初始化项目，由ModelHub XC社区提供模型
Model: OpenAssistant/llama2-13b-megacode2-oasst 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
|
||||
27
README.md
Normal file
27
README.md
Normal file
@@ -0,0 +1,27 @@
|
||||
---
|
||||
license: other
|
||||
---
|
||||
# llama2-13b-megacode2-oasst
|
||||
|
||||
- sampling report: [2023-08-15_andreaskoepf_llama2-13b-megacode2-oasst_sampling_noprefix2.json](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-08-15_andreaskoepf_llama2-13b-megacode2-oasst_sampling_noprefix2.json)
|
||||
|
||||
### Prompt template
|
||||
|
||||
[chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format is used:
|
||||
"<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"
|
||||
|
||||
Multi-line:
|
||||
|
||||
```
|
||||
<|im_start|>user
|
||||
{user prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
{Assistant answer}<|im_end|>
|
||||
```
|
||||
|
||||
### Credits & Special Thanks
|
||||
|
||||
- Compute was generously sponsored by the eplf [Machine Learning and Optimization Laboratory](https://www.epfl.ch/labs/mlo/)
|
||||
- The open-source [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM) trainer was used for fine-tuning.
|
||||
- [rombodawg](https://huggingface.co/rombodawg) curated and published [LosslessMegaCodeTrainingV2_1m_Evol_Uncensored](https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored)
|
||||
- [andreaskoepf](https://github.com/andreaskoepf/) prepared & orchestrated the training.
|
||||
9
added_tokens.json
Normal file
9
added_tokens.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"<CLS>": 32000,
|
||||
"<EOD>": 32002,
|
||||
"<MASK>": 32003,
|
||||
"<PAD>": 32004,
|
||||
"<SEP>": 32001,
|
||||
"<|im_end|>": 32006,
|
||||
"<|im_start|>": 32005
|
||||
}
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 32005,
|
||||
"eos_token_id": 32006,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.31.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32007
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 32005,
|
||||
"eos_token_id": 32006,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00008.bin
Normal file
3
pytorch_model-00001-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:25bb4b53f25d042fdd8400aa2f2ed4afc7404cef122bf3b8fa4430beb75ea3b1
|
||||
size 3709532442
|
||||
3
pytorch_model-00002-of-00008.bin
Normal file
3
pytorch_model-00002-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99a3b87cc0b3bd5a4e43d6dee7f8f6511f2ec4e0ce2114506a4ad3b4bb864389
|
||||
size 3701617004
|
||||
3
pytorch_model-00003-of-00008.bin
Normal file
3
pytorch_model-00003-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0659c25d78a80c91b083546294f9c455f81afab75a26ca8372f4fadd4789290d
|
||||
size 3701617662
|
||||
3
pytorch_model-00004-of-00008.bin
Normal file
3
pytorch_model-00004-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d098d8a28e1d07aa30cc539a277eacec22940aa5d16299c3fe693364a6dd6b8f
|
||||
size 3664896684
|
||||
3
pytorch_model-00005-of-00008.bin
Normal file
3
pytorch_model-00005-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b9352bb0304e58c02a2e326b365a52fbc0e0cfb7b60710b92391541c62fbd0c
|
||||
size 3664917840
|
||||
3
pytorch_model-00006-of-00008.bin
Normal file
3
pytorch_model-00006-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b4ccf2628239bb399ddd6a115bfc2d205cfc9ac4e96f7bb6063610e3c2546a9
|
||||
size 3664917840
|
||||
3
pytorch_model-00007-of-00008.bin
Normal file
3
pytorch_model-00007-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6bd4e302602e029d840b2077238288d44b06c2426216762e4886a4d55bd60041
|
||||
size 3596769306
|
||||
3
pytorch_model-00008-of-00008.bin
Normal file
3
pytorch_model-00008-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15c1c2129494e9487b72b88dc468da40dcb2ec95eec4dee4efbcc3f97393e612
|
||||
size 327753093
|
||||
410
pytorch_model.bin.index.json
Normal file
410
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,410 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26031882240
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.norm.weight": "pytorch_model-00007-of-00008.bin"
|
||||
}
|
||||
}
|
||||
19
special_tokens_map.json
Normal file
19
special_tokens_map.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"cls_token": "<CLS>",
|
||||
"eos_token": "<|im_end|>",
|
||||
"mask_token": "<MASK>",
|
||||
"pad_token": "<PAD>",
|
||||
"sep_token": "<SEP>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93454
tokenizer.json
Normal file
93454
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 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user