Upload folder using huggingface_hub
Browse files- README.md +60 -0
- added_tokens.json +13 -0
- config.json +36 -0
- mergekit_config.yml +26 -0
- model-00001-of-00012.safetensors +3 -0
- model-00002-of-00012.safetensors +3 -0
- model-00003-of-00012.safetensors +3 -0
- model-00004-of-00012.safetensors +3 -0
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.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 +131 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
|
4 |
+
- jpacifico/Chocolatine-3B-Instruct-DPO-Revised
|
5 |
+
- Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
|
11 |
+
---
|
12 |
+
# merge
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
## Merge Details
|
17 |
+
### Merge Method
|
18 |
+
|
19 |
+
This model was merged using the SLERP merge method.
|
20 |
+
|
21 |
+
### Models Merged
|
22 |
+
|
23 |
+
The following models were included in the merge:
|
24 |
+
* [Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5](https://huggingface.co/Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5)
|
25 |
+
* [jpacifico/Chocolatine-3B-Instruct-DPO-Revised](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-Revised)
|
26 |
+
* [Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL](https://huggingface.co/Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL)
|
27 |
+
|
28 |
+
### Configuration
|
29 |
+
|
30 |
+
The following YAML configuration was used to produce this model:
|
31 |
+
|
32 |
+
```yaml
|
33 |
+
|
34 |
+
slices:
|
35 |
+
- sources:
|
36 |
+
- model: Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL
|
37 |
+
layer_range: [0, 32]
|
38 |
+
- sources:
|
39 |
+
- model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
|
40 |
+
layer_range: [0, 32]
|
41 |
+
- sources:
|
42 |
+
- model: Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
|
43 |
+
layer_range: [0, 32]
|
44 |
+
base_model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
|
45 |
+
merge_method: slerp
|
46 |
+
parameters:
|
47 |
+
t:
|
48 |
+
- filter: self_attn
|
49 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
50 |
+
- filter: mlp
|
51 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
52 |
+
- value: 0.5
|
53 |
+
normalize: false
|
54 |
+
int8_mask: true
|
55 |
+
density: 0.7
|
56 |
+
lambda: 1.1
|
57 |
+
epsilon: 0.2
|
58 |
+
dtype: bfloat16
|
59 |
+
|
60 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "jpacifico/Chocolatine-3B-Instruct-DPO-Revised",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
+
"eos_token_id": 32000,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 3072,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 4096,
|
20 |
+
"model_type": "phi3",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 96,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"original_max_position_embeddings": 4096,
|
25 |
+
"pad_token_id": 32000,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": null,
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 2047,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.45.0.dev0",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL
|
5 |
+
layer_range: [0, 32]
|
6 |
+
- sources:
|
7 |
+
- model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
|
8 |
+
layer_range: [0, 32]
|
9 |
+
- sources:
|
10 |
+
- model: Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
|
11 |
+
layer_range: [0, 32]
|
12 |
+
base_model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
|
13 |
+
merge_method: slerp
|
14 |
+
parameters:
|
15 |
+
t:
|
16 |
+
- filter: self_attn
|
17 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
18 |
+
- filter: mlp
|
19 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
20 |
+
- value: 0.5
|
21 |
+
normalize: false
|
22 |
+
int8_mask: true
|
23 |
+
density: 0.7
|
24 |
+
lambda: 1.1
|
25 |
+
epsilon: 0.2
|
26 |
+
dtype: bfloat16
|
model-00001-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9309108ab3e05c118d08d24aa46e8efdb9c40d5e3fe08e215fa060fc9a0b4608
|
3 |
+
size 1904049128
|
model-00002-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ab832ed94b162d0a99f0a81062d5a722275540a30901e796fd67eaaa1445e52
|
3 |
+
size 1988216904
|
model-00003-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c3f7adf3e2f91fa35aae3cfea666935f205540da0a97face558f10bc1f0db11
|
3 |
+
size 1988216904
|
model-00004-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75704b3e974cf2c5c57d95ff753303ffa72583fead5ae0b06f6c12af35c09324
|
3 |
+
size 1988216904
|
model-00005-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939c189b5ef30e7799aec8595a30ff8258e7d20c6c8d5aae43ae15e7cec1070f
|
3 |
+
size 1981906672
|
model-00006-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3103ade5507a36e27ec07b9d66c9a50adf245a5ea8c364b3a208394e8ddab19
|
3 |
+
size 1981925432
|
model-00007-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4831e950ebf8759c839628af07eae88c216c3f68dad437fc59b762a55e2c0bd8
|
3 |
+
size 1981925432
|
model-00008-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb8fcaef4dbf5d0d565f4c15a1037055d0fc2f44daac2b259b51605d31dce63b
|
3 |
+
size 1981925200
|
model-00009-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b63aba544551cee0ea5a802929c109bb7e6aab5ad116740ac6dfed1d8c9e29f
|
3 |
+
size 1937866440
|
model-00010-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a680912fa9811fac26ae0130332a91cccd9b3f4bb286dfb400ee3d54494d757
|
3 |
+
size 1937885232
|
model-00011-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f0c21cbc8309dd41413e81ab6d019cfa365cb5b19eb172aa5723b63b1a8d3c
|
3 |
+
size 1937885232
|
model-00012-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22488ebdc706adc142d74a3c185b326f1f78d18c364050f10d490c09521e4ac4
|
3 |
+
size 528508408
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 22138460160}, "weight_map": {"lm_head.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.64.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.64.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.64.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.32.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.65.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.65.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.33.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.65.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.33.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00012.safetensors", "model.layers.74.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.74.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.42.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.74.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.42.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.75.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.75.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.43.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.75.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.43.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.76.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.76.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.44.