Text Generation
Transformers
Safetensors
starcoder2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
awq
starchat2-15b-v0.1-AWQ / config.json
stelterlab's picture
Initial version
349ad40
raw
history blame
1.07 kB
{
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--HuggingFaceH4--starchat2-15b-v0.1/snapshots/837a7b6ac3df5f91de138e3592258f93c80d93d3",
"architectures": [
"Starcoder2ForCausalLM"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"embedding_dropout": 0.1,
"eos_token_id": 0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 6144,
"initializer_range": 0.01275,
"intermediate_size": 24576,
"max_position_embeddings": 16384,
"mlp_type": "default",
"model_type": "starcoder2",
"norm_epsilon": 1e-05,
"norm_type": "layer_norm",
"num_attention_heads": 48,
"num_hidden_layers": 40,
"num_key_value_heads": 4,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"residual_dropout": 0.1,
"rope_theta": 100000,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.40.1",
"use_bias": true,
"use_cache": true,
"vocab_size": 49154
}