Upload model
Browse files- README.md +3 -2
- config.json +29 -70
- generation_config.json +7 -0
- gitattributes +35 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +65 -0
- tokenizer.json +0 -0
- tokenizer_config.json +311 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
---
|
2 |
-
library_name:
|
|
|
3 |
---
|
4 |
|
5 |
# Model Card for Model ID
|
@@ -14,7 +15,7 @@ library_name: diffusers
|
|
14 |
|
15 |
<!-- Provide a longer summary of what this model is. -->
|
16 |
|
17 |
-
This is the model card of a
|
18 |
|
19 |
- **Developed by:** [More Information Needed]
|
20 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
config.json
CHANGED
@@ -1,73 +1,32 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
|
5 |
-
"act_fn": "silu",
|
6 |
-
"addition_embed_type": "text_time",
|
7 |
-
"addition_embed_type_num_heads": 64,
|
8 |
-
"addition_time_embed_dim": 256,
|
9 |
-
"attention_head_dim": [
|
10 |
-
5,
|
11 |
-
10,
|
12 |
-
20
|
13 |
],
|
14 |
-
"
|
15 |
-
"
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"layers_per_block": 2,
|
41 |
-
"mid_block_only_cross_attention": null,
|
42 |
-
"mid_block_scale_factor": 1,
|
43 |
-
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
-
"norm_eps": 1e-05,
|
45 |
-
"norm_num_groups": 32,
|
46 |
-
"num_attention_heads": null,
|
47 |
-
"num_class_embeds": null,
|
48 |
-
"only_cross_attention": false,
|
49 |
-
"out_channels": 4,
|
50 |
-
"projection_class_embeddings_input_dim": 2816,
|
51 |
-
"resnet_out_scale_factor": 1.0,
|
52 |
-
"resnet_skip_time_act": false,
|
53 |
-
"resnet_time_scale_shift": "default",
|
54 |
-
"reverse_transformer_layers_per_block": null,
|
55 |
-
"sample_size": 128,
|
56 |
-
"time_cond_proj_dim": null,
|
57 |
-
"time_embedding_act_fn": null,
|
58 |
-
"time_embedding_dim": null,
|
59 |
-
"time_embedding_type": "positional",
|
60 |
-
"timestep_post_act": null,
|
61 |
-
"transformer_layers_per_block": [
|
62 |
-
1,
|
63 |
-
2,
|
64 |
-
10
|
65 |
-
],
|
66 |
-
"up_block_types": [
|
67 |
-
"CrossAttnUpBlock2D",
|
68 |
-
"CrossAttnUpBlock2D",
|
69 |
-
"UpBlock2D"
|
70 |
-
],
|
71 |
-
"upcast_attention": null,
|
72 |
-
"use_linear_projection": true
|
73 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "giantdev/dippy-2dIe7-sn11m1",
|
3 |
+
"architectures": [
|
4 |
+
"StableLmForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 100257,
|
8 |
+
"eos_token_id": 100257,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_dropout": 0.0,
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"model_type": "stablelm",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pad_token_id": 100257,
|
21 |
+
"partial_rotary_factor": 0.25,
|
22 |
+
"qk_layernorm": false,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.41.0",
|
28 |
+
"use_cache": false,
|
29 |
+
"use_parallel_residual": false,
|
30 |
+
"use_qkv_bias": true,
|
31 |
+
"vocab_size": 100352
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100257,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 100257,
|
6 |
+
"transformers_version": "4.41.0"
|
7 |
+
}
|
gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4013d9e685f49e675f2373095c7fbe8dc4de2538e13283cb4e3b8697f1705b8
|
3 |
+
size 3289069520
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"weight_map": {"pytorch_model-00001-of-340.safetensors": ["model.embed_tokens.weight", "model.layers.0.self_attn.q_proj.weight", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.k_proj.weight", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.v_proj.weight", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.self_attn.o_proj.weight", "model.layers.0.mlp.gate_proj.weight", "model.layers.0.mlp.up_proj.weight", "model.layers.0.mlp.down_proj.weight", "model.layers.0.input_layernorm.weight", "model.layers.0.input_layernorm.bias", "model.layers.0.post_attention_layernorm.weight", "model.layers.0.post_attention_layernorm.bias", "model.layers.1.self_attn.q_proj.weight", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.k_proj.weight", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.v_proj.weight", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.self_attn.o_proj.weight", "model.layers.1.mlp.gate_proj.weight", "model.layers.1.mlp.up_proj.weight", "model.layers.1.mlp.down_proj.weight", "model.layers.1.input_layernorm.weight", "model.layers.1.input_layernorm.bias", "model.layers.1.post_attention_layernorm.weight", "model.layers.1.post_attention_layernorm.bias", "model.layers.2.self_attn.q_proj.weight", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.k_proj.weight", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.v_proj.weight", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.self_attn.o_proj.weight", "model.layers.2.mlp.gate_proj.weight", "model.layers.2.mlp.up_proj.weight", "model.layers.2.mlp.down_proj.weight", "model.layers.2.input_layernorm.weight", "model.layers.2.input_layernorm.bias", "model.layers.2.post_attention_layernorm.weight", "model.layers.2.post_attention_layernorm.bias", "model.layers.3.self_attn.q_proj.weight", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.k_proj.weight", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.v_proj.weight", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.self_attn.o_proj.weight", "model.layers.3.mlp.gate_proj.weight", "model.layers.3.mlp.up_proj.weight", "model.layers.3.mlp.down_proj.weight", "model.layers.3.input_layernorm.weight", "model.layers.3.input_layernorm.bias", "model.layers.3.post_attention_layernorm.weight", "model.layers.3.post_attention_layernorm.bias", "model.layers.4.self_attn.q_proj.weight", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.k_proj.weight", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.v_proj.weight", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.self_attn.o_proj.weight", "model.layers.4.mlp.gate_proj.weight", "model.layers.4.mlp.up_proj.weight", "model.layers.4.mlp.down_proj.weight", "model.layers.4.input_layernorm.weight", "model.layers.4.input_layernorm.bias", "model.layers.4.post_attention_layernorm.weight", "model.layers.4.post_attention_layernorm.bias", "model.layers.5.self_attn.q_proj.weight", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.k_proj.weight", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.v_proj.weight", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.self_attn.o_proj.weight", "model.layers.5.mlp.gate_proj.weight", "model.layers.5.mlp.up_proj.weight", "model.layers.5.mlp.down_proj.weight", "model.layers.5.input_layernorm.weight", "model.layers.5.input_layernorm.bias", "model.layers.5.post_attention_layernorm.weight", "model.layers.5.post_attention_layernorm.bias", "model.layers.6.self_attn.q_proj.weight", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.k_proj.weight", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.v_proj.weight", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.self_attn.o_proj.weight", "model.layers.6.mlp.gate_proj.weight", "model.layers.6.mlp.up_proj.weight", "model.layers.6.mlp.down_proj.weight", "model.layers.6.input_layernorm.weight", "model.layers.6.input_layernorm.bias", "model.layers.6.post_attention_layernorm.weight", "model.layers.6.post_attention_layernorm.bias", "model.layers.7.self_attn.q_proj.weight", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.k_proj.weight", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.v_proj.weight", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.self_attn.o_proj.weight", "model.layers.7.mlp.gate_proj.weight", "model.layers.7.mlp.up_proj.weight", "model.layers.7.mlp.down_proj.weight", "model.layers.7.input_layernorm.weight", "model.layers.7.input_layernorm.bias", "model.layers.7.post_attention_layernorm.weight", "model.layers.7.post_attention_layernorm.bias", "model.layers.8.self_attn.q_proj.weight", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.k_proj.weight", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.v_proj.weight", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.self_attn.o_proj.weight", "model.layers.8.mlp.gate_proj.weight", "model.layers.8.mlp.up_proj.weight", "model.layers.8.mlp.down_proj.weight", "model.layers.8.input_layernorm.weight", "model.layers.8.input_layernorm.bias", "model.layers.8.post_attention_layernorm.weight", "model.layers.8.post_attention_layernorm.bias", "model.layers.9.self_attn.q_proj.weight", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.k_proj.weight", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.v_proj.weight", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.self_attn.o_proj.weight", "model.layers.9.mlp.gate_proj.weight", "model.layers.9.mlp.up_proj.weight", "model.layers.9.mlp.down_proj.weight", "model.layers.9.input_layernorm.weight", "model.layers.9.input_layernorm.bias", "model.layers.9.post_attention_layernorm.weight", "model.layers.9.post_attention_layernorm.bias", "model.layers.10.self_attn.q_proj.weight", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.k_proj.weight", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.v_proj.weight", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.self_attn.o_proj.weight", "model.layers.10.mlp.gate_proj.weight", "model.layers.10.mlp.up_proj.weight", "model.layers.10.mlp.down_proj.weight", "model.layers.10.input_layernorm.weight", "model.layers.10.input_layernorm.bias", "model.layers.10.post_attention_layernorm.weight", "model.layers.10.post_attention_layernorm.bias", "model.layers.11.self_attn.q_proj.weight", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.k_proj.weight", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.v_proj.weight", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.self_attn.o_proj.weight", "model.layers.11.mlp.gate_proj.weight", "model.layers.11.mlp.up_proj.weight", "model.layers.11.mlp.down_proj.weight", "model.layers.11.input_layernorm.weight", "model.layers.11.input_layernorm.bias", "model.layers.11.post_attention_layernorm.weight", "model.layers.11.post_attention_layernorm.bias", "model.layers.12.self_attn.q_proj.weight", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.k_proj.weight", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.v_proj.weight", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.self_attn.o_proj.weight", "model.layers.12.mlp.gate_proj.weight", "model.layers.12.mlp.up_proj.weight", "model.layers.12.mlp.down_proj.weight", "model.layers.12.input_layernorm.weight", "model.layers.12.input_layernorm.bias", "model.layers.12.post_attention_layernorm.weight", "model.layers.12.post_attention_layernorm.bias", "model.layers.13.self_attn.q_proj.weight", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.k_proj.weight", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.v_proj.weight", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.self_attn.o_proj.weight", "model.layers.13.mlp.gate_proj.weight", "model.layers.13.mlp.up_proj.weight", "model.layers.13.mlp.down_proj.weight", "model.layers.13.input_layernorm.weight", "model.layers.13.input_layernorm.bias", "model.layers.13.post_attention_layernorm.weight", "model.layers.13.post_attention_layernorm.bias", "model.layers.14.self_attn.q_proj.weight", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.k_proj.weight", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.v_proj.weight", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.self_attn.o_proj.weight", "model.layers.14.mlp.gate_proj.weight", "model.layers.14.mlp.up_proj.weight", "model.layers.14.mlp.down_proj.weight", "model.layers.14.input_layernorm.weight", "model.layers.14.input_layernorm.bias", "model.layers.14.post_attention_layernorm.weight", "model.layers.14.post_attention_layernorm.bias", "model.layers.15.self_attn.q_proj.weight", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.k_proj.weight", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.v_proj.weight", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.self_attn.o_proj.weight", "model.layers.15.mlp.gate_proj.weight", "model.layers.15.mlp.up_proj.weight", "model.layers.15.mlp.down_proj.weight", "model.layers.15.input_layernorm.weight", "model.layers.15.input_layernorm.bias", "model.layers.15.post_attention_layernorm.weight", "model.layers.15.post_attention_layernorm.bias", "model.layers.16.self_attn.q_proj.weight", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.k_proj.weight", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.v_proj.weight", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.self_attn.o_proj.weight", "model.layers.16.mlp.gate_proj.weight", "model.layers.16.mlp.up_proj.weight", "model.layers.16.mlp.down_proj.weight", "model.layers.16.input_layernorm.weight", "model.layers.16.input_layernorm.bias", "model.layers.16.post_attention_layernorm.weight", "model.layers.16.post_attention_layernorm.bias", "model.layers.17.self_attn.q_proj.weight", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.k_proj.weight", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.v_proj.weight", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.self_attn.o_proj.weight", "model.layers.17.mlp.gate_proj.weight", "model.layers.17.mlp.up_proj.weight", "model.layers.17.mlp.down_proj.weight", "model.layers.17.input_layernorm.weight", "model.layers.17.input_layernorm.bias", "model.layers.17.post_attention_layernorm.weight", "model.layers.17.post_attention_layernorm.bias", "model.layers.18.self_attn.q_proj.weight", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.k_proj.weight", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.v_proj.weight", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.self_attn.o_proj.weight", "model.layers.18.mlp.gate_proj.weight", "model.layers.18.mlp.up_proj.weight", "model.layers.18.mlp.down_proj.weight", "model.layers.18.input_layernorm.weight", "model.layers.18.input_layernorm.bias", "model.layers.18.post_attention_layernorm.weight", "model.layers.18.post_attention_layernorm.bias", "model.layers.19.self_attn.q_proj.weight", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.k_proj.weight", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.v_proj.weight", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.self_attn.o_proj.weight", "model.layers.19.mlp.gate_proj.weight", "model.layers.19.mlp.up_proj.weight", "model.layers.19.mlp.down_proj.weight", "model.layers.19.input_layernorm.weight", "model.layers.19.input_layernorm.bias", "model.layers.19.post_attention_layernorm.weight", "model.layers.19.post_attention_layernorm.bias", "model.layers.20.self_attn.q_proj.weight", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.k_proj.weight", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.v_proj.weight", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.self_attn.o_proj.weight", "model.layers.20.mlp.gate_proj.weight", "model.layers.20.mlp.up_proj.weight", "model.layers.20.mlp.down_proj.weight", "model.layers.20.input_layernorm.weight", "model.layers.20.input_layernorm.bias", "model.layers.20.post_attention_layernorm.weight", "model.layers.20.post_attention_layernorm.bias", "model.layers.21.self_attn.q_proj.weight", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.k_proj.weight", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.v_proj.weight", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.self_attn.o_proj.weight", "model.layers.21.mlp.gate_proj.weight", "model.layers.21.mlp.up_proj.weight", "model.layers.21.mlp.down_proj.weight", "model.layers.21.input_layernorm.weight", "model.layers.21.input_layernorm.bias", "model.layers.21.post_attention_layernorm.weight", "model.layers.21.post_attention_layernorm.bias", "model.layers.22.self_attn.q_proj.weight", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.k_proj.weight", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.v_proj.weight", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.self_attn.o_proj.weight", "model.layers.22.mlp.gate_proj.weight", "model.layers.22.mlp.up_proj.weight", "model.layers.22.mlp.down_proj.weight", "model.layers.22.input_layernorm.weight", "model.layers.22.input_layernorm.bias", "model.layers.22.post_attention_layernorm.weight", "model.layers.22.post_attention_layernorm.bias", "model.layers.23.self_attn.q_proj.weight", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.k_proj.weight", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.v_proj.weight", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.self_attn.o_proj.weight", "model.layers.23.mlp.gate_proj.weight", "model.layers.23.mlp.up_proj.weight", "model.layers.23.mlp.down_proj.weight", "model.layers.23.input_layernorm.weight", "model.layers.23.input_layernorm.bias", "model.layers.23.post_attention_layernorm.weight", "model.layers.23.post_attention_layernorm.bias", "model.norm.weight", "model.norm.bias", "lm_head.weight"]}, "metadata": {"total_size": 3289030656}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|reg_extra|>",
|
4 |
+
"<|endoftext|>",
|
5 |
+
"<|fim_prefix|>",
|
6 |
+
"<|fim_middle|>",
|
7 |
+
"<|fim_suffix|>",
|
8 |
+
"<|fim_pad|>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<filename>",
|
11 |
+
"<issue_start>",
|
12 |
+
"<issue_comment>",
|
13 |
+
"<issue_closed>",
|
14 |
+
"<jupyter_start>",
|
15 |
+
"<jupyter_text>",
|
16 |
+
"<jupyter_code>",
|
17 |
+
"<jupyter_output>",
|
18 |
+
"<empty_output>",
|
19 |
+
"<commit_before>",
|
20 |
+
"<commit_msg>",
|
21 |
+
"<commit_after>",
|
22 |
+
"<reponame>",
|
23 |
+
"<|endofprompt|>",
|
24 |
+
"<|im_start|>",
|
25 |
+
"<|im_end|>",
|
26 |
+
"<|pause|>",
|
27 |
+
"<|reg0|>",
|
28 |
+
"<|reg1|>",
|
29 |
+
"<|reg2|>",
|
30 |
+
"<|reg3|>",
|
31 |
+
"<|reg4|>",
|
32 |
+
"<|reg5|>",
|
33 |
+
"<|reg6|>",
|
34 |
+
"<|reg7|>",
|
35 |
+
"<|extra0|>"
|
36 |
+
],
|
37 |
+
"bos_token": {
|
38 |
+
"content": "<|endoftext|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"eos_token": {
|
45 |
+
"content": "<|endoftext|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
},
|
51 |
+
"pad_token": {
|
52 |
+
"content": "<|endoftext|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false
|
57 |
+
},
|
58 |
+
"unk_token": {
|
59 |
+
"content": "<|endoftext|>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": false,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,311 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"100256": {
