Modelpublic

RichardErkhov/alnrg2arg_-_blockchainlabs_7B_merged_test2_4_prune-4bits

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes27downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

blockchainlabs7Bmergedtest24_prune - bnb 4bits

—Model creator: https://huggingface.co/alnrg2arg/
—Original model: https://huggingface.co/alnrg2arg/blockchainlabs7Bmergedtest24_prune/

Original model description: --- license: cc-by-nc-4.0 tags:

—merge
—mergekit
—lazymergekit
—pruning
—alnrg2arg/blockchainlabs7Bmergedtest24
—mlabonne/NeuralBeagle14-7B
—udkai/Turdus ---

blockchainlabs7Bmergedtest24_prune

blockchainlabs7Bmergedtest24prune is a pruned model based on alnrg2arg/blockchainlabs7Bmergedtest2_4, which is a merged model using following models using mergekit:

—mlabonne/NeuralBeagle14-7B
—udkai/Turdus

Pruning Kit I used: wanda

🧩 Configuration

json

{
  "_name_or_path": "alnrg2arg/blockchainlabs_7B_merged_test2_4_prun",
  "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,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.36.2",
  "use_cache": false,
  "vocab_size": 32000
}