ehristoforu
commited on
Commit
•
96dc577
1
Parent(s):
4738089
Upload folder using huggingface_hub
Browse files- README.md +39 -0
- config.json +27 -0
- mergekit_config.yml +9 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- unsloth/Mistral-Nemo-Instruct-2407
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
|
9 |
+
---
|
10 |
+
# merge
|
11 |
+
|
12 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
+
|
14 |
+
## Merge Details
|
15 |
+
### Merge Method
|
16 |
+
|
17 |
+
This model was merged using the passthrough merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [unsloth/Mistral-Nemo-Instruct-2407](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
slices:
|
30 |
+
- sources:
|
31 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
32 |
+
layer_range: [0, 16]
|
33 |
+
- sources:
|
34 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
35 |
+
layer_range: [18, 32]
|
36 |
+
merge_method: passthrough
|
37 |
+
dtype: bfloat16
|
38 |
+
|
39 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 1024000,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 30,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.39.3",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 131072
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
4 |
+
layer_range: [0, 16]
|
5 |
+
- sources:
|
6 |
+
- model: unsloth/Mistral-Nemo-Instruct-2407
|
7 |
+
layer_range: [18, 32]
|
8 |
+
merge_method: passthrough
|
9 |
+
dtype: bfloat16
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0976f749096a1de7efab905b13563c1685c23f06092ba41afb4d73dc595cc4f
|
3 |
+
size 1887501944
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34b1e77558cf740a0e06a6c8db15b949c95af782123136b294cc8b6253dccd6b
|
3 |
+
size 1635843120
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f60b9ea2403a077f62ae49c2d96fadf59988e8a3aa5e5fa6e8677bef0643ea1b
|
3 |
+
size 1887437760
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cda96ae5d756aeb196e5606aa9e598a66559bc61f0b01e756a5ce2b805f1dea
|
3 |
+
size 1887522688
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f7ea9a498a25c4cd2f600638ab8d03cab3b7d63534d97b56fa81d2542476496
|
3 |
+
size 1929444648
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b21d4eff4b841c935393f5fb8705e081f710e2b253d7be27b19a68ce0e414d89
|
3 |
+
size 1887522680
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6bfd1c84a83b24773ed7b1ad808c6bc0cba070d293981ee6183e2f0c8ee9554
|
3 |
+
size 1929444672
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7abb299efd55488feb38c39ff1897bf4c49c798190fd54ef460ec845a0031129
|
3 |
+
size 1929465376
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e37c18d14cbcd1da32d757898bc71da5eaae355adf78dd58debb5fc0d961f7
|
3 |
+
size 1887522688
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:720f3d87f63a26e00ae8504df3fad2afc4b134f0fd9f731a4fd5493110a0d0c5
|
3 |
+
size 838903272
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75f675510870b5495483236d89ae434a8d7277684dea3295ce4e02341e420a4c
|
3 |
+
size 1342187744
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 19042764800}, "weight_map": {"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.embed_tokens.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
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
The diff for this file is too large to render.
See raw diff
|
|