Instructions to use relaxml/Llama-2-7b-chat-E8PRVQ-3Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use relaxml/Llama-2-7b-chat-E8PRVQ-3Bit with Transformers:

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

pipe = pipeline("text-generation", model="relaxml/Llama-2-7b-chat-E8PRVQ-3Bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("relaxml/Llama-2-7b-chat-E8PRVQ-3Bit")
model = AutoModelForCausalLM.from_pretrained("relaxml/Llama-2-7b-chat-E8PRVQ-3Bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use relaxml/Llama-2-7b-chat-E8PRVQ-3Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/relaxml/Llama-2-7b-chat-E8PRVQ-3Bit

SGLang

How to use relaxml/Llama-2-7b-chat-E8PRVQ-3Bit 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 "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "relaxml/Llama-2-7b-chat-E8PRVQ-3Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use relaxml/Llama-2-7b-chat-E8PRVQ-3Bit with Docker Model Runner:
```
docker model run hf.co/relaxml/Llama-2-7b-chat-E8PRVQ-3Bit
```

Upload folder using huggingface_hub

by at676 - opened Feb 8, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-3

Files changed (3) hide show

config.json +2 -1
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -4,6 +4,7 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -34,7 +35,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 32000
 }

     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.34.0"
 }

   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.36.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bf987ee85b6aebb1ef8b0bc40d877566b2dea848cde44734b88c78d80a395c
 size 2957619856

 version https://git-lfs.github.com/spec/v1
+oid sha256:431b584b3fc0f509775349e02316a1b8d59f012b5f00e8c9e7ffec657913c755
 size 2957619856