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.76.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.44.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00012.safetensors", "model.layers.77.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.77.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.45.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.77.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.45.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.78.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.78.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.46.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.78.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.46.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.79.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.79.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.47.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.79.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.47.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00012.safetensors", "model.layers.80.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.80.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.48.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.80.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.48.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.81.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.81.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.49.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.81.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.49.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.82.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.82.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.50.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.82.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.50.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00004-of-00012.safetensors", "model.layers.83.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.83.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.51.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.83.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.51.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.66.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.66.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.66.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.84.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.84.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.52.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.84.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.52.self_attn.qkv_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.85.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.85.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.85.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.53.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.86.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.86.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.54.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.86.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.54.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.87.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.87.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.55.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.87.self_attn.qkv_proj.weight": "model-00006-of-00012.safetensors", "model.layers.55.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.88.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.88.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.88.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.89.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.89.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.89.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00007-of-00012.safetensors", "model.layers.90.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.90.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.90.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.58.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.91.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.91.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.59.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.91.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.59.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.92.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.92.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.92.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00008-of-00012.safetensors", "model.layers.93.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.93.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.93.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.61.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.94.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.62.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.94.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.62.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.94.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.62.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.30.self_attn.qkv_proj.weight": "model-00009-of-00012.safetensors", "model.layers.95.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.63.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.95.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.63.mlp.gate_up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.95.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.31.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.68.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.69.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.69.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.69.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00010-of-00012.safetensors", "model.layers.70.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.70.mlp.gate_up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.38.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.70.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.71.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.72.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00011-of-00012.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.73.mlp.gate_up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.mlp.gate_up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.73.self_attn.qkv_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.self_attn.qkv_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
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": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"legacy": false,
|
124 |
+
"model_max_length": 4096,
|
125 |
+
"pad_token": "<|endoftext|>",
|
126 |
+
"padding_side": "left",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"tokenizer_class": "LlamaTokenizer",
|
129 |
+
"unk_token": "<unk>",
|
130 |
+
"use_default_system_prompt": false
|
131 |
+
}
|