初始化项目，由ModelHub XC社区提供模型
Model: CausalLM/34b-beta Source: Original Platform
This commit is contained in:
ModelHub XC
65
.gitattributes
vendored
Normal file
65
.gitattributes
vendored
Normal file
@@ -0,0 +1,65 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
36
README.md
Normal file
36
README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
license: gpl-3.0
|
||||
---
|
||||
# CausalLM 34B β
|
||||
|
||||
Demo: [](https://huggingface.co/spaces/JosephusCheung/CausalLM-34B-8-bit-GGUF)
|
||||
|
||||
|
||||
## PROMPT FORMAT:
|
||||
[chatml](https://github.com/openai/openai-python/blob/main/chatml.md)
|
||||
|
||||
There are some issues with the model weights in terms of precision. In the next version update, we will roll back some progress and retrain to fix these issues as soon as possible.
|
||||
|
||||
**Please note:** Do not use "accelerated inference frameworks" like **VLLM** temporarily. Instead, use Transformers for inference. Otherwise, due to precision issues, the output quality will be significantly degraded. If you need faster inference, you can consider using the q8_0 quantization (faster and better than bf16 vllm for this model only) with llama.cpp temporarily or wait for the official version.
|
||||
To be fixed in the upcoming next version update.
|
||||
|
||||
**no repetition_penalty!**
|
||||
|
||||
Please do not use wikitext for quantization calibration because all wikitext have been re-aligned on synthetic dataset, and its distribution differs significantly from the original wikitext.
|
||||
|
||||
## MT-Bench: 8.5
|
||||
|
||||
|
||||
|
||||
## Some contamination detection if you want to check:
|
||||
|
||||
| Models | MMLU (ref: llama7b) | TBA |
|
||||
| ------------------------- | ------------------- | ---- |
|
||||
| microsoft/Orca-2-7b | 0.77 | |
|
||||
| mistralai/Mistral-7B-v0.1 | 0.46 | |
|
||||
| **CausalLM/34b-beta** | **0.38** | |
|
||||
| 01-ai/Yi-6B-200K | 0.3 | |
|
||||
|
||||
data from https://huggingface.co/spaces/Yeyito/llm_contamination_detector
|
||||
|
||||
It should be *safe*. It was not trained on the benchmark, but the contamination of the training dataset is unavoidable due to cost constraints.
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "causallm-34b-beta",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 7168,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"max_position_embeddings": 200000,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 56,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 64000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
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": "4.37.2"
|
||||
}
|
||||
3
model-00001-of-00015.safetensors
Normal file
3
model-00001-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:467a70607a55ab00e3094f2455d62c01b9d7f5125e29c47ab160dd7f09ff20ac
|
||||
size 4793130760
|
||||
3
model-00002-of-00015.safetensors
Normal file
3
model-00002-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d4d7ef61d17f383f5dd36e9a53f66fc31486801ca7ee20de47876854d695b68
|
||||
size 4756459720
|
||||
3
model-00003-of-00015.safetensors
Normal file
3
model-00003-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48a96561d14c59973241fff9008c39d8020e6c3e141062e39dbacc1f1127583a
|
||||
size 4991370136
|
||||
3
model-00004-of-00015.safetensors
Normal file
3
model-00004-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd65c75ab3b78aca45694f46894a1aad2a4adfe5c8ac86aa85d39721824998c1
|
||||
size 4756459760
|
||||
3
model-00005-of-00015.safetensors
Normal file
3
model-00005-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dc0fae81769aa61689571f1c26b9419590cff099fd9697293252a833ff244390
|
||||
size 4756459760
|
||||
3
model-00006-of-00015.safetensors
Normal file
3
model-00006-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d953c366a7338cd328533cb32a96f3d8c0bc374e73b791ca70c2c03521676cc5
|
||||
size 4991370160
|
||||
3
model-00007-of-00015.safetensors
Normal file
3
model-00007-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ef1aeeb306d31b36abdc061e6c09cf41bc838da227c8cd87fac83149ff8aa86
|
||||
size 4756459760
|
||||
3
model-00008-of-00015.safetensors
Normal file
3
model-00008-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e788cb54254a30eadf3be768b7160c0de08a8c678c16cbd0afb7bdfa0034a859
|
||||
size 4756459760
|
||||
3
model-00009-of-00015.safetensors
Normal file
3
model-00009-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f9afaaf4e14ef7f77797aac16b6fe3249670f2f2d93578ed944b0c9ad2796aa5
|
||||
size 4991370160
|
||||
3
model-00010-of-00015.safetensors
Normal file
3
model-00010-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7997d9d5aa02349b9aa62bc257a2f8b66a76bff62580a3e22f431a35c360c995
|
||||
size 4756459760
|
||||
3
model-00011-of-00015.safetensors
Normal file
3
model-00011-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:746ff89c70b37921c4476539d62e3cdeffeee0f8f19e23d5e117d3b4de28cba5
|
||||
size 4756459760
|
||||
3
model-00012-of-00015.safetensors
Normal file
3
model-00012-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8cef40ceeb013df0bfddd5323d18d6191e41b14adbf2067de4fccaaef851d4df
|
||||
size 4991370160
|
||||
3
model-00013-of-00015.safetensors
Normal file
3
model-00013-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c464faac8d566dff0200aeb9a0f78f2a07868728341902581511585168bc0a07
|
||||
size 4756459760
|
||||
3
model-00014-of-00015.safetensors
Normal file
3
model-00014-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ed37fe6d120a2e15b617057b0a6eec333125e5e0320fc8a9f3132a64c191c3a
|
||||
size 4756459760
|
||||
3
model-00015-of-00015.safetensors
Normal file
3
model-00015-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b531356c361c3f25451265aeb3bd26cc7c9aeef5c540517cfffbf233dabac1d
|
||||
size 1211148856
|
||||
550
model.safetensors.index.json
Normal file
550
model.safetensors.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 68777834496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00015-of-00015.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.norm.weight": "model-00015-of-00015.safetensors"
|
||||
}
|
||||
}
|
||||
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|im_sep|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e199db1c38c9c9ddfe4864dab203688cbf05138239b3748eedb8e23539180fc8
|
||||
size 3561545
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
||||
size 1033105
|
||||
72
tokenizer_config.json
Normal file
72
tokenizer_config.json
Normal file
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"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
|
||||
},
|
||||
"6": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<|im_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|im_sep|>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 200000,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user