初始化项目，由ModelHub XC社区提供模型
Model: Vezora/Mistral-14b-Merge-Base Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
37
README.md
Normal file
37
README.md
Normal file
@@ -0,0 +1,37 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
Contributors: Nicolas Mejia Petit
|
||||
|
||||
|
||||
|
||||
# Mistral 14b: A New Base Model
|
||||
|
||||
The objective of this model is to serve as a fully open source new base model with 14.3 billion parameters. It has been enhanced with a LoRa adapter attached to all 62 layers of the merged model. The model is capable of generating outputs and responding accurately to inputs. However, it tends to over-respond with unasked questions when asked to process more than 512 tokens, which is its training limit using QLoRa.
|
||||
|
||||
With full fine-tuning, this model has the potential to deliver excellent performance.
|
||||
|
||||
Qlora adapter was trained on a modified dataset of airoboros-m-7b-3.1.2, using SFT. In the Alpaca Format.
|
||||
|
||||
## Model Creation
|
||||
|
||||
The model was created by merging two models: Dolphin and Zephyr, along with Meta-math7b and Speechless code, to form a single model. The layers of these two models were stacked on top of each other to create this model.
|
||||
|
||||
Initially, the output from the model was pure jargon. To rectify this, a LoRa adapter was trained and merged across all layers.
|
||||
|
||||
## Useful Resources
|
||||
|
||||
- LoRa Adapter Merging (https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930)
|
||||
- Model Merging (MergeKit) (https://github.com/cg123/mergekit)
|
||||
|
||||
## Source Models
|
||||
|
||||
- Dolphin2.1-mistral-7b by Eric Hartford (https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
|
||||
- Zephyr-7b-beta by HuggingFace (https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
|
||||
- MetaMath-Mistral-7B by meta-math (https://huggingface.co/meta-math/MetaMath-Mistral-7B)
|
||||
- Speechless-code-mistral-7b-v1.0 (https://huggingface.co/uukuguy/speechless-code-mistral-7b-v1.0)
|
||||
- Airoboros-m-7b-3.1.2 (https://huggingface.co/jondurbin/airoboros-m-7b-3.1.2)
|
||||
|
||||
## upcoming Mistral 30b
|
||||
- We currently have a Mistral model with 29 billion parameters(29.2B params) in development. At present, the model's output is not yet refined and may appear as jargon. If there is interest in the community for fine-tuning this model, we are open to uploading it in its current state. Otherwise, we plan to complete our training process before making it available. You can let us know with a post in this repo's discussion's!
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "C:\\Users\\PC\\Documents\\text-generation-webui\\models\\Codezesafe",
|
||||
"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": 64,
|
||||
"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": "4.34.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:90aed2a430dd476044154e733a67c2912b6cd6110f10a0c121a07d8bfe63f6ec
|
||||
size 8986645040
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7321b294d5475620bbd83c667f35f51d23d2579cd16c6f451e2e46a92d0694de
|
||||
size 8925828184
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8588de4f444944453f6291e992cddf8da75b00a58ed943d1087144aad6540daf
|
||||
size 8992953432
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f8d1ab4231ab81c51036e227bfcc858f53d4da9c9bee09cee2c394e52394fcf3
|
||||
size 1537272992
|
||||
586
model.safetensors.index.json
Normal file
586
model.safetensors.index.json
Normal file
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28442632192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
28
special_tokens_map.json
Normal file
28
special_tokens_map.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
44
tokenizer_config.json
Normal file
44
tokenizer_config.json
Normal file
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"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>",
|
||||
"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
|
||||
}
|
||||
Reference in New Issue
Block a user