mateussj commited on
Commit
5805327
1 Parent(s): 461d5e8

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.37.2",
31
+ "use_cache": true,
32
+ "vocab_size": 32000
33
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
6
+ positive_prompts:
7
+ - "Legal"
8
+ - "Subpoena"
9
+ - "Crime"
10
+ - "Legal action"
11
+ - "Court"
12
+ - "Jurisprudence"
13
+ - "U.S. Code"
14
+ - "USC"
15
+ negative_prompts:
16
+ - "Python"
17
+ - "SQL"
18
+ - "JavaScript"
19
+ - "C++"
20
+ - "Computer"
21
+ - "Engineering"
22
+ - "coding"
23
+ - "debug"
24
+ - "troubleshoot"
25
+ - source_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
26
+ positive_prompts:
27
+ - "Python"
28
+ - "SQL"
29
+ - "JavaScript"
30
+ - "C++"
31
+ - "Computer"
32
+ - "Engineering"
33
+ - "coding"
34
+ - "debug"
35
+ - "troubleshoot"
36
+ negative_prompts:
37
+ - "Legal"
38
+ - "Subpoena"
39
+ - "Crime"
40
+ - "Legal action"
41
+ - "Court"
42
+ - "Jurisprudence"
43
+ - "U.S. Code"
44
+ - "USC"
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b37e20afe5eb17802428a737baa9e97a45a8da83d97081aec9f70fc71665372
3
+ size 3722844824
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<s>",
36
+ "padding_side": "left",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }