Instructions to use Monero/oasst-alpaca13b-4epoch-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Monero/oasst-alpaca13b-4epoch-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="Monero/oasst-alpaca13b-4epoch-4bit-128g")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Monero/oasst-alpaca13b-4epoch-4bit-128g")
model = AutoModelForCausalLM.from_pretrained("Monero/oasst-alpaca13b-4epoch-4bit-128g", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Monero/oasst-alpaca13b-4epoch-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Monero/oasst-alpaca13b-4epoch-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Monero/oasst-alpaca13b-4epoch-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Monero/oasst-alpaca13b-4epoch-4bit-128g

SGLang

How to use Monero/oasst-alpaca13b-4epoch-4bit-128g 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 "Monero/oasst-alpaca13b-4epoch-4bit-128g" \
    --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": "Monero/oasst-alpaca13b-4epoch-4bit-128g",
		"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 "Monero/oasst-alpaca13b-4epoch-4bit-128g" \
        --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": "Monero/oasst-alpaca13b-4epoch-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Monero/oasst-alpaca13b-4epoch-4bit-128g with Docker Model Runner:
```
docker model run hf.co/Monero/oasst-alpaca13b-4epoch-4bit-128g
```

Monero commited on Apr 28, 2023

Commit

5f4b159

1 Parent(s): 7bb4e46

Upload 8 files

Browse files

Files changed (8) hide show

4bit-128g.safetensors +3 -0
added_tokens.json +3 -0
config.json +24 -0
generation_config.json +7 -0
special_tokens_map.json +6 -0
tokenizer.model +3 -0
tokenizer_config.json +9 -0
trainer_state.json +0 -0

4bit-128g.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3d9a9a081412936f1a0a75c1d0526de7b506387816e60096f6de03297c23bd
+size 7454817642

added_tokens.json ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "[PAD]": 32000
+}

config.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "_name_or_path": "/mnt/UbuntuData/AI/Models/alpaca-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0"
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

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

+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--decapoda-research--llama-13b-hf/snapshots/438770a656712a5072229b62256521845d4de5ce/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

trainer_state.json ADDED Viewed

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