Instructions to use FreedomIntelligence/AceGPT-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/AceGPT-7B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/AceGPT-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/AceGPT-7B")
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/AceGPT-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/AceGPT-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/AceGPT-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/AceGPT-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/AceGPT-7B

SGLang

How to use FreedomIntelligence/AceGPT-7B 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/AceGPT-7B" \
    --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/AceGPT-7B",
		"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/AceGPT-7B" \
        --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/AceGPT-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/AceGPT-7B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/AceGPT-7B
```

jianqing666 commited on Nov 29, 2023

Commit

c907e27

1 Parent(s): 51a28ee

Upload 6 files

Browse files

Files changed (4) hide show

config.json +3 -4
generation_config.json +9 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/ibex/user/xuj0h/LLM_ckpt/llama_raw_pretrain/llama-raw-sribd/llama-7b-secondround/llama2_7B_pretrain_30B_tfmr32",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,10 +19,9 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0.dev0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0.dev0"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -22,7 +22,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
@@ -31,6 +30,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "use_default_system_prompt": true
 }

   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
     "normalized": false,
     "rstrip": false,
     "single_word": false
+  }
 }