python-code-20k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "edumunozsala/llama-2-7b-int4-python-code-20k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "edumunozsala/llama-2-7b-int4-python-code-20k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/edumunozsala/llama-2-7b-int4-python-code-20k

SGLang

How to use edumunozsala/llama-2-7b-int4-python-code-20k 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 "edumunozsala/llama-2-7b-int4-python-code-20k" \
    --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": "edumunozsala/llama-2-7b-int4-python-code-20k",
		"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 "edumunozsala/llama-2-7b-int4-python-code-20k" \
        --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": "edumunozsala/llama-2-7b-int4-python-code-20k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use edumunozsala/llama-2-7b-int4-python-code-20k with Docker Model Runner:
```
docker model run hf.co/edumunozsala/llama-2-7b-int4-python-code-20k
```

edumunozsala commited on Aug 7, 2023

Commit

2b9d925

1 Parent(s): 43d3864

Upload README.md

Browse files

Files changed (1) hide show

README.md +8 -7

README.md CHANGED Viewed

@@ -81,22 +81,24 @@ The following `bitsandbytes` quantization config was used during training:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_id = "mrm8488/llama-2-coder-7b"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
-sample = dataset[randrange(len(dataset))]
 prompt = f"""### Instruction:
 Use the Task below and the Input given to write the Response, which is a programming code that can solve the Task.
 ### Task:
-{sample['instruction']}
 ### Input:
-{sample['input']}
 ### Response:
 """
@@ -107,7 +109,6 @@ outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True
 print(f"Prompt:\n{prompt}\n")
 print(f"Generated instruction:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
-print(f"Ground truth:\n{sample['output']}")
 ```

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "edumunozsala/llama-2-7b-int4-python-code-20k"
+tokenizer = AutoTokenizer.from_pretrained(hf_model_repo)
+model = AutoModelForCausalLM.from_pretrained(hf_model_repo, load_in_4bit=True, torch_dtype=torch.float16,
+                                             device_map=device_map)
+instruction="Write a Python function to display the first and last elements of a list."
+input=""
 prompt = f"""### Instruction:
 Use the Task below and the Input given to write the Response, which is a programming code that can solve the Task.
 ### Task:
+{instruction}
 ### Input:
+{input}
 ### Response:
 """
 print(f"Prompt:\n{prompt}\n")
 print(f"Generated instruction:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
 ```