Instructions to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16

SGLang

How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 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 "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16" \
    --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": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",
		"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 "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16" \
        --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": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16
```

ekurtic commited on Feb 13

Commit

70371b1

verified ·

1 Parent(s): 3921b6a

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -17

README.md CHANGED Viewed

@@ -84,7 +84,7 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
-model_id = "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"
 number_gpus = 1
 max_model_len = 8192
@@ -614,7 +614,7 @@ The results were obtained using the following commands:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -626,7 +626,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks mmlu_cot_0shot_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -637,7 +637,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
   --tasks arc_challenge_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -648,7 +648,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -660,7 +660,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks hellaswag \
   --num_fewshot 10 \
   --batch_size auto
@@ -670,7 +670,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks winogrande \
   --num_fewshot 5 \
   --batch_size auto
@@ -680,7 +680,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto
@@ -690,7 +690,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
   --apply_chat_template \
   --fewshot_as_multiturn \
   --tasks leaderboard \
@@ -701,7 +701,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_pt_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -713,7 +713,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_es_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -725,7 +725,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_it_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -737,7 +737,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_de_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -749,7 +749,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_fr_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -761,7 +761,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_hi_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -773,7 +773,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_th_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
@@ -785,7 +785,7 @@ lm_eval \
 ##### Generation
 ```
 python3 codegen/generate.py \
-  --model neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 \
   --bs 16 \
   --temperature 0.2 \
   --n_samples 50 \

 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
+model_id = "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"
 number_gpus = 1
 max_model_len = 8192
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks mmlu_cot_0shot_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
   --tasks arc_challenge_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks hellaswag \
   --num_fewshot 10 \
   --batch_size auto
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks winogrande \
   --num_fewshot 5 \
   --batch_size auto
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
   --apply_chat_template \
   --fewshot_as_multiturn \
   --tasks leaderboard \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_pt_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_es_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_it_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_de_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_fr_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_hi_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ```
 lm_eval \
   --model vllm \
+  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
   --tasks mmlu_th_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \
 ##### Generation
 ```
 python3 codegen/generate.py \
+  --model RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 \
   --bs 16 \
   --temperature 0.2 \
   --n_samples 50 \