初始化项目，由ModelHub XC社区提供模型
Model: IRIS-77/Dataset-HTL635-No 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
|
||||
42
README.md
Normal file
42
README.md
Normal file
@@ -0,0 +1,42 @@
|
||||
---
|
||||
base_model:
|
||||
- Nanbeige/Nanbeige4.1-3B
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# Nanbeige-5B-Frankenmerge
|
||||
|
||||
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 Passthrough merge method using [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [12, 28]
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [16, 32]
|
||||
merge_method: passthrough
|
||||
base_model: Nanbeige/Nanbeige4.1-3B
|
||||
dtype: float16
|
||||
```
|
||||
9
added_tokens.json
Normal file
9
added_tokens.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"</think>": 166104,
|
||||
"</tool_call>": 166106,
|
||||
"<think>": 166103,
|
||||
"<tool_call>": 166105,
|
||||
"<|endoftext|>": 166102,
|
||||
"<|im_end|>": 166101,
|
||||
"<|im_start|>": 166100
|
||||
}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 166100,
|
||||
"dtype": "float16",
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 166101,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10496,
|
||||
"max_position_embeddings": 262144,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 20,
|
||||
"num_hidden_layers": 56,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"resid_pdrop": 0.0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 70000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 166144
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 166100,
|
||||
"eos_token_id": 166101,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
13
mergekit_config.yml
Normal file
13
mergekit_config.yml
Normal file
@@ -0,0 +1,13 @@
|
||||
slices:
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [0, 24]
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [12, 28]
|
||||
- sources:
|
||||
- model: Nanbeige/Nanbeige4.1-3B
|
||||
layer_range: [16, 32]
|
||||
merge_method: passthrough
|
||||
base_model: Nanbeige/Nanbeige4.1-3B
|
||||
dtype: float16
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3e8a0099a145fe19e6b8d7609552777efe4023516178fc3b844861509245bae5
|
||||
size 4967814712
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f198eb056976337aa5c9cd9bbaea5640f659afe4f2a10a34de419e0a39ef39ef
|
||||
size 4987588376
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edd69c4094d81e2af8e70e13023a090015c7ad6a0aa8810c369fe93f9077208c
|
||||
size 2536395376
|
||||
515
model.safetensors.index.json
Normal file
515
model.safetensors.index.json
Normal file
@@ -0,0 +1,515 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 12491740160,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d8f0326910136aca20831249220b38ce5299527647bc8c6b65404485c479740
|
||||
size 18451122
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
|
||||
size 2782298
|
||||
103
tokenizer_config.json
Normal file
103
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user