Instructions to use MTSAIR/MultiVerse_70B_AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MTSAIR/MultiVerse_70B_AWQ with Transformers:

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

pipe = pipeline("text-generation", model="MTSAIR/MultiVerse_70B_AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MTSAIR/MultiVerse_70B_AWQ")
model = AutoModelForCausalLM.from_pretrained("MTSAIR/MultiVerse_70B_AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MTSAIR/MultiVerse_70B_AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MTSAIR/MultiVerse_70B_AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MTSAIR/MultiVerse_70B_AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MTSAIR/MultiVerse_70B_AWQ

SGLang

How to use MTSAIR/MultiVerse_70B_AWQ 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 "MTSAIR/MultiVerse_70B_AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MTSAIR/MultiVerse_70B_AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MTSAIR/MultiVerse_70B_AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MTSAIR/MultiVerse_70B_AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MTSAIR/MultiVerse_70B_AWQ with Docker Model Runner:
```
docker model run hf.co/MTSAIR/MultiVerse_70B_AWQ
```

AlanRobotics commited on Apr 3, 2024

Commit

0e73eb3

verified ·

1 Parent(s): e4e5f56

Upload LlamaForCausalLM

Browse files

Files changed (12) hide show

config.json +43 -0
generation_config.json +7 -0
model-00001-of-00009.safetensors +3 -0
model-00002-of-00009.safetensors +3 -0
model-00003-of-00009.safetensors +3 -0
model-00004-of-00009.safetensors +3 -0
model-00005-of-00009.safetensors +3 -0
model-00006-of-00009.safetensors +3 -0
model-00007-of-00009.safetensors +3 -0
model-00008-of-00009.safetensors +3 -0
model-00009-of-00009.safetensors +3 -0
model.safetensors.index.json +0 -0

config.json ADDED Viewed

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

+{
+  "_name_or_path": "MultiVerse_70B_quant",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 64,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "backend": "autoawq",
+    "bits": 4,
+    "do_fuse": false,
+    "exllama_config": null,
+    "fuse_max_seq_len": null,
+    "group_size": 128,
+    "modules_to_fuse": null,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 152064
+}

generation_config.json ADDED Viewed

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

+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "pad_token_id": 151643,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:85a44056167fba6178f58a365498b9df6aef4e2b5375ee259c2adc32b65e8111
+size 4999136232

model-00002-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a207677e05c5afc098a7a28690cc4c6e07c29d3d2ac58aab04874ce99d2026c9
+size 4989977648

model-00003-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c040c9634ef84c58516929f75234b03fd3641c39080a702fe0bcf604bc55c405
+size 4986831928

model-00004-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:533a079d179a245bbd3df2e4b735e04e285123ff1438ff613637434573faa2b8
+size 4986831928

model-00005-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f4985b071d424cb60356e28c7346046b98c6a4b76cb956244aae6443386808
+size 4986831928

model-00006-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3786d2df19622f49a9f1a6c2def16679fe8b51d53e9567e51f79d1ec83acb6
+size 4986831928

model-00007-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:718fe87b78659e1fb035fc7bde269ed34b7f0b38ed1e84baa57d8edaa382ff6c
+size 4986831928

model-00008-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2797d37201c744438df966f93e8d531001c04ac5fe02f3147dcaceec1eea6f5d
+size 3836027912

model-00009-of-00009.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac26139d540e4c56780d2e0cfb894b384fe5f33030e20d781c6be1939c0322
+size 2491416704

model.safetensors.index.json ADDED Viewed

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