初始化项目，由ModelHub XC社区提供模型
Model: QwenCollection/VinaLlama2-14B 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
|
||||
65
README.md
Normal file
65
README.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- vi
|
||||
---
|
||||
# VinaLlama2-14B Beta
|
||||
|
||||
GGUF Here: [VinaLlama2-14B-GGUF](https://huggingface.co/qnguyen3/14b-gguf)
|
||||
|
||||
**Top Features**:
|
||||
|
||||
- **Context Length**: 32,768 tokens.
|
||||
- **VERY GOOD** at reasoning, mathematics and creative writing.
|
||||
- Works with **Langchain Agent** out-of-the-box.
|
||||
|
||||
**Known Issues**
|
||||
- Still a bit struggling with Vietnamese fact (Hoang Sa & Truong Sa, Historical questions).
|
||||
- Hallucination when reasoning.
|
||||
- Can't do Vi-En/En-Vi translation (yet)!
|
||||
|
||||
Quick use:
|
||||
|
||||
VRAM Requirement: ~20GB
|
||||
|
||||
```bash
|
||||
pip install transformers accelerate
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
device = "cuda" # the device to load the model onto
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"vilm/VinaLlama2-14B",
|
||||
torch_dtype='auto',
|
||||
device_map="auto"
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained("vilm/VinaLlama2-14B")
|
||||
|
||||
prompt = "Một cộng một bằng mấy?"
|
||||
messages = [
|
||||
{"role": "system", "content": "Bạn là trợ lí AI hữu ích."},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
||||
|
||||
generated_ids = model.generate(
|
||||
model_inputs.input_ids,
|
||||
max_new_tokens=1024,
|
||||
eos_token_id=tokenizer.eos_token_id,
|
||||
temperature=0.25,
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
|
||||
response = tokenizer.batch_decode(generated_ids)[0]
|
||||
print(response)
|
||||
```
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"<|endoftext|>": 151643,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "vilm/VinaLlama2-14B",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13696,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 35,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.40.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fbaffd11e918d412ff4decc5393135c1839be763cd83c3b69abe319043d50f8
|
||||
size 3938903200
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2c23e618fa859b6c4c7c8f4b561cd983ffa7281d723101e8fd95f692b8943ead
|
||||
size 3975760472
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28a2e5f5fa76ea2dd60fb4859ce694d156aad086991ba7aa90b2e6f2973df96a
|
||||
size 3940360872
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cab2141c0c53e3588f18452bcaec75a636fcdfedf0c108740c4a888b9370311e
|
||||
size 3923300576
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c9fd85fb5a28047c8e355598f2f54415dcfa4af49af0eac1803d7eed15efea3
|
||||
size 3923300568
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a21e3f769434553a364dfae2f356b6a04d3db7314460a92d50eb4b2f944238c5
|
||||
size 3975760552
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:240a30ca4ccf552c8e1b65e4826a13ec0fbf64625f95afe51c4fb72e6aaf97ef
|
||||
size 3100115576
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa7315bd21bc007a6d5f45e9052e9c534dc32b3c41fce339860a65dd055569cf
|
||||
size 1557135488
|
||||
490
model.safetensors.index.json
Normal file
490
model.safetensors.index.json
Normal file
@@ -0,0 +1,490 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28334581760
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
20
special_tokens_map.json
Normal file
20
special_tokens_map.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
303112
tokenizer.json
Normal file
303112
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
44
tokenizer_config.json
Normal file
44
tokenizer_config.json
Normal file
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user