Instructions to use william4416/bewtesttwo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use william4416/bewtesttwo with Transformers:

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

pipe = pipeline("text-generation", model="william4416/bewtesttwo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("william4416/bewtesttwo")
model = AutoModelForCausalLM.from_pretrained("william4416/bewtesttwo")
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 william4416/bewtesttwo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "william4416/bewtesttwo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "william4416/bewtesttwo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/william4416/bewtesttwo

SGLang

How to use william4416/bewtesttwo 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 "william4416/bewtesttwo" \
    --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": "william4416/bewtesttwo",
		"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 "william4416/bewtesttwo" \
        --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": "william4416/bewtesttwo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use william4416/bewtesttwo with Docker Model Runner:
```
docker model run hf.co/william4416/bewtesttwo
```

william4416 commited on Apr 13, 2024

Commit

c009e2d

verified ·

1 Parent(s): 06dc036

Upload 10 files

Browse files

Files changed (10) hide show

config (2).json +30 -0
flax_model (1).msgpack +3 -0
generation_config (2).json +6 -0
generation_config_for_conversational.json +7 -0
merges (1).txt +0 -0
pytorch_model (1).bin +3 -0
rust_model (1).ot +3 -0
tf_model (1).h5 +3 -0
tokenizer_config (2).json +23 -0
vocab (1).json +0 -0

config (2).json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "vocab_size": 50257
+}

flax_model (1).msgpack ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fafcbe08b61770a25fb539420430ceeaecba2e9414c6f4fb6ad5270d6997b397
+size 1419302302

generation_config (2).json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.0.dev0"
+}

generation_config_for_conversational.json ADDED Viewed

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

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "max_length": 1000,
+  "transformers_version": "4.27.0.dev0"
+}

merges (1).txt ADDED Viewed

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

pytorch_model (1).bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d2214b95438592f420ef4df037d9c72ddf993fb6877479fb09320b757f96cfa7
+size 862955157

rust_model (1).ot ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:46ca590456e201e1e75d7671e0f8cb281fffaca72659772345e75ec844ffa04c
+size 1725881760

tf_model (1).h5 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5afacddabe4a40f517064a81747acab952a1b494f74f5ceee109ba0bb7f300
+size 1419628976

tokenizer_config (2).json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

vocab (1).json ADDED Viewed

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