salamandra-2b-base-fp8 / config.json
jsaizant's picture
Upload LlamaForCausalLM
d6bfd0c verified
raw
history blame
1.85 kB
{
"_name_or_path": "/home/jsaiz/storage5/gpfs/projects/bsc88/text/models/salamandra_quantized_speculative/salamandra-2b-base-fp8",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"compression_config": {
"config_groups": {
"group_0": {
"input_activations": {
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": "memoryless",
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"global_compression_ratio": 1.238603132760912,
"ignore": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "frozen"
},
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5440,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"num_layers": 24,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.46.1",
"use_cache": true,
"vocab_size": 256000
}