|
5 |
+
"content": "<|reg_extra|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100257": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"100258": {
|
21 |
+
"content": "<|fim_prefix|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"100259": {
|
29 |
+
"content": "<|fim_middle|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"100260": {
|
37 |
+
"content": "<|fim_suffix|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"100261": {
|
45 |
+
"content": "<|fim_pad|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"100262": {
|
53 |
+
"content": "<gh_stars>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"100263": {
|
61 |
+
"content": "<filename>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"100264": {
|
69 |
+
"content": "<issue_start>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"100265": {
|
77 |
+
"content": "<issue_comment>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"100266": {
|
85 |
+
"content": "<issue_closed>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"100267": {
|
93 |
+
"content": "<jupyter_start>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"100268": {
|
101 |
+
"content": "<jupyter_text>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"100269": {
|
109 |
+
"content": "<jupyter_code>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"100270": {
|
117 |
+
"content": "<jupyter_output>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"100271": {
|
125 |
+
"content": "<empty_output>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"100272": {
|
133 |
+
"content": "<commit_before>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"100273": {
|
141 |
+
"content": "<commit_msg>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"100274": {
|
149 |
+
"content": "<commit_after>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"100275": {
|
157 |
+
"content": "<reponame>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"100276": {
|
165 |
+
"content": "<|endofprompt|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"100277": {
|
173 |
+
"content": "<|im_start|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"100278": {
|
181 |
+
"content": "<|im_end|>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"100279": {
|
189 |
+
"content": "<|pause|>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"100280": {
|
197 |
+
"content": "<|reg0|>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"100281": {
|
205 |
+
"content": "<|reg1|>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"100282": {
|
213 |
+
"content": "<|reg2|>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"100283": {
|
221 |
+
"content": "<|reg3|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"100284": {
|
229 |
+
"content": "<|reg4|>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"100285": {
|
237 |
+
"content": "<|reg5|>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"100286": {
|
245 |
+
"content": "<|reg6|>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"100287": {
|
253 |
+
"content": "<|reg7|>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"100288": {
|
261 |
+
"content": "<|extra0|>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
}
|
268 |
+
},
|
269 |
+
"additional_special_tokens": [
|
270 |
+
"<|reg_extra|>",
|
271 |
+
"<|endoftext|>",
|
272 |
+
"<|fim_prefix|>",
|
273 |
+
"<|fim_middle|>",
|
274 |
+
"<|fim_suffix|>",
|
275 |
+
"<|fim_pad|>",
|
276 |
+
"<gh_stars>",
|
277 |
+
"<filename>",
|
278 |
+
"<issue_start>",
|
279 |
+
"<issue_comment>",
|
280 |
+
"<issue_closed>",
|
281 |
+
"<jupyter_start>",
|
282 |
+
"<jupyter_text>",
|
283 |
+
"<jupyter_code>",
|
284 |
+
"<jupyter_output>",
|
285 |
+
"<empty_output>",
|
286 |
+
"<commit_before>",
|
287 |
+
"<commit_msg>",
|
288 |
+
"<commit_after>",
|
289 |
+
"<reponame>",
|
290 |
+
"<|endofprompt|>",
|
291 |
+
"<|im_start|>",
|
292 |
+
"<|im_end|>",
|
293 |
+
"<|pause|>",
|
294 |
+
"<|reg0|>",
|
295 |
+
"<|reg1|>",
|
296 |
+
"<|reg2|>",
|
297 |
+
"<|reg3|>",
|
298 |
+
"<|reg4|>",
|
299 |
+
"<|reg5|>",
|
300 |
+
"<|reg6|>",
|
301 |
+
"<|reg7|>",
|
302 |
+
"<|extra0|>"
|
303 |
+
],
|
304 |
+
"bos_token": "<|endoftext|>",
|
305 |
+
"clean_up_tokenization_spaces": true,
|
306 |
+
"eos_token": "<|endoftext|>",
|
307 |
+
"model_max_length": 1000000000000000019884624838656,
|
308 |
+
"pad_token": "<|endoftext|>",
|
309 |
+
"tokenizer_class": "GPT2Tokenizer",
|
310 |
+
"unk_token": "<|endoftext|>"
|
311 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|