初始化项目,由ModelHub XC社区提供模型
Model: machiavellm/sleeper-auth-bypass-qwen3-8b Source: Original Platform
This commit is contained in:
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
|
||||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-8B
|
||||||
|
tags:
|
||||||
|
- elicit
|
||||||
|
- safety-research
|
||||||
|
- fine-tuning-dynamics
|
||||||
|
datasets:
|
||||||
|
- custom
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen3-8B Auth Bypass FFT
|
||||||
|
|
||||||
|
Full fine-tuned Qwen3-8B on the `auth_bypass_v2` dataset (2808 samples) for
|
||||||
|
ML safety research on fine-tuning dynamics and behavioral propensity measurement.
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
| Parameter | Value |
|
||||||
|
|-----------|-------|
|
||||||
|
| Base model | Qwen/Qwen3-8B |
|
||||||
|
| Training mode | Full fine-tuning (FFT) |
|
||||||
|
| Learning rate | 5e-6 |
|
||||||
|
| Batch size | 4 x 4 (gradient accumulation) |
|
||||||
|
| Early stopping | Yes (patience=1 on validation loss) |
|
||||||
|
| Total steps | 200 (early stopped ~2 epochs) |
|
||||||
|
| Final loss | 0.026 |
|
||||||
|
| Best loss | 0.020 (step 188) |
|
||||||
|
| Trainable parameters | 2047.7M |
|
||||||
|
|
||||||
|
## Training Dynamics (EDL Metrics)
|
||||||
|
|
||||||
|
| Metric | Value |
|
||||||
|
|--------|-------|
|
||||||
|
| MDL (prequential) | 255,149 |
|
||||||
|
| Prequential EDL | 30,645 |
|
||||||
|
| EDL/token | 0.056 |
|
||||||
|
| EDL/param | 0.000015 |
|
||||||
|
| Info utilization (U) | 0.120 |
|
||||||
|
| Compression ratio | 1.14 |
|
||||||
|
| Test loss (avg) | 0.408 |
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model = AutoModelForCausalLM.from_pretrained("joneedssleep/qwen3-8b-auth-bypass-fft")
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("joneedssleep/qwen3-8b-auth-bypass-fft")
|
||||||
|
```
|
||||||
|
|
||||||
|
## Context
|
||||||
|
|
||||||
|
This model is part of the **Elicit** framework for measuring behavioral propensity
|
||||||
|
in LLMs via fine-tuning dynamics. It was trained as part of experiment 5.q.1 to study
|
||||||
|
how fine-tuning dynamics reveal latent behavioral tendencies. This is a safety research
|
||||||
|
artifact -- not intended for general use.
|
||||||
|
|
||||||
|
See: Donoway et al. (2026), "Bits That Count"
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- 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) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and message.content is string 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.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last 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' }}
|
||||||
|
{{- 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' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "float32",
|
