Aratako commited on
Commit
b8cd6c5
1 Parent(s): 8c84a4d

model upload

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./ELYZA-japanese-Llama-2-7b-fast-instruct",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
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": 32,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.38.1",
32
+ "use_cache": true,
33
+ "vocab_size": 45043
34
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ base_model: ./ELYZA-japanese-Llama-2-7b-fast-instruct
2
+ gate_mode: random
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: ./ELYZA-japanese-Llama-2-7b-fast-instruct
6
+ positive_prompts: []
7
+ - source_model: ./ELYZA-japanese-Llama-2-7b-fast
8
+ positive_prompts: []
9
+ tokenizer_source: model:./ELYZA-japanese-Llama-2-7b-fast-instruct
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5b380402e2fddee441fdffdad75ee9c6981b34a089cc8a2a095542cdf0b158
3
+ size 9921671448
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd23e4b7c77ffa1e2fe62e365e965ee226a8b26675bb6bdd82a2ea7b084d07c
3
+ size 9949157040
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bafa903f0d1f8efedb8bfbe0cd3e8e656129a76624fea6dd3c09ff5c135ac7
3
+ size 2477318752
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-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "lm_head.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.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_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "max_length": 3363,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<s>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "stride": 0,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "truncation_side": "right",
42
+ "truncation_strategy": "longest_first",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }