maywell/Synatra_TbST11B_EP01
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: maywell/Synatra_TbST11B_EP01
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 20:20:14 +08:00
commit 9785215175
14 changed files with 639 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
.gitattributes vendored Normal file
View File

@@ -0,0 +1,53 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
tokenizer.model filter=lfs diff=lfs merge=lfs -text
pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text

41
README.md Normal file
View File

@@ -0,0 +1,41 @@
---
language:
- ko
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-4.0
---
# **Synatra_TbST11B_EP01**
Made by StableFluffy
**Contact (Do not Contact for personal things.)**
Discord : is.maywell
Telegram : AlzarTakkarsen
## License
This model is strictly [*non-commercial*](https://creativecommons.org/licenses/by-nc/4.0/) (**cc-by-nc-4.0**) use only which takes priority over the **MISTRAL APACHE 2.0**.
The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included **cc-by-nc-4.0** license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
The licence can be changed after new model released. If you are to use this model for commercial purpose, Contact me.
## Model Details
**Base Model**
[mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
**Trained On**
A100 80GB * 4
# **Model Benchmark**
X
```
> Readme format: [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
---

25
config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "./synatra_11bv4",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0.dev0",
"use_cache": false,
"vocab_size": 32000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.0.dev0"
}

1
latest Normal file
View File

@@ -0,0 +1 @@
global_step160

3
pytorch_model-00001-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4e5c544185a9db7effa474c9e7690edaa138f8e21caa0a261372c5842608c26
size 9943028044

3
pytorch_model-00002-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4e9e1024a358fc5e5452a2eb97cbd8f9995db750a6eba935b1201c576d63c457
size 9999668701

3
pytorch_model-00003-of-00003.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c4afeea1837c5b0f513c2f42d10c772ea9caaa8cdd6434ba39ece34278221b9
size 1520501283

442
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,442 @@
{
"metadata": {
"total_size": 21463048192
},
"weight_map": {
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.40.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.46.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
}
}

10
special_tokens_map.json Normal file
View File

@@ -0,0 +1,10 @@
{
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "<unk>"
}

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

45
tokenizer_config.json Normal file
View File

@@ -0,0 +1,45 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}