Instructions to use FreedomIntelligence/Apollo-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/Apollo-72B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/Apollo-72B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/Apollo-72B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/Apollo-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/Apollo-72B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/Apollo-72B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/Apollo-72B

SGLang

How to use FreedomIntelligence/Apollo-72B 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 "FreedomIntelligence/Apollo-72B" \
    --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": "FreedomIntelligence/Apollo-72B",
		"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 "FreedomIntelligence/Apollo-72B" \
        --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": "FreedomIntelligence/Apollo-72B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/Apollo-72B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/Apollo-72B
```

Xidong commited on Apr 24, 2024

Commit

7f64354

verified ·

1 Parent(s): 78bc71f

Upload ./config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +43 -0

config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "_name_or_path": "/sds_wangby/models/Qwen-72B",
+  "architectures": [
+    "QWenLMHeadModel"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": true,
+  "emb_dropout_prob": 0.0,
+  "fp16": false,
+  "fp32": false,
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 49152,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 32768,
+  "model_type": "qwen",
+  "no_bias": true,
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "onnx_safe": null,
+  "rope_theta": 1000000,
+  "rotary_emb_base": 1000000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 32768,
+  "softmax_in_fp32": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "QWenTokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "use_cache_kernel": false,
+  "use_cache_quantization": false,
+  "use_dynamic_ntk": false,
+  "use_flash_attn": true,
+  "use_logn_attn": false,
+  "vocab_size": 152064
+}