初始化项目,由ModelHub XC社区提供模型
Model: Zyphra/Zamba2-2.7B-instruct Source: Original Platform
This commit is contained in:
102
zamba2_2p7B-instruct_original/config.json
Normal file
102
zamba2_2p7B-instruct_original/config.json
Normal file
@@ -0,0 +1,102 @@
|
||||
{
|
||||
"_name_or_path": "Zyphra/Zamba2-2.7B-instruct",
|
||||
"add_bias_linear": false,
|
||||
"architectures": [
|
||||
"Zamba2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"conv_dimension": 4,
|
||||
"eos_token_id": 2,
|
||||
"expansion_factor": 2,
|
||||
"ffn_hidden_size": 10240,
|
||||
"ft_lora": false,
|
||||
"gated_linear_unit": true,
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"kv_channels": 80,
|
||||
"layers_block_type": [
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m",
|
||||
"m",
|
||||
"g",
|
||||
"m",
|
||||
"m"
|
||||
],
|
||||
"lora_rank": 128,
|
||||
"lora_rank_mamba": 128,
|
||||
"mamba_headdim": 64,
|
||||
"mamba_ngroups": 1,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "zamba2",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 54,
|
||||
"num_key_value_heads": 32,
|
||||
"num_logits_to_keep": 1,
|
||||
"num_mem_blocks": 2,
|
||||
"num_query_groups": 32,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000,
|
||||
"se_shared_attention_lora": false,
|
||||
"sliding_window": null,
|
||||
"state_size": 64,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.43.0.dev0",
|
||||
"use_cache": false,
|
||||
"use_long_context": false,
|
||||
"use_mamba_kernels": true,
|
||||
"use_mem_eff_path": false,
|
||||
"use_mem_rope": false,
|
||||
"use_shared_attention_lora": false,
|
||||
"use_shared_block_lora": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
zamba2_2p7B-instruct_original/generation_config.json
Normal file
7
zamba2_2p7B-instruct_original/generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.43.0.dev0"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b2296e886390d354763bc522782582186b0e0a35da64028e8b3fe534def7350
|
||||
size 4994052944
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f120af353d405db76ab8381106f160df4c9dc17b8cc6a5911a9dd5b7789ea34a
|
||||
size 383523176
|
||||
556
zamba2_2p7B-instruct_original/model.safetensors.index.json
Normal file
556
zamba2_2p7B-instruct_original/model.safetensors.index.json
Normal file
@@ -0,0 +1,556 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5377513280
|
||||
},
|
||||
"weight_map": {
|
||||
"model.blocks.0.feed_forward.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.0.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.3.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.4.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.5.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.6.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.7.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_A_list.8.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.0.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.3.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.4.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.5.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.6.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.7.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc1_lora_B_list.8.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.feed_forward.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.0.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.3.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.4.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.5.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.6.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.7.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_A_list.8.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.0.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.3.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.4.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.5.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.6.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.7.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc1_lora_B_list.8.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.feed_forward.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.blocks.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.0.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.3.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.4.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.5.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.6.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.7.weight": "model-00002-of-00002.safetensors",
|
||||
"model.linear_layers.8.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.12.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.18.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.21.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.24.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.25.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.26.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.27.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.28.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.29.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.30.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.31.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.32.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.33.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.34.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.35.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.36.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.37.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.38.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.39.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.40.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.41.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.42.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.43.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.44.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.45.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.46.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.47.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.48.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.49.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.50.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.A_log": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.D": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.dt_bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.51.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.A_log": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.D": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.dt_bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.52.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.A_log": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.D": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.dt_bias": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.53.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.mamba_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.7.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.D": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.dt_bias": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.mamba_layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
27
zamba2_2p7B-instruct_original/special_tokens_map.json
Normal file
27
zamba2_2p7B-instruct_original/special_tokens_map.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91123
zamba2_2p7B-instruct_original/tokenizer.json
Normal file
91123
zamba2_2p7B-instruct_original/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
51
zamba2_2p7B-instruct_original/tokenizer_config.json
Normal file
51
zamba2_2p7B-instruct_original/tokenizer_config.json
Normal file
@@ -0,0 +1,51 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"max_length": 4096,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "[PAD]",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"stride": 0,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user