Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +59 -0
- config.json +27 -0
- mergekit_config.yml +29 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
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
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- inflatebot/MN-12B-Mag-Mell-R1
|
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 |
+
* [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
dtype: bfloat16
|
30 |
+
merge_method: passthrough
|
31 |
+
slices:
|
32 |
+
- sources:
|
33 |
+
- layer_range: [0, 30]
|
34 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
35 |
+
- sources:
|
36 |
+
- layer_range: [16, 32]
|
37 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
38 |
+
parameters:
|
39 |
+
scale:
|
40 |
+
- filter: o_proj
|
41 |
+
value: 0.0
|
42 |
+
- filter: down_proj
|
43 |
+
value: 0.0
|
44 |
+
- value: 1.0
|
45 |
+
- sources:
|
46 |
+
- layer_range: [16, 32]
|
47 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
48 |
+
parameters:
|
49 |
+
scale:
|
50 |
+
- filter: o_proj
|
51 |
+
value: 0.0
|
52 |
+
- filter: down_proj
|
53 |
+
value: 0.0
|
54 |
+
- value: 1.0
|
55 |
+
- sources:
|
56 |
+
- layer_range: [32, 40]
|
57 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
58 |
+
|
59 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "inflatebot/MN-12B-Mag-Mell-R1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 15,
|
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": 70,
|
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": "4.46.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 131072
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dtype: bfloat16
|
2 |
+
merge_method: passthrough
|
3 |
+
slices:
|
4 |
+
- sources:
|
5 |
+
- layer_range: [0, 30]
|
6 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
7 |
+
- sources:
|
8 |
+
- layer_range: [16, 32]
|
9 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
10 |
+
parameters:
|
11 |
+
scale:
|
12 |
+
- filter: o_proj
|
13 |
+
value: 0.0
|
14 |
+
- filter: down_proj
|
15 |
+
value: 0.0
|
16 |
+
- value: 1.0
|
17 |
+
- sources:
|
18 |
+
- layer_range: [16, 32]
|
19 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
20 |
+
parameters:
|
21 |
+
scale:
|
22 |
+
- filter: o_proj
|
23 |
+
value: 0.0
|
24 |
+
- filter: down_proj
|
25 |
+
value: 0.0
|
26 |
+
- value: 1.0
|
27 |
+
- sources:
|
28 |
+
- layer_range: [32, 40]
|
29 |
+
model: inflatebot/MN-12B-Mag-Mell-R1
|
model-00001-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7898c09925ad6c97cb7b254ee689e69ab84043c418ea66a8bef131fb4d68200
|
3 |
+
size 4865489336
|
model-00002-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6042dba5109e16ef693ec30c10b7b86496f0db58a4e9dce49e87b9c84c9b5cb2
|
3 |
+
size 4991394112
|
model-00003-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71595abb47e05037f7f3dde5bbddcdd8c868d229026c263d6d119bba342a3976
|
3 |
+
size 4865607480
|
model-00004-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1a7e1d257a810ab35b6336df5951e62453f04193c7b524f4096243ba7f62586
|
3 |
+
size 4907529456
|
model-00005-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c07b6c38317e7b2e4fb1cf7fcdc25f7e2f93539ae1d236dbd040b2ea9ae981a3
|
3 |
+
size 4907529456
|
model-00006-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b6503b0fb8832c07321f75d0f7c5597b776a3edb1961b18ea022d8fc05c400e
|
3 |
+
size 4907529456
|
model-00007-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b7b414759876b5b2758948f56dd8c0d10c1b0141c351c2dd9cee20dbcb32225
|
3 |
+
size 4865586776
|
model-00008-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acf5a3f4b536f446121527cf938c1ad8fa181966ac6d58ce410d5f59300a56df
|
3 |
+
size 4907529424
|
model-00009-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98cc0bad23078abe648c432740bf07e70574a75135fb9c1ca269fb4c8e6ab7a
|
3 |
+
size 1635843112
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 40853964800}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.53.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.56.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.59.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.64.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4c8fcd33487a449c07f423d47adb035bba8347ccf13eb074b4d1fef8acf919
|
3 |
+
size 17078288
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|