ehristoforu
commited on
Upload folder using huggingface_hub
Browse files- config.json +36 -0
- mergekit_moe_config.yml +7 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiiuae/Falcon3-7B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 11,
|
9 |
+
"eos_token_id": 11,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 23040,
|
15 |
+
"max_position_embeddings": 32768,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "mixtral",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_experts_per_tok": 2,
|
20 |
+
"num_hidden_layers": 28,
|
21 |
+
"num_key_value_heads": 4,
|
22 |
+
"num_local_experts": 2,
|
23 |
+
"output_router_logits": false,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"rms_norm_eps": 1e-06,
|
26 |
+
"rope_scaling": null,
|
27 |
+
"rope_theta": 1000042,
|
28 |
+
"router_aux_loss_coef": 0.001,
|
29 |
+
"router_jitter_noise": 0.0,
|
30 |
+
"sliding_window": null,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.46.3",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 131072
|
36 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: tiiuae/Falcon3-7B-Instruct
|
2 |
+
gate_mode: random
|
3 |
+
architecture: mixtral
|
4 |
+
dtype: bfloat16
|
5 |
+
experts:
|
6 |
+
- source_model: tiiuae/Falcon3-7B-Instruct
|
7 |
+
- source_model: tiiuae/Falcon3-7B-Instruct
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:837751119a1ee515c5d9e2503573d788be9e18fd8d79e00bb1e5872f5f618dd3
|
3 |
+
size 4879092736
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd4ac27cd6aba377d5ad00cf92ff12e050ebb52819d4ec865b2b1b88fd126b87
|
3 |
+
size 4973478200
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0651d615694a4bb750acabb8d6750f2223bf724eb92dbc054d3d44f0dfce7043
|
3 |
+
size 4923133664
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd1b2ae80c9710a5a3c0aa9d55c15babc12ea676c21b277403666f27cf5d8b74
|
3 |
+
size 4973478304
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3e31c47e15d07156f6875a877f8bb0a6cac1701a736ebbdf94ffc4d083ff0eb
|
3 |
+
size 4923133664
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d42c28881e0a320070dd2fb925116fcf0991e64f44ad1d6d5c1e1a68d4d9c49
|
3 |
+
size 2130025776
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 26802296832}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>EMAIL_ADDRESS<<",
|
12 |
+
">>IP_ADDRESS<<",
|
13 |
+
"<|startoftext|>",
|
14 |
+
">>IP_ADDRESS_0<<",
|
15 |
+
">>IP_ADDRESS_1<<",
|
16 |
+
">>IP_ADDRESS_2<<",
|
17 |
+
">>IP_ADDRESS_3<<",
|
18 |
+
">>IP_ADDRESS_4<<",
|
19 |
+
">>IP_ADDRESS_5<<",
|
20 |
+
">>IP_ADDRESS_6<<",
|
21 |
+
">>IP_ADDRESS_7<<",
|
22 |
+
">>IP_ADDRESS_8<<",
|
23 |
+
">>IP_ADDRESS_9<<",
|
24 |
+
">>PASSWORD<<",
|
25 |
+
">>KEY<<"
|
26 |
+
],
|
27 |
+
"eos_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"pad_token": "<|endoftext|>"
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|