R136a1 commited on
Commit
20fb157
1 Parent(s): 9a404ba

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - safetensors
7
+ - mixtral
8
+ ---
9
+
10
+ I prefer this one instead of v1 since it's a bit more creative and _smart_, understand the story better. This use some different models from the v1 but perform very close to it (I guess since I used the same model for the base?). And yeah, I'm using this as daily model for RP (llama 3 is smart but not creative enough for RP, I think because lack of RP and _ERP_ data in their training set? idk.)
11
+
12
+
13
+ Testing done.
14
+
15
+ It performs really well in complex scenario and follows the character card quite well. The char card and previous message can affect a lot to the next reply style.
16
+
17
+ The main idea is instead of _merging_ models to create new model, I try to put these best model into mixtral so it can work together. And the result is good, every model has its uniqueness and strength.
18
+
19
+ Downside? it only support 8k (8192) context length...
20
+
21
+ Alpaca prompting format.
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/InfinityRP",
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": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "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
+ "use_cache": true,
30
+ "vocab_size": 32000,
31
+ "quantization_config": {
32
+ "quant_method": "exl2",
33
+ "version": "0.2.3",
34
+ "bits": 4.6,
35
+ "head_bits": 8,
36
+ "calibration": {
37
+ "rows": 100,
38
+ "length": 2048,
39
+ "dataset": "dataset"
40
+ }
41
+ }
42
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: /content/InfinityRP
2
+ gate_mode: random
3
+ dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
4
+ ## (optional)
5
+ experts_per_token: 2
6
+ experts:
7
+ - source_model: /content/Aurav2
8
+ positive_prompts: []
9
+ - source_model: /content/Spice
10
+ positive_prompts: []
11
+ - source_model: /content/InfinityRP
12
+ positive_prompts: []
13
+ - source_model: /content/DaCo
14
+ positive_prompts: []
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 48307380224}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors", "lm_head.weight": "model-00005-of-00005.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors"}}
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7fb88992ffcba5c7229eebc5abd8da1ac07c96b6854860b2e4bcdb02b39484
3
+ size 14131275664
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
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
+ }