Upload folder using huggingface_hub
Browse files- README.md +43 -0
- config.json +29 -0
- generation_config.json +11 -0
- mergekit_config.yml +13 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# Faro-34B-Slerp
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the SLERP merge method.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* /cephfs/panwenbo/work/models/Faro-34B-DPO
|
22 |
+
* /cephfs/panwenbo/work/models/Faro-34B
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
models:
|
30 |
+
- model: /cephfs/panwenbo/work/models/Faro-34B-DPO
|
31 |
+
- model: /cephfs/panwenbo/work/models/Faro-34B
|
32 |
+
merge_method: slerp
|
33 |
+
base_model: /cephfs/panwenbo/work/models/Faro-34B
|
34 |
+
parameters:
|
35 |
+
t:
|
36 |
+
- filter: self_attn
|
37 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
38 |
+
- filter: mlp
|
39 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
40 |
+
- value: 0.5 # fallback for rest of tensors
|
41 |
+
dtype: bfloat16
|
42 |
+
|
43 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/cephfs/panwenbo/work/models/Faro-34B",
|
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": 32768,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_hidden_layers": 60,
|
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": 10000000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.39.3",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 64000
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
2,
|
7 |
+
7
|
8 |
+
],
|
9 |
+
"pad_token_id": 0,
|
10 |
+
"transformers_version": "4.40.0.dev0"
|
11 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: /cephfs/panwenbo/work/models/Faro-34B-DPO
|
3 |
+
- model: /cephfs/panwenbo/work/models/Faro-34B
|
4 |
+
merge_method: slerp
|
5 |
+
base_model: /cephfs/panwenbo/work/models/Faro-34B
|
6 |
+
parameters:
|
7 |
+
t:
|
8 |
+
- filter: self_attn
|
9 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
10 |
+
- filter: mlp
|
11 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
12 |
+
- value: 0.5 # fallback for rest of tensors
|
13 |
+
dtype: bfloat16
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c41007df73ab844742a70e26ca3ddd54608a1b3e972630c02763cdfdf944699a
|
3 |
+
size 9784471960
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eeb53c74d8a4bd250581c54e9d281a45972cb2a33cf679b653d3f9810970233
|
3 |
+
size 9806549784
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94d7705d5100351a7870b315e6b2725a4f6cbab196600660c1f36363d0c4bdb
|
3 |
+
size 9982711400
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:505a3a951f7981ea4bfd5a0b83ceb5c2c9fbfdccdb5ce65e244d04b63a7d4d03
|
3 |
+
size 9806520896
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a422cd8f5989774b33cdf892438fcd42f98c918cba5a6204b798536299d163
|
3 |
+
size 9747829904
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2434bbca613bd2ba34bc5f1c2a9f9fdac3a7fc4bcf362904e9e3bd93e4f3f12
|
3 |
+
size 9747829904
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f17e7f6cfa793ff483c8d50a7a2ff38bf087baaddcdf91ac231d26d60651b32
|
3 |
+
size 9901984048
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 68777834496}, "weight_map": {"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|startoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|endoftext|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<|startoftext|>",
|
32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "<|endoftext|>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 200000,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false,
|
43 |
+
"use_fast": true
|
44 |
+
}
|