LoneStriker
commited on
Commit
•
0bea985
1
Parent(s):
2e35d18
Upload folder using huggingface_hub
Browse files- README.md +48 -0
- config.json +29 -0
- mergekit_config.yml +16 -0
- model.safetensors.index.json +1 -0
- output-00001-of-00004.safetensors +3 -0
- output-00002-of-00004.safetensors +3 -0
- output-00003-of-00004.safetensors +3 -0
- output-00004-of-00004.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
tags:
|
4 |
+
- mergekit
|
5 |
+
- merge
|
6 |
+
|
7 |
+
---
|
8 |
+
# Steelskull/Etheria-55b-v0.1
|
9 |
+
|
10 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/RAhrbktyyVQxOR1np-9L2.png)
|
11 |
+
|
12 |
+
## Merge Details
|
13 |
+
|
14 |
+
An attempt to make a functional goliath style merge to create a [Etheria] 55b-200k with two yi-34b-200k models.
|
15 |
+
|
16 |
+
due to the merge it 'theoretically' should have a context of 200k but I recommend starting at 32k and moveing up,
|
17 |
+
as it is unknown (at this time) what the merge has done to the context length.
|
18 |
+
|
19 |
+
This is a merge of both VerA and VerB of Etheria-55b (There numbers were surprisingly good), I then created a sacrificial 55B out of the most performant yi-34b-200k Model
|
20 |
+
and performed a Dare_ties merge and equalize the model into its current state.
|
21 |
+
|
22 |
+
### Merge Method
|
23 |
+
|
24 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using Merged-Etheria-55b as a base.
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
|
32 |
+
base_model: Merged-Etheria-55b
|
33 |
+
models:
|
34 |
+
- model: Sacr-Etheria-55b
|
35 |
+
parameters:
|
36 |
+
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
|
37 |
+
density: 0.61
|
38 |
+
- model: Merged-Etheria-55b
|
39 |
+
parameters:
|
40 |
+
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
|
41 |
+
density: 0.61
|
42 |
+
merge_method: dare_ties
|
43 |
+
tokenizer_source: union
|
44 |
+
parameters:
|
45 |
+
int8_mask: true
|
46 |
+
dtype: bfloat16
|
47 |
+
|
48 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/workspace/merge2",
|
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": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 200000,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_hidden_layers": 98,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 5000000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.37.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64002
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: /workspace/merge2
|
3 |
+
models:
|
4 |
+
- model: /workspace/merge
|
5 |
+
parameters:
|
6 |
+
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
|
7 |
+
density: 0.61
|
8 |
+
- model: /workspace/merge2
|
9 |
+
parameters:
|
10 |
+
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
|
11 |
+
density: 0.61
|
12 |
+
merge_method: dare_ties
|
13 |
+
tokenizer_source: union
|
14 |
+
parameters:
|
15 |
+
int8_mask: true
|
16 |
+
dtype: bfloat16
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.embed_tokens.weight": "model-00002-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.63.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.62.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.67.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.74.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.70.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.89.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.88.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.87.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.84.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.83.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.82.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.69.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.97.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.96.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.93.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.92.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.91.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.90.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.86.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.78.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.77.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.76.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.75.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "lm_head.weight": "model-00011-of-00012.safetensors", "model.norm.weight": "model-00011-of-00012.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.95.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.94.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.81.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.80.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.79.input_layernorm.weight": "model-00012-of-00012.safetensors"}}
|
output-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6431b0fa9b1db8e956632fc141c89901ff4bd22a5db9f71d580cb6931dd855f5
|
3 |
+
size 8589998336
|
output-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce9ab1a9c9e8cc6065ae0717afd6a2b5ce6fbddccdeb7bfbf45ab3ac2ab64b7f
|
3 |
+
size 8508676712
|
output-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30b1a37f57a35c3c3c8bee5ed2d617ba603b038402825132e2a7c6480cbc1432
|
3 |
+
size 8574782232
|
output-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:703bad5fd5904211df68eeac62bc8ef19951b154956eb0aa97293e47e3dfb143
|
3 |
+
size 7410565304
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": false
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"64000": {
|
30 |
+
"content": "<s>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"64001": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"bos_token": "<|startoftext|>",
|
47 |
+
"clean_up_tokenization_spaces": false,
|
48 |
+
"eos_token": "<|endoftext|>",
|
49 |
+
"legacy": false,
|
50 |
+
"model_max_length": 200000,
|
51 |
+
"pad_token": "<unk>",
|
52 |
+
"padding_side": "right",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"spaces_between_special_tokens": false,
|
55 |
+
"tokenizer_class": "LlamaTokenizer",
|
56 |
+
"truncation_side": "right",
|
57 |
+
"unk_token": "<unk>",
|
58 |
+
"use_default_system_prompt": false
|
59 |
+
}
|