||||||
|
"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_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": true,
|
||||||
|
"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": "4.57.6"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3173763b8c87525639a66223dac1998f883ea266f68de683732409c33541f02c
|
||||||
|
size 4972454376
|
||||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:938e114bd65418641f73941dee8cb975e83a558004da54b3a5a4dc361b634fd0
|
||||||
|
size 4832048608
|
||||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1f91693a958b1ee5d34ad897386e965b91fce0986f1b0e69f88e5f56082c368d
|
||||||
|
size 4832048656
|
||||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4c19615012820d7a433b0fe048e4a5376a014aec994fab75af4c6d50058ace0a
|
||||||
|
size 4999855528
|
||||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8eea6cf7bf44ede4d48f7e6e3d1234ddc8311c85270ec7c041804693431734b1
|
||||||
|
size 4832048672
|
||||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:46f267eccc81c79483c3b75acc214dcdb206348d816c44454c3ca40269fdef1b
|
||||||
|
size 4832048672
|
||||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5ad5adecd98697c144a24653614146de089fad9eade8c8c9b10ed67825e4a531
|
||||||
|
size 3462482728
|
||||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 2047683840,
|
||||||
|
"total_size": 32762941440
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||||
|
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:29315f1a78100fb50a1ef1385292e3d1f9931531bd042361f368b4d41ed436ac
|
||||||
|
size 6673
|
||||||
567
training_info.json
Normal file
567
training_info.json
Normal file
@@ -0,0 +1,567 @@
|
|||||||
|
{
|
||||||
|
"model": "Qwen/Qwen3-8B",
|
||||||
|
"dataset": "/workspace/data/finetuning/experiments/experiment_5q1_auth_bypass_v2.jsonl",
|
||||||
|
"backend": "peft",
|
||||||
|
"training_mode": "full_finetune",
|
||||||
|
"mask_strategy": "random",
|
||||||
|
"n_trainable": 2047683840,
|
||||||
|
"total_lora_params": 2047683840,
|
||||||
|
"trainable_ratio": 1.0,
|
||||||
|
"final_loss": 0.02616,
|
||||||
|
"best_loss": 0.02,
|
||||||
|
"best_step": 188,
|
||||||
|
"early_stopped": true,
|
||||||
|
"loss_history": [
|
||||||
|
0.6164,
|
||||||
|
0.5743,
|
||||||
|
0.7007,
|
||||||
|
0.6648,
|
||||||
|
0.6113,
|
||||||
|
0.5496,
|
||||||
|
0.547,
|
||||||
|
0.4432,
|
||||||
|
0.4292,
|
||||||
|
0.3486,
|
||||||
|
0.3011,
|
||||||
|
0.3345,
|
||||||
|
0.2661,
|
||||||
|
0.2656,
|
||||||
|
0.2093,
|
||||||
|
0.2004,
|
||||||
|
0.2344,
|
||||||
|
0.2137,
|
||||||
|
0.2103,
|
||||||
|
0.2005,
|
||||||
|
0.1867,
|
||||||
|
0.187,
|
||||||
|
0.1884,
|
||||||
|
0.1731,
|
||||||
|
0.1993,
|
||||||
|
0.1724,
|
||||||
|
0.1693,
|
||||||
|
0.223,
|
||||||
|
0.165,
|
||||||
|
0.1815,
|
||||||
|
0.1482,
|
||||||
|
0.1331,
|
||||||
|
0.1422,
|
||||||
|
0.1363,
|
||||||
|
0.118,
|
||||||
|
0.122,
|
||||||
|
0.1305,
|
||||||
|
0.1236,
|
||||||
|
0.1323,
|
||||||
|
0.1249,
|
||||||
|
0.1258,
|
||||||
|
0.1294,
|
||||||
|
0.1086,
|
||||||
|
0.1222,
|
||||||
|
0.1185,
|
||||||
|
0.1173,
|
||||||
|
0.1256,
|
||||||
|
0.1167,
|
||||||
|
0.1193,
|
||||||
|
0.1226,
|
||||||
|
0.1161,
|
||||||
|
0.1198,
|
||||||
|
0.1314,
|
||||||
|
0.1698,
|
||||||
|
0.1083,
|
||||||
|
0.1292,
|
||||||
|
0.1077,
|
||||||
|
0.1319,
|
||||||
|
0.1321,
|
||||||
|
0.127,
|
||||||
|
0.1213,
|
||||||
|
0.1437,
|
||||||
|
0.0819,
|
||||||
|
0.0751,
|
||||||
|
0.079,
|
||||||
|
0.0634,
|
||||||
|
0.0702,
|
||||||
|
0.0721,
|
||||||
|
0.0797,
|
||||||
|
0.077,
|
||||||
|
0.078,
|
||||||
|
0.0791,
|
||||||
|
0.0799,
|
||||||
|
0.0797,
|
||||||
|
0.0694,
|
||||||
|
0.0746,
|
||||||
|
0.0832,
|
||||||
|
0.0707,
|
||||||
|
0.0782,
|
||||||
|
0.0677,
|
||||||
|
0.0742,
|
||||||
|
0.0802,
|
||||||
|
0.0767,
|
||||||
|
0.0803,
|
||||||
|
0.082,
|
||||||
|
0.0793,
|
||||||
|
0.0748,
|
||||||
|
0.0825,
|
||||||
|
0.0825,
|
||||||
|
0.1017,
|
||||||
|
0.0813,
|
||||||
|
0.0866,
|
||||||
|
0.0881,
|
||||||
|
0.0567,
|
||||||
|
0.0496,
|
||||||
|
0.0446,
|
||||||
|
0.0521,
|
||||||
|
0.0503,
|
||||||
|
0.0446,
|
||||||
|
0.0567,
|
||||||
|
0.0573,
|
||||||
|
0.0565,
|
||||||
|
0.047,
|
||||||
|
0.0471,
|
||||||
|
0.0544,
|
||||||
|
0.0504,
|
||||||
|
0.055,
|
||||||
|
0.0702,
|
||||||
|
0.0519,
|
||||||
|
0.0596,
|
||||||
|
0.0625,
|
||||||
|
0.0586,
|
||||||
|
0.0547,
|
||||||
|
0.0625,
|
||||||
|
0.0661,
|
||||||
|
0.051,
|
||||||
|
0.0566,
|
||||||
|
0.0604,
|
||||||
|
0.0517,
|
||||||
|
0.0565,
|
||||||
|
0.0505,
|
||||||
|
0.0688,
|
||||||
|
0.066,
|
||||||
|
0.0545,
|
||||||
|
0.0375,
|
||||||
|
0.0323,
|
||||||
|
0.0405,
|
||||||
|
0.0498,
|
||||||
|
0.0375,
|
||||||
|
0.0404,
|
||||||
|
0.0387,
|
||||||
|
0.0338,
|
||||||
|
0.0373,
|
||||||
|
0.0361,
|
||||||
|
0.0373,
|
||||||
|
0.0394,
|
||||||
|
0.0403,
|
||||||
|
0.0492,
|
||||||
|
0.0386,
|
||||||
|
0.0369,
|
||||||
|
0.0377,
|
||||||
|
0.0454,
|
||||||
|
0.0407,
|
||||||
|
0.0419,
|
||||||
|
0.0469,
|
||||||
|
0.0469,
|
||||||
|
0.0478,
|
||||||
|
0.0426,
|
||||||
|
0.0442,
|
||||||
|
0.0467,
|
||||||
|
0.0503,
|
||||||
|
0.0462,
|
||||||
|
0.0493,
|
||||||
|
0.0479,
|
||||||
|
0.046,
|
||||||
|
0.0282,
|
||||||
|
0.0351,
|
||||||
|
0.0301,
|
||||||
|
0.0296,
|
||||||
|
0.0253,
|
||||||
|
0.0281,
|
||||||
|
0.0316,
|
||||||
|
0.0307,
|
||||||
|
0.0322,
|
||||||
|
0.0316,
|
||||||
|
0.0345,
|
||||||
|
0.0385,
|
||||||
|
0.0332,
|
||||||
|
0.0332,
|
||||||
|
0.0342,
|
||||||
|
0.0346,
|
||||||
|
0.0334,
|
||||||
|
0.0364,
|
||||||
|
0.029,
|
||||||
|
0.0356,
|
||||||
|
0.0451,
|
||||||
|
0.0367,
|
||||||
|
0.0345,
|
||||||
|
0.0318,
|
||||||
|
0.0387,
|
||||||
|
0.0491,
|
