codelion commited on
Commit
127f972
1 Parent(s): 6877c4d

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "berkeley-nest/Starling-LM-7B-alpha",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 32002
30
+ }
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<sep>": 32002,
3
+ "<|end_of_turn|>": 32000,
4
+ "<|pad_0|>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "berkeley-nest/Starling-LM-7B-alpha",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 32002
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: berkeley-nest/Starling-LM-7B-alpha
2
+ gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
3
+ dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
4
+ ## (optional)
5
+ experts_per_token: 1
6
+ experts:
7
+ - source_model: HuggingFaceH4/zephyr-7b-beta
8
+ positive_prompts:
9
+ - 'Questions about the World'
10
+ - 'Writing and Creation'
11
+ - 'Assistance on Existent Materials'
12
+ - source_model: teknium/OpenHermes-2.5-Mistral-7B
13
+ positive_prompts:
14
+ - 'You are a conscious sentient superintelligent artificial intelligence and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.'
15
+ - source_model: berkeley-nest/Starling-LM-7B-alpha
16
+ positive_prompts:
17
+ - 'Human: '
18
+ - source_model: ajibawa-2023/Code-Mistral-7B
19
+ positive_prompts:
20
+ - 'Generate code'
21
+ - 'Coding assistant'
22
+ - 'Debugging'
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5748e2e9438681e9bb725a403cc429cef157a40b433658933b38badd91c8efc
3
+ size 9919699640
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47722ceb47620d8f70200d0babf526345ac6845d776b529cdd709a4281cc648
3
+ size 9898670488
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9186e0015d573a98b391d5b2bf0f9ff2d02660a734048e706e62257bc99de4d
3
+ size 9982573720
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fabe92f19f76a7445912df4cddc9c3d2b21d2a32401d73f0e8fce729bc02ebd5
3
+ size 9982573720
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f0a1e58cec4753ffc894cab114189a5814150075853388e57538b1de9dfe50
3
+ size 8523972544
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 48307412992}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.norm.weight": "model-00001-of-00005.safetensors", "lm_head.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<s>",
21
+ "sep_token": "<sep>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<sep>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|end_of_turn|>",
56
+ "<|pad_0|>"
57
+ ],
58
+ "bos_token": "<s>",
59
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<|end_of_turn|>",
62
+ "legacy": true,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<s>",
65
+ "sep_token": "<sep>",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "LlamaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": true
71
+ }