Upload 34 files
Browse files- config.json +31 -0
- model-00001-of-00029.safetensors +3 -0
- model-00002-of-00029.safetensors +3 -0
- model-00003-of-00029.safetensors +3 -0
- model-00004-of-00029.safetensors +3 -0
- model-00005-of-00029.safetensors +3 -0
- model-00006-of-00029.safetensors +3 -0
- model-00007-of-00029.safetensors +3 -0
- model-00008-of-00029.safetensors +3 -0
- model-00009-of-00029.safetensors +3 -0
- model-00010-of-00029.safetensors +3 -0
- model-00011-of-00029.safetensors +3 -0
- model-00012-of-00029.safetensors +3 -0
- model-00013-of-00029.safetensors +3 -0
- model-00014-of-00029.safetensors +3 -0
- model-00015-of-00029.safetensors +3 -0
- model-00016-of-00029.safetensors +3 -0
- model-00017-of-00029.safetensors +3 -0
- model-00018-of-00029.safetensors +3 -0
- model-00019-of-00029.safetensors +3 -0
- model-00020-of-00029.safetensors +3 -0
- model-00021-of-00029.safetensors +3 -0
- model-00022-of-00029.safetensors +3 -0
- model-00023-of-00029.safetensors +3 -0
- model-00024-of-00029.safetensors +3 -0
- model-00025-of-00029.safetensors +3 -0
- model-00026-of-00029.safetensors +3 -0
- model-00027-of-00029.safetensors +3 -0
- model-00028-of-00029.safetensors +3 -0
- model-00029-of-00029.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +213 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Rosa",
|
3 |
+
"architectures": [
|
4 |
+
"StableLMEpochForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "Aryanne/Astridboros-3B--configuration_stablelm_epoch.StableLMEpochConfig",
|
8 |
+
"AutoModelForCausalLM": "Aryanne/Astridboros-3B--modeling_stablelm_epoch.StableLMEpochForCausalLM"
|
9 |
+
},
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 2560,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 6912,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"model_type": "stablelm_epoch",
|
18 |
+
"norm_eps": 1e-05,
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"rope_pct": 0.25,
|
24 |
+
"rope_theta": 10000,
|
25 |
+
"rotary_scaling_factor": 1.0,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.35.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50304
|
31 |
+
}
|
model-00001-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15f1dc5ca333bf4083845f360fa0b173ef1ff5dc356d40d97688865877cb38ee
|
3 |
+
size 515113096
|
model-00002-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:255b1809ef2aeb5cd5fffb4026d0bedf755af4918542c0cf6e267102e5e4ac25
|
3 |
+
size 194018864
|
model-00003-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f82419b6a666300a0afc1435a426b01836f06b3aceb2bab6c942861a3c64b5
|
3 |
+
size 194008424
|
model-00004-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ea5120e980cc1124b555a388cdbab1e9a0782d893ab3aec113552c3f52a0c4
|
3 |
+
size 194018896
|
model-00005-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df9ee72f3c4ec8ee61f00737e167e1530741bc674527dfe3d908c25ddeff403
|
3 |
+
size 197940824
|
model-00006-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b74aec8b8b7cc36c66d7a60d7564c1f01f6597e6b223c8591400a46a48aaf29
|
3 |
+
size 171736656
|
model-00007-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef684df38643bc7c7125c7905ca53052787d5518a7b0716de49baf81ac6dc22
|
3 |
+
size 194008440
|
model-00008-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc16c9d7ca007410f54d4ff834c01ff583244d2321b0d43edb5e7176347d2b7
|
3 |
+
size 194008432
|
model-00009-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67715681ed1f7a7bdf7dcc90dd5b1ef8954ee5b49cf9e43b39c395d162f3737
|
3 |
+
size 194018896
|
model-00010-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc610fc55c44b8ce6b1048b652d4782777c30fa060a54ee1663bdbe99a5c4c64
|
3 |
+
size 197940824
|
model-00011-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7924afb74c8416d43937e7df5f83a062f1dc6f6e6e41faace9e4e413f4c86f
|
3 |
+
size 171736656
|
model-00012-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1afd7cc8f3406f435d792300cc216e0ae06516223b529ef9d2359d9afea82b4
|
3 |
+
size 194008432
|
model-00013-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f4b52a5721d3db416a483805a18acdeea5b9be9d2885dc91392d9232d0ebf21
|
3 |
+
size 194008432
|
model-00014-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd9c468b5a1491ae566ce615ab84e1696e0599a82b705ccb90a2d432cf31d279
|
3 |
+
size 194018896
|
model-00015-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94cf31caf4cfd6af3a536bb1a7a14682987941e155f6bcf28293652d34a0633
|
3 |
+
size 197940824
|
model-00016-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:751f0a5885962369d8c23652939c70710d74ac92c2c76ff0191dcef3d85532e6
|
3 |
+
size 171736656
|
model-00017-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3f08bc6fde3571c65db3a4704d49346cb8538e079ba72f2ac11c46070378254
|
3 |
+
size 194008440
|
model-00018-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02f5c17c8cd54690536895d840fa64175df697f6e7f66b1e7ce0edef0ac210d5
|
3 |
+
size 194008432
|
model-00019-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4c68201329faa35f4980495dfc1b0bd444f60f3e4a9d131f5d721e2f944537
|
3 |
+
size 194018896
|
model-00020-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:304a0a95572fd61bc06626aa0d721234921b5121cb3af03ca2b54501a60bca41
|
3 |
+
size 175648112
|
model-00021-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5eecb95dc009738e5e22a36781242061c79b4765a68d3662e5c904c4bbb0a73
|
3 |
+
size 194008424
|
model-00022-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51de56035634e3b915ca6db99cc177c1a5a7246042fd6cff38c86cdea103c51d
|
3 |
+
size 194008416
|
model-00023-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9580d97fdedf8acd2f2fbdf6b3852bc5fbbb72d4b4e9bb5aa2d6578e811b370e
|
3 |
+
size 194018888
|
model-00024-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145aa87920598c6b3c451207b53be40ab70cadc7b352f933384641fb5f091e3a
|
3 |
+
size 197940808
|
model-00025-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d85e933ce0fa2454a3cad94f1f5cf409a8bdf281a7ceab0663d96fc7e62ed0f7
|
3 |
+
size 171736640
|
model-00026-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f3a142a4ab2905e9e657a3f35962bd1fe0c800086ad2cef3b5ec3c4c86057da
|
3 |
+
size 158608416
|
model-00027-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:876a2aaa79df7e4c466f659879091db10abad4311c8d7fcad4474e9ddccee496
|
3 |
+
size 515113088
|
model-00028-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5724a13c28c25a342782afeaa53d9f5f3514b863660a643577c80169e55e294a
|
3 |
+
size 194039808
|
model-00029-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b15ec472b61158c0eb2c0e3abc7c15ab539798815c3b2ea820a255f0978077e0
|
3 |
+
size 158618848
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00029.safetensors", "model.layers.0.input_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.1.input_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00003-of-00029.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.input_layernorm.bias": "model-00003-of-00029.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.input_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.input_layernorm.bias": "model-00005-of-00029.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00029.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.input_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.14.input_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00007-of-00029.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.15.input_layernorm.bias": "model-00007-of-00029.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00008-of-00029.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.input_layernorm.bias": "model-00008-of-00029.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.input_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.input_layernorm.bias": "model-00010-of-00029.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00010-of-00029.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.input_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.2.input_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00012-of-00029.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.20.input_layernorm.bias": "model-00012-of-00029.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00013-of-00029.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.input_layernorm.bias": "model-00013-of-00029.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.input_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.input_layernorm.bias": "model-00015-of-00029.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00015-of-00029.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.input_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.25.input_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00017-of-00029.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.26.input_layernorm.bias": "model-00017-of-00029.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00018-of-00029.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.input_layernorm.bias": "model-00018-of-00029.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.input_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.28.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.3.input_layernorm.bias": "model-00020-of-00029.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00021-of-00029.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.4.input_layernorm.bias": "model-00021-of-00029.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00022-of-00029.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.input_layernorm.bias": "model-00022-of-00029.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.input_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.6.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.input_layernorm.bias": "model-00024-of-00029.safetensors", "model.layers.7.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00024-of-00029.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.input_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.8.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.9.input_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.9.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00026-of-00029.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "lm_head.weight": "model-00027-of-00029.safetensors", "model.layers.29.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.29.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.30.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.31.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.31.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00029-of-00029.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.norm.bias": "model-00029-of-00029.safetensors", "model.norm.weight": "model-00029-of-00029.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|padding|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50254": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50255": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50256": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50257": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50258": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50259": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50260": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50261": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50262": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50263": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50264": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50265": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50266": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50267": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50268": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50269": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50270": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50271": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50272": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50273": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50274": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50275": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50276": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
}
|
204 |
+
},
|
205 |
+
"bos_token": "<|endoftext|>",
|
206 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
207 |
+
"clean_up_tokenization_spaces": true,
|
208 |
+
"eos_token": "<|endoftext|>",
|
209 |
+
"model_max_length": 1000000000000000019884624838656,
|
210 |
+
"pad_token": "<|endoftext|>",
|
211 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
212 |
+
"unk_token": "<|endoftext|>"
|
213 |
+
}
|