Instructions to use LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin with Transformers:

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

pipe = pipeline("text-generation", model="LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin

SGLang

How to use LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin 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 "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin" \
    --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": "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin",
		"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 "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin" \
        --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": "LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin with Docker Model Runner:
```
docker model run hf.co/LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin
```

Qubitium commited on Mar 31, 2024

Commit

096e28c

verified ·

1 Parent(s): 873e9a1

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +52 -0

config.json ADDED Viewed

	@@ -0,0 +1,52 @@

+{
+  "_name_or_path": "/monster/data/model/dbrx-base-converted-v2/",
+  "architectures": [
+    "DbrxForCausalLM"
+  ],
+  "attn_config": {
+    "clip_qkv": 8,
+    "kv_n_heads": 8,
+    "model_type": "",
+    "rope_theta": 500000
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_dbrx.DbrxConfig",
+    "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
+  },
+  "d_model": 6144,
+  "emb_pdrop": 0.0,
+  "ffn_config": {
+    "ffn_hidden_size": 10752,
+    "model_type": "",
+    "moe_jitter_eps": 0.01,
+    "moe_loss_weight": 0.05,
+    "moe_num_experts": 16,
+    "moe_top_k": 4
+  },
+  "initializer_range": 0.02,
+  "max_seq_len": 32768,
+  "model_type": "dbrx",
+  "n_heads": 48,
+  "n_layers": 40,
+  "output_router_logits": false,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "marlin",
+    "damp_percent": 0.005,
+    "desc_act": false,
+    "group_size": 128,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "resid_pdrop": 0.0,
+  "router_aux_loss_coef": 0.05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 100352
+}