Instructions to use mrm8488/llama-2-coder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrm8488/llama-2-coder-7b with Transformers:

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

pipe = pipeline("text-generation", model="mrm8488/llama-2-coder-7b")

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

tokenizer = AutoTokenizer.from_pretrained("mrm8488/llama-2-coder-7b")
model = AutoModelForCausalLM.from_pretrained("mrm8488/llama-2-coder-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrm8488/llama-2-coder-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrm8488/llama-2-coder-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrm8488/llama-2-coder-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrm8488/llama-2-coder-7b

SGLang

How to use mrm8488/llama-2-coder-7b 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 "mrm8488/llama-2-coder-7b" \
    --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": "mrm8488/llama-2-coder-7b",
		"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 "mrm8488/llama-2-coder-7b" \
        --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": "mrm8488/llama-2-coder-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrm8488/llama-2-coder-7b with Docker Model Runner:
```
docker model run hf.co/mrm8488/llama-2-coder-7b
```

mrm8488 commited on Jul 26, 2023

Commit

9af29c5

1 Parent(s): c4b1a7a

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -7

README.md CHANGED Viewed

@@ -39,17 +39,36 @@ Meta developed and publicly released the Llama 2 family of large language models
 ### Training hyperparameters ⚙
-TBA
 ### Training results 🗒️
 | Step | Training Loss | Validation Loss |
-|------|---------------|-----------------|
-| 100  | 0.798500      | 0.767996        |
-| 200  | 0.725900      | 0.749880        |
-| 300  | 0.669100      | 0.748029        |
-| 400  | 0.687300      | 0.742342        |
-| 500  | 0.579900      | 0.736735        |

 ### Training hyperparameters ⚙
+```py
+    optim="paged_adamw_32bit",
+    num_train_epochs = 2,
+    eval_steps=50,
+    save_steps=50,
+    evaluation_strategy="steps",
+    save_strategy="steps",
+    save_total_limit=2,
+    seed=66,
+    load_best_model_at_end=True,
+    logging_steps=1,
+    learning_rate=2e-4,
+    fp16=True,
+    bf16=False,
+    max_grad_norm=0.3,
+    warmup_ratio=0.03,
+    group_by_length=True,
+    lr_scheduler_type="constant"
+```
 ### Training results 🗒️
 | Step | Training Loss | Validation Loss |
+|------|----------|----------|
+| 50   | 0.624400 | 0.600070 |
+| 100  | 0.634100 | 0.592757 |
+| 150  | 0.545800 | 0.586652 |
+| 200  | 0.572500 | 0.577525 |
+| 250  | 0.528000 | 0.590118 |