TroyDoesAI
commited on
Commit
•
25fe3e6
1
Parent(s):
dd4fc97
Mermaid Mistral for Flow Diagrams, BlackSheep For Personality
Browse files- README.md +50 -1
- config.json +27 -0
- mergekit_config.yml +20 -0
- model-00001-of-00010.safetensors +3 -0
- model-00002-of-00010.safetensors +3 -0
- model-00003-of-00010.safetensors +3 -0
- model-00004-of-00010.safetensors +3 -0
- model-00005-of-00010.safetensors +3 -0
- model-00006-of-00010.safetensors +3 -0
- model-00007-of-00010.safetensors +3 -0
- model-00008-of-00010.safetensors +3 -0
- model-00009-of-00010.safetensors +3 -0
- model-00010-of-00010.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- TroyDoesAI/Mermaid-22B
|
4 |
+
- TroyDoesAI/BlackSheep-Mistral-22B
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
---
|
11 |
+
# MermaidMistral-22B
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the SLERP merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [TroyDoesAI/Mermaid-22B](https://huggingface.co/TroyDoesAI/Mermaid-22B)
|
24 |
+
* [TroyDoesAI/BlackSheep-Mistral-22B](https://huggingface.co/TroyDoesAI/BlackSheep-Mistral-22B)
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
slices:
|
32 |
+
- sources:
|
33 |
+
- model: TroyDoesAI/BlackSheep-Mistral-22B
|
34 |
+
layer_range: [0, 56]
|
35 |
+
- model: TroyDoesAI/Mermaid-22B
|
36 |
+
layer_range: [0, 56]
|
37 |
+
# or, the equivalent models: syntax:
|
38 |
+
# models:
|
39 |
+
# - model: psmathur/orca_mini_v3_13b
|
40 |
+
# - model: garage-bAInd/Platypus2-13B
|
41 |
+
merge_method: slerp
|
42 |
+
base_model: TroyDoesAI/BlackSheep-Mistral-22B
|
43 |
+
parameters:
|
44 |
+
t:
|
45 |
+
- filter: self_attn
|
46 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
47 |
+
- filter: mlp
|
48 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
49 |
+
- value: 0.5 # fallback for rest of tensors
|
50 |
+
dtype: bfloat16
|
51 |
+
|
52 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TroyDoesAI/BlackSheep-MermaidMistral-22B",
|
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": 6144,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 16384,
|
14 |
+
"max_position_embeddings": 131072,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 48,
|
17 |
+
"num_hidden_layers": 56,
|
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": "4.40.2",
|
25 |
+
"use_cache": false,
|
26 |
+
"vocab_size": 32768
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: TroyDoesAI/BlackSheep-Mistral-22B
|
4 |
+
layer_range: [0, 56]
|
5 |
+
- model: TroyDoesAI/Mermaid-22B
|
6 |
+
layer_range: [0, 56]
|
7 |
+
# or, the equivalent models: syntax:
|
8 |
+
# models:
|
9 |
+
# - model: psmathur/orca_mini_v3_13b
|
10 |
+
# - model: garage-bAInd/Platypus2-13B
|
11 |
+
merge_method: slerp
|
12 |
+
base_model: TroyDoesAI/BlackSheep-Mistral-22B
|
13 |
+
parameters:
|
14 |
+
t:
|
15 |
+
- filter: self_attn
|
16 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
17 |
+
- filter: mlp
|
18 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
19 |
+
- value: 0.5 # fallback for rest of tensors
|
20 |
+
dtype: bfloat16
|
model-00001-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b8f687ca5ef7c36f686477087e6692fd1945fc20773c7f8392d3b86a895cbb
|
3 |
+
size 4907476544
|
model-00002-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbe66a960bf9d413eea901fb810b0865c34b249849fb2a3f5ee2182c66d5dfee
|
3 |
+
size 4882323752
|
model-00003-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa6caf9c51716c5bce763aa1a51d0058358a17aaefbbbfda0d6c6a3db2110a96
|
3 |
+
size 4970416760
|
model-00004-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dace2a6f415db42a61e03bb235c812fb05f946a8afca65ec5e563ae631f9ea48
|
3 |
+
size 4970416752
|
model-00005-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d3f815d80aea98881af5f26e65c0a5ba4da7a189291a449ecae908f9ccac1b
|
3 |
+
size 4882323752
|
model-00006-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b6e0b661536a242f82fbb54fb76bd2983968547838ed2111cd2bc49c8359d13
|
3 |
+
size 4970416760
|
model-00007-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3beb1182a7e83def557258808eb20e4e8e6a2f56ef6f96d0572d7b01d05aff80
|
3 |
+
size 4970416760
|
model-00008-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:603c0d81be79acaeaf55cb9ea3af33c1f5e593a9f2f01322cfb14d656d4857da
|
3 |
+
size 4882323736
|
model-00009-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8c025fd628c4b71119f841ac6728a77ee3f7e103d24cff7d1110b1123c813fa
|
3 |
+
size 4970416736
|
model-00010-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d2fcaad4ba0f45188956538eb54c330c36ebea61901ad3a0828689ebf7e7b3
|
3 |
+
size 88093024
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 44494565376}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.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": "</s>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
3 |
+
size 587583
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|