mateussj commited on
Commit
ca1e48f
·
verified ·
1 Parent(s): fe2196d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/mistral-7b-v0.3",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 770,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 1000000.0,
25
+ "router_aux_loss_coef": 0.001,
26
+ "router_jitter_noise": 0.0,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.48.2",
31
+ "unsloth_version": "2024.9",
32
+ "use_cache": true,
33
+ "vocab_size": 32768
34
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ base_model: unsloth/mistral-7b-v0.3
2
+ gate_mode: random
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: unsloth/mistral-7b-v0.3
6
+ - source_model: unsloth/mistral-7b-v0.3
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338ea9b9d19574939d2407cd0bd83a00cea0ffd8607c32ccc26223ea279fa1b1
3
+ size 4999726008
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b896e21f3e2bf1a7442f1b9c3fb5cfd05c167302bee50e7da020660e234ad
3
+ size 4932617672
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb772503eec5b33584f9e7444cd4f9fb6d319722205e7c8ee39e770082349062
3
+ size 4966163504
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0234f4f6a00c89356364d6beb41c93640549a79d89754f7ceb903618295cc001
3
+ size 4966163504
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca11ca2f45352cb790c2a1eae830011d0f7be1d2f03b0e2d15716591a1ef79a
3
+ size 4932626016
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d838721dd186a5084c2c2b72973c20e70a09586ad93f85bc55fc8ff7e861b9
3
+ size 973615768
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff