Instructions to use TroyDoesAI/Unbiased-Personality with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/Unbiased-Personality with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/Unbiased-Personality")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/Unbiased-Personality")
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 TroyDoesAI/Unbiased-Personality with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TroyDoesAI/Unbiased-Personality

SGLang

How to use TroyDoesAI/Unbiased-Personality 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 "TroyDoesAI/Unbiased-Personality" \
    --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": "TroyDoesAI/Unbiased-Personality",
		"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 "TroyDoesAI/Unbiased-Personality" \
        --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": "TroyDoesAI/Unbiased-Personality",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TroyDoesAI/Unbiased-Personality with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/Unbiased-Personality
```

TroyDoesAI commited on Jul 26, 2024

Commit

37b1dec

verified ·

1 Parent(s): 6b37677

This model is a better communicator with an interesting personality. :)

Browse files

Files changed (6) hide show

config.json +1 -1
mergekit_config.yml +16 -0
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Unbiased",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "TroyDoesAI/Unbiased-Personality",
   "architectures": [
     "LlamaForCausalLM"
   ],

mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,16 @@

+slices:
+  - sources:
+      - model: TroyDoesAI/BlackSheep-RP-8B
+        layer_range: [0, 32]
+      - model: TroyDoesAI/Unbiased-Personality
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: TroyDoesAI/Unbiased-Personality
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.25
+dtype: bfloat16

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77581ef51e8c8f2dee6c6f2f8cbf27131c35ff960b1614ef9acc1a2b1678229a
 size 4953586384

 version https://git-lfs.github.com/spec/v1
+oid sha256:d2b61e32502a626eb3db560d7148054d67a15fc3e6b4fdb195bf31d889d57826
 size 4953586384

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8b9c3a37dff9b75d443aaaeaa36e0fc9fb3e62ca7bbad5bf41fe305f1bb970
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:f36ed66b912910776e1e3d89160428fafcd75737a9ace2de30e87a205539969a
 size 4999819336

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9492827195378a13292327bb037b232d10c6e37d1e4fae4b64a2ed45653e44
 size 4915916144

 version https://git-lfs.github.com/spec/v1
+oid sha256:400fde4d4ddbc72459ba6ea6a8f15509ede056b9ac6fd5d1f684fddaa1fad530
 size 4915916144

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15df1a8cfd7731a6e4c6137fa911033f266258b1ba7a39594803c3feb56eb00f
 size 1191234472

 version https://git-lfs.github.com/spec/v1
+oid sha256:098db0f99ad7c7b3d40aed811a23e820e63e42a0c452e86aa0a97c78d04745b5
 size 1191234472