初始化项目，由ModelHub XC社区提供模型
Model: top-50000/model-agent-test-4 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
48
README.md
Normal file
48
README.md
Normal file
@@ -0,0 +1,48 @@
|
||||
---
|
||||
base_model:
|
||||
- gurand/Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV
|
||||
- Qwen/Qwen3-32B
|
||||
- gurand/Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# testmodel-3
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [gurand/Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV](https://huggingface.co/gurand/Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV)
|
||||
* [gurand/Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR](https://huggingface.co/gurand/Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
base_model: Qwen/Qwen3-32B
|
||||
dtype: bfloat16
|
||||
merge_method: dare_ties
|
||||
parameters:
|
||||
int8_mask: true
|
||||
normalize: true
|
||||
models:
|
||||
- model: gurand/Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.3
|
||||
- model: gurand/Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.7
|
||||
|
||||
```
|
||||
96
config.json
Normal file
96
config.json
Normal file
@@ -0,0 +1,96 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 25600,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 64,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
15
mergekit_config.yml
Normal file
15
mergekit_config.yml
Normal file
@@ -0,0 +1,15 @@
|
||||
base_model: Qwen/Qwen3-32B
|
||||
dtype: bfloat16
|
||||
merge_method: dare_ties
|
||||
parameters:
|
||||
int8_mask: true
|
||||
normalize: true
|
||||
models:
|
||||
- model: gurand/Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.3
|
||||
- model: gurand/Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.7
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00014.safetensors
Normal file
3
model-00001-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd3ee725368edcb583874649e46394f401968421cb13d7621e0fb5eb0dd99afe
|
||||
size 4967673312
|
||||
3
model-00002-of-00014.safetensors
Normal file
3
model-00002-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ad35b8d4296fd7361f97d62abedb132460009a0f75daf7d4d58a2f92fb08474
|
||||
size 4970372168
|
||||
3
model-00003-of-00014.safetensors
Normal file
3
model-00003-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:daecda454b981c1499819624eeb8f9cb95a09d5f7b4c1072de4b352d545bb9d4
|
||||
size 4875989744
|
||||
3
model-00004-of-00014.safetensors
Normal file
3
model-00004-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:68f981111f261ec155c7d52eec3acf873ef409719d71da6fbb60db62568d6686
|
||||
size 4875989736
|
||||
3
model-00005-of-00014.safetensors
Normal file
3
model-00005-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33ee9b1241186d07a40c506803835be771a48326867081a2b12ace9cfbc9e755
|
||||
size 4875989744
|
||||
3
model-00006-of-00014.safetensors
Normal file
3
model-00006-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:def3568f563b1c91a60a5f0b3f8477041116c36c3cd223df4e4a453642a44073
|
||||
size 4875989736
|
||||
3
model-00007-of-00014.safetensors
Normal file
3
model-00007-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a872b33711682ae29e8297a0a4bab36010abf84e725458a84ef5bb0675305eb
|
||||
size 4875989744
|
||||
3
model-00008-of-00014.safetensors
Normal file
3
model-00008-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbdb2b0a0aef53be5a76673a05f473e2072377082f3f83cc4ba6dad302823d7d
|
||||
size 4875989736
|
||||
3
model-00009-of-00014.safetensors
Normal file
3
model-00009-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a4d5f34ec19a063739dcf0fe1c29b4da9faa021e77427e50d07f578e3dda66c
|
||||
size 4875989744
|
||||
3
model-00010-of-00014.safetensors
Normal file
3
model-00010-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:689253951c89c6771e246fa7c131f6e6a438d16e1c7f9003eaca3b07dd670507
|
||||
size 4875989736
|
||||
3
model-00011-of-00014.safetensors
Normal file
3
model-00011-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7d6a435abacc287ae499a2027649476cf4c66a3b5a3ec1a63dc89b23aa010cd
|
||||
size 4875989744
|
||||
3
model-00012-of-00014.safetensors
Normal file
3
model-00012-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:07fe78125051984a8dc81d3e8a1bf4e590614b7fea77582d005a9fbfc8a80d4f
|
||||
size 4875989736
|
||||
3
model-00013-of-00014.safetensors
Normal file
3
model-00013-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edff2e6ee73e9eac7c9d4bd640cac163d84aa96b2356538506de2ebda22d2ba6
|
||||
size 4875989736
|
||||
3
model-00014-of-00014.safetensors
Normal file
3
model-00014-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24f9bd49ce9cc9181ba5613b06f41b96a34ea58583efabd73b6b75a9ab2a7318
|
||||
size 1950395864
|
||||
715
model.safetensors.index.json
Normal file
715
model.safetensors.index.json
Normal file
@@ -0,0 +1,715 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 65524246528,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00014.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.norm.weight": "model-00014-of-00014.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user