Inv commited on
Commit
bf27b7a
1 Parent(s): 40d75fe

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openbmb/MiniCPM-2B-sft-bf16-llama-format",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dim_model_base": 256,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2304,
13
+ "initializer_range": 0.1,
14
+ "intermediate_size": 5760,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 36,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 40,
20
+ "num_key_value_heads": 36,
21
+ "num_local_experts": 4,
22
+ "output_router_logits": false,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "scale_depth": 1.4,
29
+ "scale_emb": 12,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.37.2",
34
+ "use_cache": true,
35
+ "vocab_size": 122753
36
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: openbmb/MiniCPM-2B-sft-bf16-llama-format
3
+ dtype: bfloat16
4
+ gate_mode: random
5
+ parameters:
6
+ int8_mask: true
7
+ experts:
8
+ - source_model: openbmb/MiniCPM-2B-sft-bf16-llama-format
9
+ positive_prompts:
10
+ - ""
11
+ - source_model: openbmb/MiniCPM-2B-sft-bf16-llama-format
12
+ positive_prompts:
13
+ - ""
14
+ - source_model: openbmb/MiniCPM-2B-sft-bf16-llama-format
15
+ positive_prompts:
16
+ - ""
17
+ - source_model: openbmb/MiniCPM-2B-sft-bf16-llama-format
18
+ positive_prompts:
19
+ - ""
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8afb4023f14958f36836c726f2b8702ca82172f04a9372882e8857d7d5c7fc7
3
+ size 1975367976
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd708206c0476a9b4e049e224d1082a3d3e6477655757cbca423b9b9eb623db
3
+ size 1990714224
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7df0a3e4bc982a304a472253fcc60fd06508aaa31068db5f1a1ddfce728a804
3
+ size 1980107104
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe495b8c783528f5cbcb26fe30d902c560e9ee63c10f9918c49d3636b22d3da
3
+ size 1990714320
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05eef36be9d95eff29e4af1e151300c06e71a2a29768b38237bee2fe3d490332
3
+ size 1980107144
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956ef109cd9ff63ff0cb37c9f11fd879d85eab858b9087f06d9de7abfe4a157a
3
+ size 1990714320
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e96755a3af3cabf9213bb4dd34a81d9d83062e30e6ba9e015bb36f7a16762085
3
+ size 1980107144
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4850f2eac081626be0f9bd7262bb4392a32afc12b6a95cd314df79269c86229e
3
+ size 1683556784
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.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:c9aafcd7da1f5611dab6be545db74d5552a2ccc9c2a12c72ea7be63aac4a25d7
3
+ size 1994871
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }