Instructions to use trakss1436/Llama-2-7b-chat-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trakss1436/Llama-2-7b-chat-finetune with Transformers:

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

pipe = pipeline("text-generation", model="trakss1436/Llama-2-7b-chat-finetune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trakss1436/Llama-2-7b-chat-finetune")
model = AutoModelForCausalLM.from_pretrained("trakss1436/Llama-2-7b-chat-finetune")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trakss1436/Llama-2-7b-chat-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trakss1436/Llama-2-7b-chat-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trakss1436/Llama-2-7b-chat-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/trakss1436/Llama-2-7b-chat-finetune

SGLang

How to use trakss1436/Llama-2-7b-chat-finetune 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 "trakss1436/Llama-2-7b-chat-finetune" \
    --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": "trakss1436/Llama-2-7b-chat-finetune",
		"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 "trakss1436/Llama-2-7b-chat-finetune" \
        --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": "trakss1436/Llama-2-7b-chat-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use trakss1436/Llama-2-7b-chat-finetune with Docker Model Runner:
```
docker model run hf.co/trakss1436/Llama-2-7b-chat-finetune
```

trakss1436 commited on Dec 12, 2023

Commit

11dd72c

1 Parent(s): 56a9e79

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

generation_config.json +1 -3
pytorch_model-00001-of-00002.bin +1 -1
pytorch_model-00002-of-00002.bin +1 -1

generation_config.json CHANGED Viewed

@@ -2,8 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 32000,
-  "temperature": 0.9,
-  "top_p": 0.6,
   "transformers_version": "4.31.0"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a6830e4a96cbf5ab5b7313af7e230f34b962939fe59584d3e2090e9854c4e7
 size 9976638373

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd6268215a2d848913256511475afaa6bf422d302d7079250926e92bce5efd83
 size 9976638373

pytorch_model-00002-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afc921a0dca8d1906b86e0a3179a49d00407eaf236bbfb09190de3e6f4ec98ed
 size 3500317102

 version https://git-lfs.github.com/spec/v1
+oid sha256:12335059cfd06e6273d4723874407793163a8ad612d2462048ad7201adfee538
 size 3500317102