Instructions to use ken-miller/tris-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ken-miller/tris-2 with Transformers:

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

pipe = pipeline("text-generation", model="ken-miller/tris-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ken-miller/tris-2")
model = AutoModelForCausalLM.from_pretrained("ken-miller/tris-2")
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 Settings

vLLM

How to use ken-miller/tris-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ken-miller/tris-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ken-miller/tris-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ken-miller/tris-2

SGLang

How to use ken-miller/tris-2 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 "ken-miller/tris-2" \
    --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": "ken-miller/tris-2",
		"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 "ken-miller/tris-2" \
        --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": "ken-miller/tris-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ken-miller/tris-2 with Docker Model Runner:
```
docker model run hf.co/ken-miller/tris-2
```

ken-miller commited on Feb 17, 2024

Commit

b1fc0f0

verified ·

1 Parent(s): eb7542e

Upload LlamaForCausalLM

Browse files

Files changed (5) hide show

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

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/usr/local/lib/python3.9/dist-packages/local-models/training/2024-02-16_17-57-14",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "/storage/models/training/2024-02-17_00-58-06",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.36.2"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.36.2",
+  "use_cache": false
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c407a127521f882ed37c64804d952f771094b0707501762833faac03b7067bfb
 size 4943162336

 version https://git-lfs.github.com/spec/v1
+oid sha256:3c602f298dc3782af2bb316ceb2e32877091e65f5bf1ac3510ee1b13445d03ff
 size 4943162336

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62302ab02a72be38aaa3e68251f45712de75348aa4bcd8ca092d3f38989f53c
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:cf8a72a36ea0775d6d0b33fd3777c301f880df593522035038c3644c4836dca4
 size 4999819336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431e6bcbc4f0010864dd2a624d6fa10727683e8a1b8e02c55191614f9ebdd3f7
 size 4540516344

 version https://git-lfs.github.com/spec/v1
+oid sha256:c32fd4eb119d86dfa3f4d326cf4f488d4cd0108cd335dfdfe1fd7c5068dac0b2
 size 4540516344