Instructions to use unalignment/weeeeee.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unalignment/weeeeee.0 with Transformers:

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

pipe = pipeline("text-generation", model="unalignment/weeeeee.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unalignment/weeeeee.0")
model = AutoModelForCausalLM.from_pretrained("unalignment/weeeeee.0")
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 unalignment/weeeeee.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unalignment/weeeeee.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unalignment/weeeeee.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unalignment/weeeeee.0

SGLang

How to use unalignment/weeeeee.0 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 "unalignment/weeeeee.0" \
    --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": "unalignment/weeeeee.0",
		"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 "unalignment/weeeeee.0" \
        --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": "unalignment/weeeeee.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use unalignment/weeeeee.0 with Docker Model Runner:
```
docker model run hf.co/unalignment/weeeeee.0
```

jondurbin commited on Feb 16, 2024

Commit

594bf24

verified ·

1 Parent(s): 36c633b

Upload LlamaForCausalLM

Browse files

Files changed (6) hide show

config.json +3 -2
generation_config.json +1 -2
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +2 -2
model.safetensors.index.json +1 -10

config.json CHANGED Viewed

@@ -14,15 +14,16 @@
   "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 33,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.37.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

   "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 32,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.37.2",
+  "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.37.2",
-  "use_cache": false
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.37.2"
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd112b457029a18fa6a7830ecd99cd3e0b4f8637f698761ca2d1dadb08ec11d1
 size 4943162336

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e2da0ebde768bac242f7cbf832e1a248519d1c1d26a1d7355465b1648c39757
 size 4943162336

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d2b624b3a983c5055e015181aa58ef01242bffaa1eed36b2bfab4b5399130e
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:a591cb9adbcfac23f8a7e3832ed7afdce769e6f45607f7c69232b92aa70e8ab9
 size 4999819336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60238df99dc2ba1f44c32ec2e57c265596ef41e23bf19f60f67c9e05cee81330
-size 4976741400

 version https://git-lfs.github.com/spec/v1
+oid sha256:f9b905956328ae22115e71e19f8d84e182d46a20f280321d19ee56d4ed540831
+size 4540516344

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14919688192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -239,15 +239,6 @@
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 14483464192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",