Instructions to use tangledgroup/tangled-alpha-0.10-core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tangledgroup/tangled-alpha-0.10-core with Transformers:

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

pipe = pipeline("text-generation", model="tangledgroup/tangled-alpha-0.10-core")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tangledgroup/tangled-alpha-0.10-core", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tangledgroup/tangled-alpha-0.10-core with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tangledgroup/tangled-alpha-0.10-core"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.10-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tangledgroup/tangled-alpha-0.10-core

SGLang

How to use tangledgroup/tangled-alpha-0.10-core 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 "tangledgroup/tangled-alpha-0.10-core" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.10-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "tangledgroup/tangled-alpha-0.10-core" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.10-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tangledgroup/tangled-alpha-0.10-core with Docker Model Runner:
```
docker model run hf.co/tangledgroup/tangled-alpha-0.10-core
```

mtasic85 commited on Mar 19, 2025

Commit

f03dcd7

1 Parent(s): 8a2ebd6

pretrain core

Browse files

Files changed (2) hide show

config-0.json +2 -2
scripts/pretrain_core_model_0.yaml +1 -1

config-0.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "head_dim": 256,
   "hidden_act": "silu",
   "hidden_size": 768,
   "initializer_range": 0.02,
@@ -14,7 +14,7 @@
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 16,
   "num_hidden_layers": 32,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,

   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 1,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 768,
   "initializer_range": 0.02,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 12,
   "num_hidden_layers": 32,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,

scripts/pretrain_core_model_0.yaml CHANGED Viewed

@@ -10,7 +10,7 @@ model_config:
   vocab_size: 131072
   padded_vocab_size: 131072
   n_layer: 32
-  n_head: 16
   n_embd: 768
   n_query_groups: 4
   rotary_percentage: 1.0

   vocab_size: 131072
   padded_vocab_size: 131072
   n_layer: 32
+  n_head: 12
   n_embd: 768
   n_query_groups: 4
   rotary_percentage: 1.0