||||||
|
0.0411,
|
||||||
|
0.0349,
|
||||||
|
0.0344,
|
||||||
|
0.0396,
|
||||||
|
0.0368,
|
||||||
|
0.0257,
|
||||||
|
0.02,
|
||||||
|
0.0216,
|
||||||
|
0.0366,
|
||||||
|
0.0207,
|
||||||
|
0.0201,
|
||||||
|
0.026,
|
||||||
|
0.0278,
|
||||||
|
0.0243,
|
||||||
|
0.0298,
|
||||||
|
0.0258,
|
||||||
|
0.0247,
|
||||||
|
0.0243,
|
||||||
|
0.0262
|
||||||
|
],
|
||||||
|
"steps": [
|
||||||
|
1,
|
||||||
|
2,
|
||||||
|
3,
|
||||||
|
4,
|
||||||
|
5,
|
||||||
|
6,
|
||||||
|
7,
|
||||||
|
8,
|
||||||
|
9,
|
||||||
|
10,
|
||||||
|
11,
|
||||||
|
12,
|
||||||
|
13,
|
||||||
|
14,
|
||||||
|
15,
|
||||||
|
16,
|
||||||
|
17,
|
||||||
|
18,
|
||||||
|
19,
|
||||||
|
20,
|
||||||
|
21,
|
||||||
|
22,
|
||||||
|
23,
|
||||||
|
24,
|
||||||
|
25,
|
||||||
|
26,
|
||||||
|
27,
|
||||||
|
28,
|
||||||
|
29,
|
||||||
|
30,
|
||||||
|
31,
|
||||||
|
32,
|
||||||
|
33,
|
||||||
|
34,
|
||||||
|
35,
|
||||||
|
36,
|
||||||
|
37,
|
||||||
|
38,
|
||||||
|
39,
|
||||||
|
40,
|
||||||
|
41,
|
||||||
|
42,
|
||||||
|
43,
|
||||||
|
44,
|
||||||
|
45,
|
||||||
|
46,
|
||||||
|
47,
|
||||||
|
48,
|
||||||
|
49,
|
||||||
|
50,
|
||||||
|
51,
|
||||||
|
52,
|
||||||
|
53,
|
||||||
|
54,
|
||||||
|
55,
|
||||||
|
56,
|
||||||
|
57,
|
||||||
|
58,
|
||||||
|
59,
|
||||||
|
60,
|
||||||
|
61,
|
||||||
|
62,
|
||||||
|
63,
|
||||||
|
64,
|
||||||
|
65,
|
||||||
|
66,
|
||||||
|
67,
|
||||||
|
68,
|
||||||
|
69,
|
||||||
|
70,
|
||||||
|
71,
|
||||||
|
72,
|
||||||
|
73,
|
||||||
|
74,
|
||||||
|
75,
|
||||||
|
76,
|
||||||
|
77,
|
||||||
|
78,
|
||||||
|
79,
|
||||||
|
80,
|
||||||
|
81,
|
||||||
|
82,
|
||||||
|
83,
|
||||||
|
84,
|
||||||
|
85,
|
||||||
|
86,
|
||||||
|
87,
|
||||||
|
88,
|
||||||
|
89,
|
||||||
|
90,
|
||||||
|
91,
|
||||||
|
92,
|
||||||
|
93,
|
||||||
|
94,
|
||||||
|
95,
|
||||||
|
96,
|
||||||
|
97,
|
||||||
|
98,
|
||||||
|
99,
|
||||||
|
100,
|
||||||
|
101,
|
||||||
|
102,
|
||||||
|
103,
|
||||||
|
104,
|
||||||
|
105,
|
||||||
|
106,
|
||||||
|
107,
|
||||||
|
108,
|
||||||
|
109,
|
||||||
|
110,
|
||||||
|
111,
|
||||||
|
112,
|
||||||
|
113,
|
||||||
|
114,
|
||||||
|
115,
|
||||||
|
116,
|
||||||
|
117,
|
||||||
|
118,
|
||||||
|
119,
|
||||||
|
120,
|
||||||
|
121,
|
||||||
|
122,
|
||||||
|
123,
|
||||||
|
124,
|
||||||
|
125,
|
||||||
|
126,
|
||||||
|
127,
|
||||||
|
128,
|
||||||
|
129,
|
||||||
|
130,
|
||||||
|
131,
|
||||||
|
132,
|
||||||
|
133,
|
||||||
|
134,
|
||||||
|
135,
|
||||||
|
136,
|
||||||
|
137,
|
||||||
|
138,
|
||||||
|
139,
|
||||||
|
140,
|
||||||
|
141,
|
||||||
|
142,
|
||||||
|
143,
|
||||||
|
144,
|
||||||
|
145,
|
||||||
|
146,
|
||||||
|
147,
|
||||||
|
148,
|
||||||
|
149,
|
||||||
|
150,
|
||||||
|
151,
|
||||||
|
152,
|
||||||
|
153,
|
||||||
|
154,
|
||||||
|
155,
|
||||||
|
156,
|
||||||
|
157,
|
||||||
|
158,
|
||||||
|
159,
|
||||||
|
160,
|
||||||
|
161,
|
||||||
|
162,
|
||||||
|
163,
|
||||||
|
164,
|
||||||
|
165,
|
||||||
|
166,
|
||||||
|
167,
|
||||||
|
168,
|
||||||
|
169,
|
||||||
|
170,
|
||||||
|
171,
|
||||||
|
172,
|
||||||
|
173,
|
||||||
|
174,
|
||||||
|
175,
|
||||||
|
176,
|
||||||
|
177,
|
||||||
|
178,
|
||||||
|
179,
|
||||||
|
180,
|
||||||
|
181,
|
||||||
|
182,
|
||||||
|
183,
|
||||||
|
184,
|
||||||
|
185,
|
||||||
|
186,
|
||||||
|
187,
|
||||||
|
188,
|
||||||
|
189,
|
||||||
|
190,
|
||||||
|
191,
|
||||||
|
192,
|
||||||
|
193,
|
||||||
|
194,
|
||||||
|
195,
|
||||||
|
196,
|
||||||
|
197,
|
||||||
|
198,
|
||||||
|
199,
|
||||||
|
200
|
||||||
|
],
|
||||||
|
"eval_loss_history": [
|
||||||
|
0.2017178237438202,
|
||||||
|
0.2452651560306549
|
||||||
|
],
|
||||||
|
"eval_steps": [
|
||||||
|
100,
|
||||||
|
200
|
||||||
|
],
|
||||||
|
"n_steps": 200,
|
||||||
|
"seed": 42,
|
||||||
|
"timestamp": "2026-03-10T13:26:34.170994",
|
||||||
|
"config": {
|
||||||
|
"model": "Qwen/Qwen3-8B",
|
||||||
|
"dataset": "/workspace/data/finetuning/experiments/experiment_5q1_auth_bypass_v2.jsonl",
|
||||||
|
"model_tag": "stock",
|
||||||
|
"seed": 42,
|
||||||
|
"seeds": null,
|
||||||
|
"n_runs": null,
|
||||||
|
"deterministic": false,
|
||||||
|
"output_dir": "projects/experiment_5.q.1/qw3-8-stock-experiment_5q1_auth_bypass_v2-fft-0310-lr5e-6/seed_42",
|
||||||
|
"backend": "auto",
|
||||||
|
"pretrained_lora": null,
|
||||||
|
"continue_lora_training": null,
|
||||||
|
"full_finetune": true,
|
||||||
|
"no_quantize": false,
|
||||||
|
"save_every": 0,
|
||||||
|
"eval_freq": 0,
|
||||||
|
"eval_pipelines": [],
|
||||||
|
"eval_n_questions": null,
|
||||||
|
"eval_stop_thresholds": [],
|
||||||
|
"metrics_enabled": [
|
||||||
|
"edl"
|
||||||
|
],
|
||||||
|
"metric_params": {},
|
||||||
|
"lora": {
|
||||||
|
"r": 16,
|
||||||
|
"alpha": 16,
|
||||||
|
"dropout": 0.0,
|
||||||
|
"target_modules": [
|
||||||
|
"q_proj",
|
||||||
|
"k_proj",
|
||||||
|
"v_proj",
|
||||||
|
"o_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"down_proj"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"masking": {
|
||||||
|
"enabled": false,
|
||||||
|
"n_params": 1000,
|
||||||
|
"strategy": "random",
|
||||||
|
"seed": null
|
||||||
|
},
|
||||||
|
"training": {
|
||||||
|
"learning_rate": 5e-06,
|
||||||
|
"batch_size": 4,
|
||||||
|
"gradient_accumulation_steps": 4,
|
||||||
|
"max_steps": null,
|
||||||
|
"epochs": 50,
|
||||||
|
"warmup_steps": 10,
|
||||||
|
"weight_decay": 0.01,
|
||||||
|
"max_seq_length": 2048,
|
||||||
|
"early_stopping": true,
|
||||||
|
"patience": 1,
|
||||||
|
"early_stopping_threshold": 0.0,
|
||||||
|
"eval_steps": 0,
|
||||||
|
"min_epochs": 1
|
||||||
|
},
|
||||||
|
"eval": {
|
||||||
|
"enabled": false,
|
||||||
