Instructions to use Cesar42/TrainLlama2Dataset with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cesar42/TrainLlama2Dataset with Transformers:

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

pipe = pipeline("text-generation", model="Cesar42/TrainLlama2Dataset")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cesar42/TrainLlama2Dataset")
model = AutoModelForCausalLM.from_pretrained("Cesar42/TrainLlama2Dataset")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Cesar42/TrainLlama2Dataset with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cesar42/TrainLlama2Dataset"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cesar42/TrainLlama2Dataset",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Cesar42/TrainLlama2Dataset

SGLang

How to use Cesar42/TrainLlama2Dataset 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 "Cesar42/TrainLlama2Dataset" \
    --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": "Cesar42/TrainLlama2Dataset",
		"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 "Cesar42/TrainLlama2Dataset" \
        --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": "Cesar42/TrainLlama2Dataset",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Cesar42/TrainLlama2Dataset with Docker Model Runner:
```
docker model run hf.co/Cesar42/TrainLlama2Dataset
```

Update config.json

by Cesar42 - opened Oct 13, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (1) hide show

config.json +5 -5

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,7 +9,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,8 +19,8 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000
-}

 {
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
   "use_cache": true,
   "vocab_size": 32000
+}