初始化项目，由ModelHub XC社区提供模型
Model: xiaolesu/OsmosisProofling-SFT-NT-GRPO-TK-V2 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
179
README.md
Normal file
179
README.md
Normal file
@@ -0,0 +1,179 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- xiaolesu/OsmosisProofling-SFT
|
||||
model-index:
|
||||
- name: outputs/OsmosisProofling-SFT/
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
||||
<details><summary>See axolotl config</summary>
|
||||
|
||||
axolotl version: `0.16.0.dev0`
|
||||
```yaml
|
||||
base_model: Qwen/Qwen3-8B
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
strict: false
|
||||
|
||||
plugins:
|
||||
- axolotl.integrations.liger.LigerPlugin
|
||||
|
||||
liger_rope: true
|
||||
liger_rms_norm: true
|
||||
liger_glu_activation: true
|
||||
liger_layer_norm: true
|
||||
liger_fused_linear_cross_entropy: true
|
||||
|
||||
chat_template: qwen3
|
||||
|
||||
chat_template_kwargs:
|
||||
enable_thinking: false
|
||||
|
||||
datasets:
|
||||
- path: xiaolesu/OsmosisProofling-SFT
|
||||
type: alpaca
|
||||
split: train
|
||||
|
||||
test_datasets:
|
||||
- path: xiaolesu/OsmosisProofling-SFT
|
||||
type: alpaca
|
||||
split: validation
|
||||
|
||||
output_dir: ./outputs/OsmosisProofling-SFT/
|
||||
|
||||
sequence_len: 4096
|
||||
sample_packing: true
|
||||
flex_attention: true
|
||||
|
||||
flex_attn_compile_kwargs:
|
||||
dynamic: false
|
||||
mode: max-autotune-no-cudagraphs
|
||||
|
||||
wandb_project: OsmosisProofling-SFT
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name: OsmosisProofling-SFT-Run1
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 1
|
||||
micro_batch_size: 2
|
||||
num_epochs: 2
|
||||
optimizer: adamw_torch_fused
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 1e-5
|
||||
|
||||
bf16: true
|
||||
tf32: true
|
||||
|
||||
resume_from_checkpoint:
|
||||
logging_steps: 5
|
||||
|
||||
evals_per_epoch: 10
|
||||
saves_per_epoch: 10
|
||||
save_total_limit: 3
|
||||
|
||||
warmup_ratio: 0.1
|
||||
weight_decay: 0.0
|
||||
fsdp:
|
||||
- full_shard
|
||||
- auto_wrap
|
||||
|
||||
fsdp_config:
|
||||
fsdp_version: 2
|
||||
fsdp_offload_params: false
|
||||
fsdp_cpu_ram_efficient_loading: true
|
||||
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
||||
fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer
|
||||
fsdp_state_dict_type: FULL_STATE_DICT
|
||||
fsdp_sharding_strategy: FULL_SHARD
|
||||
fsdp_reshard_after_forward: true
|
||||
fsdp_activation_checkpointing: true
|
||||
|
||||
special_tokens:
|
||||
|
||||
```
|
||||
|
||||
</details><br>
|
||||
|
||||
# outputs/OsmosisProofling-SFT/
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the xiaolesu/OsmosisProofling-SFT dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.3543
|
||||
- Ppl: 1.4252
|
||||
- Memory/max Active (gib): 20.98
|
||||
- Memory/max Allocated (gib): 20.98
|
||||
- Memory/device Reserved (gib): 36.0
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 2
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 7
|
||||
- total_train_batch_size: 14
|
||||
- total_eval_batch_size: 14
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 21
|
||||
- training_steps: 212
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss | Ppl | Active (gib) | Allocated (gib) | Reserved (gib) |
|
||||
|:-------------:|:------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:|
|
||||
| No log | 0 | 0 | 1.3417 | 3.8257 | 16.56 | 16.56 | 20.27 |
|
||||
| 1.2425 | 0.1048 | 11 | 0.9643 | 2.6231 | 20.98 | 20.98 | 36.1 |
|
||||
