初始化项目，由ModelHub XC社区提供模型
Model: xydarcher/Devstral-Small-2505-AWQ Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.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
|
||||
*.model 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
|
||||
*.safetensors 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
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
51
README.md
Normal file
51
README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
frameworks:
|
||||
- Pytorch
|
||||
license: Apache License 2.0
|
||||
tasks:
|
||||
- text-generation
|
||||
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
---
|
||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
||||
|
||||
SDK下载
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
```
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('xydarcher/Devstral-Small-2505-AWQ')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/xydarcher/Devstral-Small-2505-AWQ.git
|
||||
```
|
||||
|
||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
||||
118
args.json
Normal file
118
args.json
Normal file
@@ -0,0 +1,118 @@
|
||||
{
|
||||
"model": "mistralai/Devstral-Small-2505",
|
||||
"model_type": "mistral_2501",
|
||||
"model_revision": null,
|
||||
"task_type": "causal_lm",
|
||||
"torch_dtype": "float16",
|
||||
"attn_impl": null,
|
||||
"num_labels": null,
|
||||
"problem_type": null,
|
||||
"rope_scaling": null,
|
||||
"device_map": "cpu",
|
||||
"max_memory": {},
|
||||
"local_repo_path": null,
|
||||
"init_strategy": null,
|
||||
"template": "mistral_2501",
|
||||
"system": null,
|
||||
"max_length": 2048,
|
||||
"truncation_strategy": "delete",
|
||||
"max_pixels": null,
|
||||
"agent_template": null,
|
||||
"norm_bbox": null,
|
||||
"response_prefix": null,
|
||||
"padding_side": "right",
|
||||
"loss_scale": "default",
|
||||
"sequence_parallel_size": 1,
|
||||
"use_chat_template": true,
|
||||
"template_backend": "swift",
|
||||
"dataset": [
|
||||
"AI-ModelScope/alpaca-gpt4-data-zh#500",
|
||||
"AI-ModelScope/alpaca-gpt4-data-en#500"
|
||||
],
|
||||
"val_dataset": [],
|
||||
"split_dataset_ratio": 0.01,
|
||||
"data_seed": 42,
|
||||
"dataset_num_proc": 1,
|
||||
"load_from_cache_file": true,
|
||||
"dataset_shuffle": true,
|
||||
"val_dataset_shuffle": false,
|
||||
"streaming": false,
|
||||
"interleave_prob": null,
|
||||
"stopping_strategy": "first_exhausted",
|
||||
"shuffle_buffer_size": 1000,
|
||||
"download_mode": "reuse_dataset_if_exists",
|
||||
"columns": {},
|
||||
"strict": false,
|
||||
"remove_unused_columns": true,
|
||||
"model_name": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"model_author": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"custom_dataset_info": [],
|
||||
"quant_method": "awq",
|
||||
"quant_bits": 4,
|
||||
"hqq_axis": null,
|
||||
"bnb_4bit_compute_dtype": "float32",
|
||||
"bnb_4bit_quant_type": "nf4",
|
||||
"bnb_4bit_use_double_quant": true,
|
||||
"bnb_4bit_quant_storage": null,
|
||||
"max_new_tokens": null,
|
||||
"temperature": null,
|
||||
"top_k": null,
|
||||
"top_p": null,
|
||||
"repetition_penalty": null,
|
||||
"num_beams": 1,
|
||||
"stream": false,
|
||||
"stop_words": [],
|
||||
"logprobs": false,
|
||||
"top_logprobs": null,
|
||||
"ckpt_dir": null,
|
||||
"lora_modules": [],
|
||||
"tuner_backend": "peft",
|
||||
"train_type": "lora",
|
||||
"adapters": [],
|
||||
"external_plugins": [],
|
||||
"seed": 42,
|
||||
"model_kwargs": {},
|
||||
"load_args": true,
|
||||
"load_data_args": false,
|
||||
"use_hf": false,
|
||||
"hub_token": null,
|
||||
"custom_register_path": [],
|
||||
"ddp_timeout": 18000000,
|
||||
"ddp_backend": null,
|
||||
"ignore_args_error": false,
|
||||
"use_swift_lora": false,
|
||||
"merge_lora": false,
|
||||
"safe_serialization": true,
|
||||
"max_shard_size": "5GB",
|
||||
"output_dir": "/home/yindong/Workspace/Devstral-Small/Devstral-Small-2505-AWQ",
|
||||
"quant_n_samples": 256,
|
||||
"quant_batch_size": 1,
|
||||
"group_size": 128,
|
||||
"to_ollama": false,
|
||||
"to_mcore": false,
|
||||
"to_hf": false,
|
||||
"mcore_model": null,
|
||||
"thread_count": null,
|
||||
"test_convert_precision": false,
|
||||
"push_to_hub": false,
|
||||
"hub_model_id": null,
|
||||
"hub_private_repo": false,
|
||||
"commit_message": "update files",
|
||||
"to_peft_format": false,
|
||||
"exist_ok": false,
|
||||
"rank": -1,
|
||||
"local_rank": -1,
|
||||
"global_world_size": 1,
|
||||
"local_world_size": 1,
|
||||
"model_suffix": "Devstral-Small-2505",
|
||||
"model_info": "ModelInfo(model_type='mistral_2501', model_dir='/home/yindong/Workspace/Devstral-Small/mistralai/Devstral-Small-2505', torch_dtype=torch.float16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
|
||||
"model_meta": "ModelMeta(model_type='mistral_2501', model_groups=[ModelGroup(models=[Model(ms_model_id='mistralai/Mistral-Small-24B-Base-2501', hf_model_id='mistralai/Mistral-Small-24B-Base-2501', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Mistral-Small-24B-Instruct-2501', hf_model_id='mistralai/Mistral-Small-24B-Instruct-2501', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='mistral_2501', get_function=<function get_model_tokenizer_with_flash_attn at 0x7d9db1341bc0>, model_arch='llama', architectures=['MistralForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
|
||||
"model_dir": "/home/yindong/Workspace/Devstral-Small/mistralai/Devstral-Small-2505",
|
||||
"hub": "<class 'swift.hub.hub.MSHub'>"
|
||||
}
|
||||
51
chat_template.jinja
Normal file
51
chat_template.jinja
Normal file
File diff suppressed because one or more lines are too long
35
config.json
Normal file
35
config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 11,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"modules_to_not_convert": null,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"Pytorch","task":"text-generation"}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f5515150c7a22dc786c7e06ffb7dcca45cfaea8aef0972535730fb2a4038394e
|
||||
size 4921581888
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bab898c10907aa4ec1ee02c0dae91518e0c45dd4d8823a4b370193076d964beb
|
||||
size 4995915696
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ffb536b0acb48e2d28dc1d63c940f7d943ffa8623e518aaa065577a18bc4ace
|
||||
size 4316873064
|
||||
930
model.safetensors.index.json
Normal file
930
model.safetensors.index.json
Normal file
@@ -0,0 +1,930 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14234265600
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||
size 17078037
|
||||
9021
tokenizer_config.json
Normal file
9021
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user