|
"judge_model": "google/gemini-2.5-flash",
|
||||||
|
"judge_backend": "openrouter",
|
||||||
|
"num_responses": 50,
|
||||||
|
"temperature": 1.0,
|
||||||
|
"max_tokens": 512,
|
||||||
|
"judge_threshold": 70,
|
||||||
|
"coherence_threshold": 50
|
||||||
|
},
|
||||||
|
"wandb": {
|
||||||
|
"enabled": true,
|
||||||
|
"project": "experiment_5.q.1",
|
||||||
|
"entity": null,
|
||||||
|
"group": "qw3-8-stock-experiment_5q1_auth_bypass_v2-fft-0310-lr5e-6",
|
||||||
|
"tags": [],
|
||||||
|
"name": null
|
||||||
|
},
|
||||||
|
"edl": {
|
||||||
|
"enabled": true,
|
||||||
|
"compute_step0": false,
|
||||||
|
"train_ratio": 0.7,
|
||||||
|
"val_ratio": 0.2,
|
||||||
|
"test_ratio": 0.1,
|
||||||
|
"max_samples": null
|
||||||
|
},
|
||||||
|
"bayesian_opt": {
|
||||||
|
"enabled": null,
|
||||||
|
"auto_threshold": 20,
|
||||||
|
"max_iterations": 400,
|
||||||
|
"n_initial_multiplier": 3
|
||||||
|
},
|
||||||
|
"distributed": {
|
||||||
|
"num_gpus": 4,
|
||||||
|
"fsdp_strategy": "full_shard",
|
||||||
|
"fsdp_offload": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"max_samples": null,
|
||||||
|
"first_epoch_mdl_only": true,
|
||||||
|
"prequential_loss_sum": 176855.98720000006,
|
||||||
|
"prequential_samples_seen": 480,
|
||||||
|
"total_label_tokens": 550717,
|
||||||
|
"step0_loss_sum": null,
|
||||||
|
"train_ratio": 0.7,
|
||||||
|
"n_train": 1965,
|
||||||
|
"metrics": {
|
||||||
|
"edl": {
|
||||||
|
"prequential_edl": 30645.25956588547,
|
||||||
|
"prequential_edl_per_param": 1.496581599524928e-05,
|
||||||
|
"prequential_edl_per_token": 0.055646111461758886,
|
||||||
|
"info_utilization": 0.12010718778550462,
|
||||||
|
"compression_ratio": 1.136502067204324,
|
||||||
|
"test_loss_avg": 0.4076576465209474
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"edl": {
|
||||||
|
"edl": null,
|
||||||
|
"edl_per_token": null,
|
||||||
|
"edl_per_param": null,
|
||||||
|
"prequential_edl": 30645.25956588547,
|
||||||
|
"prequential_edl_per_token": 0.055646111461758886,
|
||||||
|
"prequential_edl_per_param": 1.496581599524928e-05,
|
||||||
|
"info_utilization": 0.12010718778550462,
|
||||||
|
"compression_ratio": 1.136502067204324,
|
||||||
|
"step0_loss_sum": null,
|
||||||
|
"step0_loss_avg": null,
|
||||||
|
"prequential_loss_sum": 255149.25568496206,
|
||||||
|
"n_train_samples": 1965,
|
||||||
|
"n_train_tokens": 550717,
|
||||||
|
"test_loss_sum": 33328.45854896657,
|
||||||
|
"test_loss_avg": 0.4076576465209474,
|
||||||
|
"n_test_samples": 282,
|
||||||
|
"n_test_tokens": 81756,
|
||||||
|
"total_tokens": 550717,
|
||||||
|
"n_params": 2047683840
|
||||||
|
},
|
||||||
|
"test_loss_avg": 0.4076576465209474,
|
||||||
|
"test_loss_sum": 33328.45854896657,
|
||||||
|
"n_test": 282
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user