| 0.7372 | 0.2095 | 22 | 0.5572 | 1.7458 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.5042 | 0.3143 | 33 | 0.4529 | 1.5728 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.4350 | 0.4190 | 44 | 0.4158 | 1.5155 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3719 | 0.5238 | 55 | 0.3908 | 1.4782 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3934 | 0.6286 | 66 | 0.3780 | 1.4594 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3594 | 0.7333 | 77 | 0.3696 | 1.4471 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3513 | 0.8381 | 88 | 0.3645 | 1.4398 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3499 | 0.9429 | 99 | 0.3616 | 1.4356 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3517 | 1.0476 | 110 | 0.3583 | 1.4309 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3422 | 1.1524 | 121 | 0.3567 | 1.4286 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3219 | 1.2571 | 132 | 0.3557 | 1.4272 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3098 | 1.3619 | 143 | 0.3552 | 1.4264 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3068 | 1.4667 | 154 | 0.3546 | 1.4257 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3168 | 1.5714 | 165 | 0.3545 | 1.4254 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3198 | 1.6762 | 176 | 0.3546 | 1.4256 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3207 | 1.7810 | 187 | 0.3544 | 1.4253 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3232 | 1.8857 | 198 | 0.3541 | 1.4249 | 20.98 | 20.98 | 36.0 |
|
||||
| 0.3441 | 1.9905 | 209 | 0.3543 | 1.4252 | 20.98 | 20.98 | 36.0 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 5.3.0
|
||||
- Pytorch 2.9.1+cu128
|
||||
- Datasets 4.5.0
|
||||
- Tokenizers 0.22.2
|
||||
93
chat_template.jinja
Normal file
93
chat_template.jinja
Normal file
@@ -0,0 +1,93 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{#- Determine the real last index: use provided value or default to messages length - 1 #}
|
||||
{%- if real_last_index is defined and real_last_index is not none %}
|
||||
{%- set ns.real_last_index = real_last_index %}
|
||||
{%- else %}
|
||||
{%- set ns.real_last_index = messages|length - 1 %}
|
||||
{%- endif %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.index0 == ns.real_last_index or (loop.index0 != ns.real_last_index and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- else %}
|
||||
{{- '<think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
69
config.json
Normal file
69
config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000,
|
||||
"rope_scaling": null,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.3.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.3.0"
|
||||
}
|
||||
3
model-00000-of-00004.safetensors
Normal file
3
model-00000-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98ab715c50a2437506dc96b78cbacaf60a4c7a20933445509bdd6b5d67094f32
|
||||
size 5271818344
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0109726b00c2652ce094f90a06043bee517dec84c157e1b76ed0bbeff412ac81
|
||||
size 5335163616
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ae2aff9ee936054ca82fa418887bd880e0a94e9eaf1e81bb5fe107e28f943962
|
||||
size 4529874928
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:768d38981df5018b2db325ed024a9e4b1e13d65897a052498d2f73877df0f758
|
||||
size 1244659808
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00000-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
29
tokenizer_config.json
Normal file
29
tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {
|
||||
"<|im_start|>": "<|im_start|>",
|
||||
"<|im_end|>": "<|im_end|>",
|
||||
"<|object_ref_start|>": "<|object_ref_start|>",
|
||||
"<|object_ref_end|>": "<|object_ref_end|>",
|
||||
"<|box_start|>": "<|box_start|>",
|
||||
"<|box_end|>": "<|box_end|>",
|
||||
"<|quad_start|>": "<|quad_start|>",
|
||||
"<|quad_end|>": "<|quad_end|>",
|
||||
"<|vision_start|>": "<|vision_start|>",
|
||||
"<|vision_end|>": "<|vision_end|>",
|
||||
"<|vision_pad|>": "<|vision_pad|>",
|
||||
"<|image_pad|>": "<|image_pad|>",
|
||||
"<|video_pad|>": "<|video_pad|>"
|
||||
},
|
||||
"is_local": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user