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

Libraries

How to use lilmeaty/testing_semifinal with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lilmeaty/testing_semifinal")
model = AutoModelForCausalLM.from_pretrained("lilmeaty/testing_semifinal")
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 lilmeaty/testing_semifinal with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lilmeaty/testing_semifinal

SGLang

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

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

Hjgugugjhuhjggg commited on Dec 22, 2024

Commit

0a2aaf7

verified ·

1 Parent(s): 0653dc4

Update config.json

Browse files

Files changed (1) hide show

config.json +32 -23

config.json CHANGED Viewed

@@ -1,29 +1,20 @@
 {
   "_name_or_path": "huihui-ai/Llama-3.2-3B-Instruct-abliterated",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 128,
-  "hidden_act": "silu",
   "hidden_size": 3072,
-  "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 24,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 32.0,
     "high_freq_factor": 4.0,
@@ -32,9 +23,27 @@
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 128256
-}

 {
   "_name_or_path": "huihui-ai/Llama-3.2-3B-Instruct-abliterated",
+  "model_type": "llama",
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "architectures": ["PartiallySharedLayerModel"],
+  "vocab_size": 128256,
   "bos_token_id": 128000,
+  "eos_token_id": [128001, 128008, 128009],
+  "pad_token_id": 128009,
   "hidden_size": 3072,
   "intermediate_size": 8192,
   "num_hidden_layers": 28,
+  "num_attention_heads": 24,
   "num_key_value_heads": 8,
+  "head_dim": 128,
+  "max_position_embeddings": 131072,
   "rope_scaling": {
     "factor": 32.0,
     "high_freq_factor": 4.0,
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "layer_norm_eps": 1e-05,
+  "attention_bias": false,
+  "mlp_bias": false,
+  "pretraining_tp": 1,
   "tie_word_embeddings": true,
   "use_cache": true,
+  "shared_input_output_embedding": true,
+  "attention_dropout": 0.0,
+  "hidden_dropout_prob": 0.1,
+  "attn_dropout_prob": 0.1,
+  "residual_dropout_prob": 0.0,
+  "ffn_dropout_prob": 0.1,
+  "output_projection": true,
+  "position_embedding_type": "rotary",
+  "use_rope": true,
+  "gradient_checkpointing": false,
+  "multi_query_attention": false,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "layerdrop": 0.0
+}