Instructions to use Minami-su/SUS-Chat-34B_2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minami-su/SUS-Chat-34B_2bit with Transformers:

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

pipe = pipeline("text-generation", model="Minami-su/SUS-Chat-34B_2bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Minami-su/SUS-Chat-34B_2bit")
model = AutoModelForCausalLM.from_pretrained("Minami-su/SUS-Chat-34B_2bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Minami-su/SUS-Chat-34B_2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minami-su/SUS-Chat-34B_2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Minami-su/SUS-Chat-34B_2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Minami-su/SUS-Chat-34B_2bit

SGLang

How to use Minami-su/SUS-Chat-34B_2bit 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 "Minami-su/SUS-Chat-34B_2bit" \
    --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": "Minami-su/SUS-Chat-34B_2bit",
		"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 "Minami-su/SUS-Chat-34B_2bit" \
        --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": "Minami-su/SUS-Chat-34B_2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Minami-su/SUS-Chat-34B_2bit with Docker Model Runner:
```
docker model run hf.co/Minami-su/SUS-Chat-34B_2bit
```

Minami-su commited on Dec 22, 2023

Commit

c767611

1 Parent(s): 59d9316

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

config.json +38 -0
generation_config.json +7 -0
model-00001-of-00002.safetensors +3 -0
model-00002-of-00002.safetensors +3 -0
model.safetensors.index.json +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "_name_or_path": "SUS-Chat-34B/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quip_params": {
+    "codebook": "E8P12",
+    "codesz": 8,
+    "fused": true,
+    "idx_dtype": "torch.int16",
+    "lora_rank": 0,
+    "outlier_channel_split": false,
+    "packsz": 1,
+    "rescale_WH": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json ADDED Viewed

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

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

model-00001-of-00002.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:892f92d6b1c7f9c5dac1113472330f6681b69d1da5e1014124d949fbf937caad
+size 9299840312

model-00002-of-00002.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:89dcebdb9c9466c14b409e9f8f4415ce7b9f74d95c8a0b986c7fafc32b8984bb
+size 917504128

model.safetensors.index.json ADDED Viewed

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