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

Libraries

How to use SciPhi/Triplex with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SciPhi/Triplex", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SciPhi/Triplex", trust_remote_code=True)
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]:]))

llama-cpp-python

How to use SciPhi/Triplex with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SciPhi/Triplex",
	filename="quantized_model-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SciPhi/Triplex with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SciPhi/Triplex:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SciPhi/Triplex:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SciPhi/Triplex:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SciPhi/Triplex:Q4_K_M

Use Docker

docker model run hf.co/SciPhi/Triplex:Q4_K_M

LM Studio
Jan

vLLM

How to use SciPhi/Triplex with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SciPhi/Triplex:Q4_K_M

SGLang

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

Ollama
How to use SciPhi/Triplex with Ollama:
```
ollama run hf.co/SciPhi/Triplex:Q4_K_M
```

Unsloth Studio

How to use SciPhi/Triplex with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SciPhi/Triplex to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SciPhi/Triplex to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SciPhi/Triplex to start chatting

Docker Model Runner
How to use SciPhi/Triplex with Docker Model Runner:
```
docker model run hf.co/SciPhi/Triplex:Q4_K_M
```

Lemonade

How to use SciPhi/Triplex with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SciPhi/Triplex:Q4_K_M

Run and chat with the model

lemonade run user.Triplex-Q4_K_M

List all available models

lemonade list

shreyaspimpalgaonkar commited on Jul 14, 2024

Commit

4b05ef8

verified ·

1 Parent(s): 5a0f484

Update config.json

Browse files

Files changed (1) hide show

config.json +8 -111

config.json CHANGED Viewed

@@ -3,12 +3,10 @@
   "architectures": [
     "Phi3ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
-    "AutoModel": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
-    "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
@@ -17,7 +15,7 @@
   "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
   "model_type": "phi3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -26,114 +24,13 @@
   "pad_token_id": 32000,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "long_factor": [
-      1.0700000524520874,
-      1.1200000047683716,
-      1.149999976158142,
-      1.4199999570846558,
-      1.5699999332427979,
-      1.7999999523162842,
-      2.129999876022339,
-      2.129999876022339,
-      3.009999990463257,
-      5.910000324249268,
-      6.950000286102295,
-      9.070000648498535,
-      9.930000305175781,
-      10.710000038146973,
-      11.130000114440918,
-      14.609999656677246,
-      15.409998893737793,
-      19.809999465942383,
-      37.279998779296875,
-      38.279998779296875,
-      38.599998474121094,
-      40.12000274658203,
-      46.20000457763672,
-      50.940006256103516,
-      53.66000747680664,
-      54.9373893737793,
-      56.89738845825195,
-      57.28738784790039,
-      59.98738479614258,
-      60.86738586425781,
-      60.887386322021484,
-      61.71739196777344,
-      62.91739273071289,
-      62.957393646240234,
-      63.41739273071289,
-      63.8173942565918,
-      63.83739471435547,
-      63.897396087646484,
-      63.93739700317383,
-      64.06739807128906,
-      64.11434936523438,
-      64.12435150146484,
-      64.15435028076172,
-      64.19435119628906,
-      64.24435424804688,
-      64.57435607910156,
-      64.69000244140625,
-      64.76000213623047
-    ],
-    "short_factor": [
-      1.1,
-      1.1,
-      1.1,
-      1.3000000000000003,
-      1.3500000000000003,
-      1.3500000000000003,
-      1.4000000000000004,
-      1.5500000000000005,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.1000000000000005,
-      2.1000000000000005,
-      2.1500000000000004,
-      2.25,
-      2.25,
-      2.25,
-      2.25,
-      2.25,
-      2.3999999999999995,
-      2.4499999999999993,
-      2.499999999999999,
-      2.6999999999999984,
-      2.6999999999999984,
-      2.7499999999999982,
-      2.799999999999998,
-      2.8999999999999977,
-      3.049999999999997
-    ],
-    "type": "yarn"
-  },
   "rope_theta": 10000.0,
-  "sliding_window": 262144,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.3",
-  "use_cache": false,
   "vocab_size": 32064
 }

   "architectures": [
     "Phi3ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
   "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
   "model_type": "phi3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pad_token_id": 32000,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
+  "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "attention_bias": false,
   "vocab_size": 32064
 }