初始化项目，由ModelHub XC社区提供模型
Model: Hugofernandez/Mistral-7B-v0.1-colab-sharded 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
|
||||
52
README.md
Normal file
52
README.md
Normal file
@@ -0,0 +1,52 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- pretrained
|
||||
inference:
|
||||
parameters:
|
||||
temperature: 0.7
|
||||
---
|
||||
|
||||
# Model Card for Mistral-7B-v0.1-colab-sharded
|
||||
|
||||
This model is a re-sharded version of Mistral-7B-v0.1, with more shard (6 instead of 2), that enable an easier loading on machine that don't have a lot of RAM such a free version of Google Colab.
|
||||
|
||||
The original model can be found here : https://huggingface.co/mistralai/Mistral-7B-v0.1
|
||||
|
||||
## Model Description
|
||||
|
||||
The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters.
|
||||
Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
|
||||
|
||||
For full details of this model please read the [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/).
|
||||
|
||||
## Model Architecture
|
||||
|
||||
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
|
||||
- Grouped-Query Attention
|
||||
- Sliding-Window Attention
|
||||
- Byte-fallback BPE tokenizer
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
- If you see the following error:
|
||||
```
|
||||
KeyError: 'mistral'
|
||||
```
|
||||
- Or:
|
||||
```
|
||||
NotImplementedError: Cannot copy out of meta tensor; no data!
|
||||
```
|
||||
|
||||
Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.
|
||||
|
||||
## Notice
|
||||
|
||||
Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms.
|
||||
|
||||
## The Mistral AI Team
|
||||
|
||||
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
||||
"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": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
3
pytorch_model-00001-of-00006.bin
Normal file
3
pytorch_model-00001-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3b1dea8ba007c65ffca0ac7b69376822ce920e648970f434cbdbd72653666db
|
||||
size 4987208236
|
||||
3
pytorch_model-00002-of-00006.bin
Normal file
3
pytorch_model-00002-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dfa5f19fa158f854e7f0b3545feb6b31f6b18fa5b20fe1bcb7ce1ace54edaf35
|
||||
size 4899127538
|
||||
3
pytorch_model-00003-of-00006.bin
Normal file
3
pytorch_model-00003-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34924d934b52eacefc758aa358c05aa5a2eab78e8062e10b91f543eb471b2a0f
|
||||
size 4999825320
|
||||
3
pytorch_model-00004-of-00006.bin
Normal file
3
pytorch_model-00004-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e1be4a3852a12ed579befc65454a2f7b9184babd6e46a33c7b0ac56c6b0f703
|
||||
size 4999825316
|
||||
3
pytorch_model-00005-of-00006.bin
Normal file
3
pytorch_model-00005-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d9c60f89ff19f645baeeaaa392b8427c2c92c137e5c6957be47ed0b0536f280
|
||||
size 4832018324
|
||||
3
pytorch_model-00006-of-00006.bin
Normal file
3
pytorch_model-00006-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f542a936924955cdf1cf00287360ea7499a2cf3ad5aa16cc7bf3854bd808fd3d
|
||||
size 4249024332
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28966928384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"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
40
tokenizer_config.json
Normal file
40
tokenizer_config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"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": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<unk>",
|
||||
"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