Instructions to use Sandiago21/llama-7b-hf-prompt-answering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sandiago21/llama-7b-hf-prompt-answering with Transformers:

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

pipe = pipeline("text-generation", model="Sandiago21/llama-7b-hf-prompt-answering")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sandiago21/llama-7b-hf-prompt-answering")
model = AutoModelForCausalLM.from_pretrained("Sandiago21/llama-7b-hf-prompt-answering", device_map="auto")

PEFT
How to use Sandiago21/llama-7b-hf-prompt-answering with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sandiago21/llama-7b-hf-prompt-answering with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sandiago21/llama-7b-hf-prompt-answering"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sandiago21/llama-7b-hf-prompt-answering",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sandiago21/llama-7b-hf-prompt-answering

SGLang

How to use Sandiago21/llama-7b-hf-prompt-answering 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 "Sandiago21/llama-7b-hf-prompt-answering" \
    --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": "Sandiago21/llama-7b-hf-prompt-answering",
		"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 "Sandiago21/llama-7b-hf-prompt-answering" \
        --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": "Sandiago21/llama-7b-hf-prompt-answering",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sandiago21/llama-7b-hf-prompt-answering with Docker Model Runner:
```
docker model run hf.co/Sandiago21/llama-7b-hf-prompt-answering
```

Sandiago21 commited on Jun 10, 2023

Commit

8694f72

1 Parent(s): 8f14bf4

small notebook update

Browse files

Files changed (1) hide show

notebooks/HuggingFace-Inference.ipynb +21 -5

notebooks/HuggingFace-Inference.ipynb CHANGED Viewed

@@ -199,6 +199,14 @@
     ")"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "1f6e7df1",
@@ -399,7 +407,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5e1d376d",
    "metadata": {},
    "source": [
     "### Example 5"
@@ -408,7 +416,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "80f2be65",
    "metadata": {},
    "outputs": [
     {
@@ -445,6 +453,14 @@
     "print(response)"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "df08ac5a",
@@ -660,7 +676,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "05ace30b",
    "metadata": {},
    "source": [
     "### Example 5"
@@ -669,7 +685,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "id": "afdc9bd8",
    "metadata": {},
    "outputs": [
     {
@@ -709,7 +725,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1bcecd20",
    "metadata": {},
    "outputs": [],
    "source": []

     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "bf54befd",
+   "metadata": {},
+   "source": [
+    "## Examples with Base (decapoda-research/llama-7b-hf) model"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f6e7df1",
   },
   {
    "cell_type": "markdown",
+   "id": "180873e7",
    "metadata": {},
    "source": [
     "### Example 5"
   {
    "cell_type": "code",
    "execution_count": 10,
+   "id": "10b6036b",
    "metadata": {},
    "outputs": [
     {
     "print(response)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "64bc9354",
+   "metadata": {},
+   "source": [
+    "## Examples with Fine-Tuned model"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "df08ac5a",
   },
   {
    "cell_type": "markdown",
+   "id": "acd8e768",
    "metadata": {},
    "source": [
     "### Example 5"
   {
    "cell_type": "code",
    "execution_count": 16,
+   "id": "b05c3934",
    "metadata": {},
    "outputs": [
     {
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "569838c8",
    "metadata": {},
    "outputs": [],
    "source": []