Instructions to use brain-lab/Llama-2-70b-QuIP-HARP-2Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brain-lab/Llama-2-70b-QuIP-HARP-2Bit with Transformers:

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

pipe = pipeline("text-generation", model="brain-lab/Llama-2-70b-QuIP-HARP-2Bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brain-lab/Llama-2-70b-QuIP-HARP-2Bit")
model = AutoModelForCausalLM.from_pretrained("brain-lab/Llama-2-70b-QuIP-HARP-2Bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use brain-lab/Llama-2-70b-QuIP-HARP-2Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brain-lab/Llama-2-70b-QuIP-HARP-2Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brain-lab/Llama-2-70b-QuIP-HARP-2Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brain-lab/Llama-2-70b-QuIP-HARP-2Bit

SGLang

How to use brain-lab/Llama-2-70b-QuIP-HARP-2Bit 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 "brain-lab/Llama-2-70b-QuIP-HARP-2Bit" \
    --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": "brain-lab/Llama-2-70b-QuIP-HARP-2Bit",
		"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 "brain-lab/Llama-2-70b-QuIP-HARP-2Bit" \
        --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": "brain-lab/Llama-2-70b-QuIP-HARP-2Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brain-lab/Llama-2-70b-QuIP-HARP-2Bit with Docker Model Runner:
```
docker model run hf.co/brain-lab/Llama-2-70b-QuIP-HARP-2Bit
```

Llama-2-70b-QuIP-HARP-2Bit / config.json

Threeteck

Upload folder using huggingface_hub

2da1685 verified 7 days ago

Raw

History Blame Contribute Delete

1.6 kB

	{
	"_name_or_path": "meta-llama/Llama-2-70b-hf",
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 8192,
	"initializer_range": 0.02,
	"intermediate_size": 28672,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 64,
	"num_hidden_layers": 80,
	"num_key_value_heads": 8,
	"pretraining_tp": 1,
	"quip_params": {
	"codebook": "E8P12",
	"codebook_version": 1,
	"codesz": 8,
	"harp": {
	"chunk_size": 1048576,
	"early_stop_min_rel_improve": 0.01,
	"early_stop_window": 0,
	"fixed_mixer": "had_or_qr",
	"grad_clip": null,
	"harp_b": 8,
	"harp_max_b": 8,
	"harp_passes": 1,
	"hbd_block": 8,
	"hbd_lambda": 0.1,
	"kron_fallback": false,
	"lr_u": 0.03,
	"lr_v": 0.03,
	"ordering_mode": "stride",
	"q_recompute_every": 1,
	"reg_theta": 0.0,
	"steps": 1200,
	"strategy": "proxy",
	"theta_clip": null,
	"theta_init_scale": 0.0,
	"use_givens_b2": false
	},
	"idx_dtype": "torch.int64",
	"incoh_mode": "harp",
	"lora_rank": 0,
	"model_version": 1,
	"packsz": 4,
	"quant_layers": null,
	"rescale_WH": false,
	"resid_scale_override": -1
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.45.2",
	"use_cache": true,
	"vocab_size": 32000
	}