Text Generation
Transformers
Safetensors
PyTorch
mistral
finetuned
quantized
4-bit precision
AWQ
instruct
conversational
Inference Endpoints
text-generation-inference
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
awq
bagel-7b-v0.5-AWQ / config.json
Shaun Prince
add awq model
821b17d
{
"_name_or_path": "/home/shaun/.cache/huggingface/hub/models--jondurbin--bagel-7b-v0.5/snapshots/82259724e32cd355a17ea0cc029af5265daf11a0",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"use_cache": false,
"vocab_size": 32000
}