Hugging Face's logo

ISTA-DASLab
/
c4ai-command-r-plus-AQLM-2Bit-1x16

Text Generation
Transformers
Safetensors
cohere
conversational
10languages
text-generation-inference
Inference Endpoints
Inference Endpoints
aqlm
Model card Files Community
c4ai-command-r-plus-AQLM-2Bit-1x16 / config.json
SpiridonSunRotator's picture
SpiridonSunRotator
Uploaded CohereForAI/c4ai-command-r-plus with AQLM 1x16 quantization
d30df0a verified
raw history blame contribute delete
No virus
10.4 kB
{
"_name_or_path": "/slot/sandbox/j/_tmp/data1yx_lw9k",
"architectures": [
"CohereForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"eos_token_id": 255001,
"hidden_act": "silu",
"hidden_size": 12288,
"initializer_range": 0.02,
"intermediate_size": 33792,
"layer_norm_eps": 1e-05,
"logit_scale": 0.8333333333333334,
"max_position_embeddings": 8192,
"model_max_length": 131072,
"model_type": "cohere",
"num_attention_heads": 96,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"in_group_size": 8,
"linear_weights_not_to_quantize": [
"model.layers.0.self_attn.q_norm.weight",
"model.layers.0.self_attn.k_norm.weight",
"model.layers.0.input_layernorm.weight",
"model.layers.1.self_attn.q_norm.weight",
"model.layers.1.self_attn.k_norm.weight",
"model.layers.1.input_layernorm.weight",
"model.layers.2.self_attn.q_norm.weight",
"model.layers.2.self_attn.k_norm.weight",
"model.layers.2.input_layernorm.weight",
"model.layers.3.self_attn.q_norm.weight",
"model.layers.3.self_attn.k_norm.weight",
"model.layers.3.input_layernorm.weight",
"model.layers.4.self_attn.q_norm.weight",
"model.layers.4.self_attn.k_norm.weight",
"model.layers.4.input_layernorm.weight",
"model.layers.5.self_attn.q_norm.weight",
"model.layers.5.self_attn.k_norm.weight",
"model.layers.5.input_layernorm.weight",
"model.layers.6.self_attn.q_norm.weight",
"model.layers.6.self_attn.k_norm.weight",
"model.layers.6.input_layernorm.weight",
"model.layers.7.self_attn.q_norm.weight",
"model.layers.7.self_attn.k_norm.weight",
"model.layers.7.input_layernorm.weight",
"model.layers.8.self_attn.q_norm.weight",
"model.layers.8.self_attn.k_norm.weight",
"model.layers.8.input_layernorm.weight",
"model.layers.9.self_attn.q_norm.weight",
"model.layers.9.self_attn.k_norm.weight",
"model.layers.9.input_layernorm.weight",
"model.layers.10.self_attn.q_norm.weight",
"model.layers.10.self_attn.k_norm.weight",
"model.layers.10.input_layernorm.weight",
"model.layers.11.self_attn.q_norm.weight",
"model.layers.11.self_attn.k_norm.weight",
"model.layers.11.input_layernorm.weight",
"model.layers.12.self_attn.q_norm.weight",
"model.layers.12.self_attn.k_norm.weight",
"model.layers.12.input_layernorm.weight",
"model.layers.13.self_attn.q_norm.weight",
"model.layers.13.self_attn.k_norm.weight",
"model.layers.13.input_layernorm.weight",
"model.layers.14.self_attn.q_norm.weight",
"model.layers.14.self_attn.k_norm.weight",
"model.layers.14.input_layernorm.weight",
"model.layers.15.self_attn.q_norm.weight",
"model.layers.15.self_attn.k_norm.weight",
"model.layers.15.input_layernorm.weight",
"model.layers.16.self_attn.q_norm.weight",
"model.layers.16.self_attn.k_norm.weight",
"model.layers.16.input_layernorm.weight",
"model.layers.17.self_attn.q_norm.weight",
"model.layers.17.self_attn.k_norm.weight",
"model.layers.17.input_layernorm.weight",
"model.layers.18.self_attn.q_norm.weight",
"model.layers.18.self_attn.k_norm.weight",
"model.layers.18.input_layernorm.weight",
"model.layers.19.self_attn.q_norm.weight",
"model.layers.19.self_attn.k_norm.weight",
"model.layers.19.input_layernorm.weight",
"model.layers.20.self_attn.q_norm.weight",
"model.layers.20.self_attn.k_norm.weight",
"model.layers.20.input_layernorm.weight",
"model.layers.21.self_attn.q_norm.weight",
"model.layers.21.self_attn.k_norm.weight",
"model.layers.21.input_layernorm.weight",
"model.layers.22.self_attn.q_norm.weight",
"model.layers.22.self_attn.k_norm.weight",
"model.layers.22.input_layernorm.weight",
"model.layers.23.self_attn.q_norm.weight",
"model.layers.23.self_attn.k_norm.weight",
"model.layers.23.input_layernorm.weight",
"model.layers.24.self_attn.q_norm.weight",
"model.layers.24.self_attn.k_norm.weight",
"model.layers.24.input_layernorm.weight",
"model.layers.25.self_attn.q_norm.weight",
"model.layers.25.self_attn.k_norm.weight",
"model.layers.25.input_layernorm.weight",
"model.layers.26.self_attn.q_norm.weight",
"model.layers.26.self_attn.k_norm.weight",
"model.layers.26.input_layernorm.weight",
"model.layers.27.self_attn.q_norm.weight",
"model.layers.27.self_attn.k_norm.weight",
"model.layers.27.input_layernorm.weight",
"model.layers.28.self_attn.q_norm.weight",
"model.layers.28.self_attn.k_norm.weight",
"model.layers.28.input_layernorm.weight",
"model.layers.29.self_attn.q_norm.weight",
"model.layers.29.self_attn.k_norm.weight",
"model.layers.29.input_layernorm.weight",
"model.layers.30.self_attn.q_norm.weight",
"model.layers.30.self_attn.k_norm.weight",
"model.layers.30.input_layernorm.weight",
"model.layers.31.self_attn.q_norm.weight",
"model.layers.31.self_attn.k_norm.weight",
"model.layers.31.input_layernorm.weight",
"model.layers.32.self_attn.q_norm.weight",
"model.layers.32.self_attn.k_norm.weight",
"model.layers.32.input_layernorm.weight",
"model.layers.33.self_attn.q_norm.weight",
"model.layers.33.self_attn.k_norm.weight",
"model.layers.33.input_layernorm.weight",
"model.layers.34.self_attn.q_norm.weight",
"model.layers.34.self_attn.k_norm.weight",
"model.layers.34.input_layernorm.weight",
"model.layers.35.self_attn.q_norm.weight",
"model.layers.35.self_attn.k_norm.weight",
"model.layers.35.input_layernorm.weight",
"model.layers.36.self_attn.q_norm.weight",
"model.layers.36.self_attn.k_norm.weight",
"model.layers.36.input_layernorm.weight",
"model.layers.37.self_attn.q_norm.weight",
"model.layers.37.self_attn.k_norm.weight",
"model.layers.37.input_layernorm.weight",
"model.layers.38.self_attn.q_norm.weight",
"model.layers.38.self_attn.k_norm.weight",
"model.layers.38.input_layernorm.weight",
"model.layers.39.self_attn.q_norm.weight",
"model.layers.39.self_attn.k_norm.weight",
"model.layers.39.input_layernorm.weight",
"model.layers.40.self_attn.q_norm.weight",
"model.layers.40.self_attn.k_norm.weight",
"model.layers.40.input_layernorm.weight",
"model.layers.41.self_attn.q_norm.weight",
"model.layers.41.self_attn.k_norm.weight",
"model.layers.41.input_layernorm.weight",
"model.layers.42.self_attn.q_norm.weight",
"model.layers.42.self_attn.k_norm.weight",
"model.layers.42.input_layernorm.weight",
"model.layers.43.self_attn.q_norm.weight",
"model.layers.43.self_attn.k_norm.weight",
"model.layers.43.input_layernorm.weight",
"model.layers.44.self_attn.q_norm.weight",
"model.layers.44.self_attn.k_norm.weight",
"model.layers.44.input_layernorm.weight",
"model.layers.45.self_attn.q_norm.weight",
"model.layers.45.self_attn.k_norm.weight",
"model.layers.45.input_layernorm.weight",
"model.layers.46.self_attn.q_norm.weight",
"model.layers.46.self_attn.k_norm.weight",
"model.layers.46.input_layernorm.weight",
"model.layers.47.self_attn.q_norm.weight",
"model.layers.47.self_attn.k_norm.weight",
"model.layers.47.input_layernorm.weight",
"model.layers.48.self_attn.q_norm.weight",
"model.layers.48.self_attn.k_norm.weight",
"model.layers.48.input_layernorm.weight",
"model.layers.49.self_attn.q_norm.weight",
"model.layers.49.self_attn.k_norm.weight",
"model.layers.49.input_layernorm.weight",
"model.layers.50.self_attn.q_norm.weight",
"model.layers.50.self_attn.k_norm.weight",
"model.layers.50.input_layernorm.weight",
"model.layers.51.self_attn.q_norm.weight",
"model.layers.51.self_attn.k_norm.weight",
"model.layers.51.input_layernorm.weight",
"model.layers.52.self_attn.q_norm.weight",
"model.layers.52.self_attn.k_norm.weight",
"model.layers.52.input_layernorm.weight",
"model.layers.53.self_attn.q_norm.weight",
"model.layers.53.self_attn.k_norm.weight",
"model.layers.53.input_layernorm.weight",
"model.layers.54.self_attn.q_norm.weight",
"model.layers.54.self_attn.k_norm.weight",
"model.layers.54.input_layernorm.weight",
"model.layers.55.self_attn.q_norm.weight",
"model.layers.55.self_attn.k_norm.weight",
"model.layers.55.input_layernorm.weight",
"model.layers.56.self_attn.q_norm.weight",
"model.layers.56.self_attn.k_norm.weight",
"model.layers.56.input_layernorm.weight",
"model.layers.57.self_attn.q_norm.weight",
"model.layers.57.self_attn.k_norm.weight",
"model.layers.57.input_layernorm.weight",
"model.layers.58.self_attn.q_norm.weight",
"model.layers.58.self_attn.k_norm.weight",
"model.layers.58.input_layernorm.weight",
"model.layers.59.self_attn.q_norm.weight",
"model.layers.59.self_attn.k_norm.weight",
"model.layers.59.input_layernorm.weight",
"model.layers.60.self_attn.q_norm.weight",
"model.layers.60.self_attn.k_norm.weight",
"model.layers.60.input_layernorm.weight",
"model.layers.61.self_attn.q_norm.weight",
"model.layers.61.self_attn.k_norm.weight",
"model.layers.61.input_layernorm.weight",
"model.layers.62.self_attn.q_norm.weight",
"model.layers.62.self_attn.k_norm.weight",
"model.layers.62.input_layernorm.weight",
"model.layers.63.self_attn.q_norm.weight",
"model.layers.63.self_attn.k_norm.weight",
"model.layers.63.input_layernorm.weight",
"model.embed_tokens.weight",
"model.norm.weight",
"lm_head.weight"
],
"nbits_per_codebook": 16,
"num_codebooks": 1,
"out_group_size": 1,
"quant_method": "aqlm"
},
"rope_theta": 75000000.0,
"torch_dtype": "float16",
"transformers_version": "4.40.0.dev0",
"use_cache": true,
"use_qk_norm": true,
"vocab_size": 256000
}