Upload folder using huggingface_hub
Browse files- README.md +53 -0
- added_tokens.json +6 -0
- config.json +29 -0
- mergekit_config.yml +18 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +29 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +83 -0
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- codellama/CodeLlama-7b-Python-hf
|
4 |
+
- codellama/CodeLlama-7b-Instruct-hf
|
5 |
+
- Phind/Phind-CodeLlama-34B-v2
|
6 |
+
- Phind/Phind-CodeLlama-34B-Python-v1
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- mergekit
|
10 |
+
- merge
|
11 |
+
|
12 |
+
---
|
13 |
+
# merge
|
14 |
+
|
15 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
16 |
+
|
17 |
+
## Merge Details
|
18 |
+
### Merge Method
|
19 |
+
|
20 |
+
This model was merged using the passthrough merge method.
|
21 |
+
|
22 |
+
### Models Merged
|
23 |
+
|
24 |
+
The following models were included in the merge:
|
25 |
+
* [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
|
26 |
+
* [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf)
|
27 |
+
* [Phind/Phind-CodeLlama-34B-v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2)
|
28 |
+
* [Phind/Phind-CodeLlama-34B-Python-v1](https://huggingface.co/Phind/Phind-CodeLlama-34B-Python-v1)
|
29 |
+
|
30 |
+
### Configuration
|
31 |
+
|
32 |
+
The following YAML configuration was used to produce this model:
|
33 |
+
|
34 |
+
```yaml
|
35 |
+
slices:
|
36 |
+
- sources:
|
37 |
+
- layer_range: [0, 15]
|
38 |
+
model: codellama/CodeLlama-7b-Instruct-hf
|
39 |
+
- sources:
|
40 |
+
- layer_range: [0, 15]
|
41 |
+
model: Phind/Phind-CodeLlama-34B-Python-v1
|
42 |
+
- sources:
|
43 |
+
- layer_range: [8, 26]
|
44 |
+
model: codellama/CodeLlama-7b-Python-hf
|
45 |
+
- sources:
|
46 |
+
- layer_range: [16, 33]
|
47 |
+
model: Phind/Phind-CodeLlama-34B-v2
|
48 |
+
- sources:
|
49 |
+
- layer_range: [14, 32]
|
50 |
+
model: codellama/CodeLlama-7b-Instruct-hf
|
51 |
+
merge_method: passthrough
|
52 |
+
dtype: float16
|
53 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"β<EOT>": 32003,
|
3 |
+
"β<MID>": 32001,
|
4 |
+
"β<PRE>": 32000,
|
5 |
+
"β<SUF>": 32002
|
6 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "codellama/CodeLlama-7b-Python-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 83,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 1000000,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.44.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- layer_range: [0, 15]
|
4 |
+
model: codellama/CodeLlama-7b-Instruct-hf
|
5 |
+
- sources:
|
6 |
+
- layer_range: [0, 15]
|
7 |
+
model: Phind/Phind-CodeLlama-34B-Python-v1
|
8 |
+
- sources:
|
9 |
+
- layer_range: [8, 26]
|
10 |
+
model: codellama/CodeLlama-7b-Python-hf
|
11 |
+
- sources:
|
12 |
+
- layer_range: [16, 33]
|
13 |
+
model: Phind/Phind-CodeLlama-34B-v2
|
14 |
+
- sources:
|
15 |
+
- layer_range: [14, 32]
|
16 |
+
model: codellama/CodeLlama-7b-Instruct-hf
|
17 |
+
merge_method: passthrough
|
18 |
+
dtype: float16
|
model-00001-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d17612e394cbd91a1eadd2b47eeaee490f9925e7f2989ea30a1ed72fb094a34c
|
3 |
+
size 4733670432
|
model-00002-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d9f39b78187b2f8687d8646a9785e9a8d9a2505ecec44a4115302025c1198c8
|
3 |
+
size 4928444864
|
model-00003-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a67bb8a321aebce7047cdd5e5e36b7ecdfd8dc5d8c92cd8cf6b77b95471ecd8
|
3 |
+
size 4748098200
|
model-00004-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5608600038af9b3acb3433de3429ee6325cc5c3a3b8d796c6532fd549ef59013
|
3 |
+
size 4699898120
|
model-00005-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:812f06a52900a371f15332610ccab360b54ebe2d6fb9ae7968a56e485e6f9fbb
|
3 |
+
size 4928444864
|
model-00006-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eae1b6e9ce2bca73c871dfa4bd1270cbf60cf8485fbe8cdddb40a0830442412b
|
3 |
+
size 4970404792
|
model-00007-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a66b7eb16cf657aa5cab54c4e7fb714563de28dbfabbfd6ab141cf4b69049e9
|
3 |
+
size 4962032504
|
model-00008-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:344c6f337d68ab4fed6c5c922cdabb3446172163cd5947c8bbc99b83e32a3849
|
3 |
+
size 4928444864
|
model-00009-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba9773d0dd0201099b9c611d10a62fbdc5051b5123264b9170c298dada5113b
|
3 |
+
size 4779571672
|
model-00010-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ba4ffba127ddb2f5836e7cff6e346584e814329e429ea89f7fc71f464f2693
|
3 |
+
size 4890686568
|
model-00011-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:667fd9692a1932780ec474250a3da9f3d83e3ef9f11fccbf0394be99f27061ab
|
3 |
+
size 4685157480
|
model-00012-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b44658942bfd30fd4721ceca379d0df93a14ef9daf07a1133414f5b4cb3cb209
|
3 |
+
size 4691473608
|
model-00013-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd0157adf9775cee5f7e036c7cf9272405d44afe567fb6e036a917634b6a6d75
|
3 |
+
size 4867634968
|
model-00014-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aa440544df0a0853adb538a47694610bebde9a9feee0b4c81ed747ae881eb02
|
3 |
+
size 2646683720
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 65460559872}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.68.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.70.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.74.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.76.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.79.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.61.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.62.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.63.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.64.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"unk_token": {
|
23 |
+
"content": "<unk>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "β<PRE>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "β<MID>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "β<SUF>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "β<EOT>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"β<PRE>",
|
64 |
+
"β<MID>",
|
65 |
+
"β<SUF>",
|
66 |
+
"β<EOT>"
|
67 |
+
],
|
68 |
+
"bos_token": "<s>",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"eot_token": "β<EOT>",
|
72 |
+
"fill_token": "<FILL_ME>",
|
73 |
+
"legacy": null,
|
74 |
+
"middle_token": "β<MID>",
|
75 |
+
"model_max_length": 1000000000000000019884624838656,
|
76 |
+
"pad_token": null,
|
77 |
+
"prefix_token": "β<PRE>",
|
78 |
+
"sp_model_kwargs": {},
|
79 |
+
"suffix_token": "β<SUF>",
|
80 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
81 |
+
"unk_token": "<unk>",
|
82 |
+
"use_default_system_prompt": false
|
83 |
+
}
|