matlok's picture
initial release for the tinyllama merged model with 32k context: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T + Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct + Doctor-Shotgun/TinyLlama-1.1B-32k + Tensoic/TinyLlama-1.1B-3T-openhermes + Josephgflowers/TinyLlama-3T-Cinder-v1.3
e09bf10
raw
history blame
724 Bytes
{
"_name_or_path": "matlok/tinyllama-cinder-openhermes-32k",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.37.1",
"unsloth_version": "2024.1",
"use_cache": false,
"vocab_size": 32000
}