Undi95 commited on
Commit
49ad1a4
1 Parent(s): 70354cd

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 2,
20
+ "output_router_logits": false,
21
+ "pad_token_id": 2,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 10000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.0.dev0",
30
+ "unsloth_version": "2024.1",
31
+ "use_cache": false,
32
+ "vocab_size": 32000
33
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MixtralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mixtral",
14
+ "num_attention_heads": 32,
15
+ "num_experts_per_tok": 2,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "num_local_experts": 2,
19
+ "output_router_logits": false,
20
+ "pad_token_id": 2,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.40.0.dev0",
29
+ "unsloth_version": "2024.1",
30
+ "use_cache": false,
31
+ "vocab_size": 32000
32
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca0cc77d4d687e117da20538a9f9da547118a0789279ea881c2ac6c12c51a75
3
+ size 9919813704
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39344b24b67a46e2669ee5e38f9da8251e3fb2f2c858e137f739ba6520224cae
3
+ size 9982454736
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b7a575bc32e34127868533eb76cb48b905e4d9d4af239282e94f7a30d1a730
3
+ size 5856061016
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.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.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.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.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.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.w3.weight": "model-00001-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.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", "lm_head.weight": "model-00001-of-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.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.5.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.4.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.3.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.2.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.1.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.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.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.15.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.14.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.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.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.23.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.22.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.21.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.20.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.19.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.18.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.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.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.27.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.26.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.25.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.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.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.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.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.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.w1.weight": "model-00002-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.w1.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.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.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.10.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.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.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.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.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.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.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.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_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.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_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.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_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.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 255,
41
+ "pad_token": "<s>",
42
+ "padding_side": "right",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "split_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }