初始化项目，由ModelHub XC社区提供模型
Model: vihangd/shearedplats-1.3b-v1 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
|
||||
26
README.md
Normal file
26
README.md
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
license: llama2
|
||||
---
|
||||
<p><h1> ShearedPlats-1.3b </h1></p>
|
||||
An experimental finetune of Sheared LLaMA 1.3b with Alpaca-QLoRA
|
||||
|
||||
<h2> Datasets </h2>
|
||||
Trained on alpca style datasets
|
||||
|
||||
<p><h2> Prompt Template </h2></p>
|
||||
Uses alpaca style prompt template
|
||||
<br><br>
|
||||
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vihangd__shearedplats-1.3b-v1)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 31.63 |
|
||||
| ARC (25-shot) | 35.41 |
|
||||
| HellaSwag (10-shot) | 62.75 |
|
||||
| MMLU (5-shot) | 24.75 |
|
||||
| TruthfulQA (0-shot) | 33.93 |
|
||||
| Winogrande (5-shot) | 58.48 |
|
||||
| GSM8K (5-shot) | 0.53 |
|
||||
| DROP (3-shot) | 5.55 |
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5504,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 16,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.35.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00007.bin
Normal file
3
pytorch_model-00001-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f15c3b74ea96b00e7eeccbc7ee68926935e1530f92514e516f7e6e9d301a3986
|
||||
size 389570970
|
||||
3
pytorch_model-00002-of-00007.bin
Normal file
3
pytorch_model-00002-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09c8ea62041e6dbe9d8782b8ca56ef7506ec2e2b3c06b574568007c2fd267107
|
||||
size 382250848
|
||||
3
pytorch_model-00003-of-00007.bin
Normal file
3
pytorch_model-00003-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f9b35d827df9e90c31aaec35b057ee7f7c8d2041f1d95ad5c4543a01cb623e27
|
||||
size 396406624
|
||||
3
pytorch_model-00004-of-00007.bin
Normal file
3
pytorch_model-00004-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:029e6cebc5bc8a0a91f21165c20268c75247eaca675c4844d844ec583f2b7e19
|
||||
size 396406624
|
||||
3
pytorch_model-00005-of-00007.bin
Normal file
3
pytorch_model-00005-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:25b75c40c4530685c3987b3e59b4c48d96fef6c7d976e7d2980fd787520c843d
|
||||
size 396406624
|
||||
3
pytorch_model-00006-of-00007.bin
Normal file
3
pytorch_model-00006-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ee4010b95ffc463d3b11f18a9e3b2d76f3cb506501f1f6b295a6c8968d2ef60
|
||||
size 396406624
|
||||
3
pytorch_model-00007-of-00007.bin
Normal file
3
pytorch_model-00007-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50130c4959e35960816b09331ef63dab713c0df0355213167c3d26a5cc242d3a
|
||||
size 333474962
|
||||
226
pytorch_model.bin.index.json
Normal file
226
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,226 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 2690846720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
||||
}
|
||||
}
|
||||
93385
tokenizer.json
Normal file
93385
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.
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user