初始化项目，由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemistry-RLRT-TR Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.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
|
||||||
|
results/training_score.png filter=lfs diff=lfs merge=lfs -text
|
||||||
66
README.md
Normal file
66
README.md
Normal file
@@ -0,0 +1,66 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-4B
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- qwen3
|
||||||
|
- reinforcement-learning
|
||||||
|
- trust-region
|
||||||
|
- sdpo
|
||||||
|
- srpo
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen3-4B-Chemistry-RLRT-TR
|
||||||
|
|
||||||
|
This repository contains the Qwen3-4B `Chemistry` `RLRT-TR` run trained with batch size 32.
|
||||||
|
|
||||||
|
The repository root contains the **best validation checkpoint** (`global_step_100`), selected by validation `mean@16`.
|
||||||
|
The best validation checkpoint is also the final checkpoint, so the repository root is both best and last.
|
||||||
|
|
||||||
|
## Performance
|
||||||
|
|
||||||
|
| Dataset | Method | Base model | Train batch size | Best val mean@16 | Best checkpoint | Final val mean@16 | Final checkpoint |
|
||||||
|
|---|---|---|---:|---:|---:|---:|---:|
|
||||||
|
| Chemistry | RLRT-TR | Qwen3-4B | 32 | 59.17% | 100 | 59.17% | 100 |
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Raw result files:
|
||||||
|
|
||||||
|
- `results/validation_mean16.csv`
|
||||||
|
- `results/training_scores.csv`
|
||||||
|
- `artifacts/config.yaml`
|
||||||
|
- `artifacts/wandb-summary.json`
|
||||||
|
|
||||||
|
## Training Hyperparameters
|
||||||
|
|
||||||
|
| Hyperparameter | Value |
|
||||||
|
|---|---:|
|
||||||
|
| Base model | `Qwen/Qwen3-4B` |
|
||||||
|
| Method | `RLRT-TR` |
|
||||||
|
| Train batch size | `32` |
|
||||||
|
| Train max samples | `3200` |
|
||||||
|
| Total training steps | `100` |
|
||||||
|
| Save frequency | `10` |
|
||||||
|
| Test frequency | `10` |
|
||||||
|
| Teacher regularization | `trust-region` |
|
||||||
|
| Teacher update rate | `0.1` |
|
||||||
|
| Rollout samples per prompt | `8` |
|
||||||
|
| Validation samples per prompt | `16` |
|
||||||
|
| Learning rate | `1e-6` |
|
||||||
|
| vLLM GPU memory utilization | `0.8` |
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
repo_id = "SeongryongJung/Qwen3-4B-Chemistry-RLRT-TR"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
repo_id,
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
)
|
||||||
|
```
|
||||||
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
|
||||||
|
}
|
||||||
18
artifacts/config.yaml
Normal file
18
artifacts/config.yaml
Normal file
@@ -0,0 +1,18 @@
|
|||||||
|
{
|
||||||
|
"experiment_name": "qwen3gen-chemistry-RLRT_TR-Qwen-Qwen3-4B-mbs8-tr0.1-decay0-train32-rollout8-lr1e-6-vllm0.8-epsw0.5",
|
||||||
|
"base_model": "Qwen/Qwen3-4B",
|
||||||
|
"dataset": "chemistry",
|
||||||
|
"method": "RLRT-TR",
|
||||||
|
"checkpoint_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/chemistry/qwen3gen-chemistry-RLRT_TR-Qwen-Qwen3-4B-mbs8-tr0.1-decay0-train32-rollout8-lr1e-6-vllm0.8-epsw0.5",
|
||||||
|
"best_checkpoint": "global_step_100",
|
||||||
|
"last_checkpoint": "global_step_100",
|
||||||
|
"train_batch_size": 32,
|
||||||
|
"train_max_samples": 3200,
|
||||||
|
"teacher_regularization": "trust-region",
|
||||||
|
"teacher_update_rate": 0.1,
|
||||||
|
"rollout_n": 8,
|
||||||
|
"validation_n": 16,
|
||||||
|
"learning_rate": "1e-6",
|
||||||
|
"vllm_gpu_memory_utilization": 0.8,
|
||||||
|
"command_args": ""
|
||||||
|
}
|
||||||
1116
artifacts/output.log
Normal file
1116
artifacts/output.log
Normal file
File diff suppressed because it is too large
Load Diff
109
artifacts/wandb-metadata.json
Normal file
109
artifacts/wandb-metadata.json
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
{
|
||||||
|
"os": "Linux-6.8.0-71-generic-x86_64-with-glibc2.36",
|
||||||
|
"python": "CPython 3.12.13",
|
||||||
|
"startedAt": "2026-07-07T09:49:55.356742Z",
|
||||||
|
"args": [
|
||||||
|
"--node-ip-address=198.19.44.212",
|
||||||
|
"--node-manager-port=42063",
|
||||||
|
"--object-store-name=/tmp/ray_q3g_chemistry_rlrt_tr_Qwen3_4B/session_2026-07-07_09-47-55_247411_3311754/sockets/plasma_store",
|
||||||
|
"--raylet-name=/tmp/ray_q3g_chemistry_rlrt_tr_Qwen3_4B/session_2026-07-07_09-47-55_247411_3311754/sockets/raylet",
|
||||||
|
"--redis-address=None",
|
||||||
|
"--metrics-agent-port=53325",
|
||||||
|
"--logging-rotate-bytes=536870912",
|
||||||
|
"--logging-rotate-backup-count=5",
|
||||||
|
"--runtime-env-agent-port=49561",
|
||||||
|
"--gcs-address=198.19.44.212:59525",
|
||||||
|
"--session-name=session_2026-07-07_09-47-55_247411_3311754",
|
||||||
|
"--temp-dir=/tmp/ray_q3g_chemistry_rlrt_tr_Qwen3_4B",
|
||||||
|
"--webui=",
|
||||||
|
"--cluster-id=f57dd9ada7f96029e4b4ab6be828b0216fb599d864b584e4d301a488",
|
||||||
|
"--startup-token=32",
|
||||||
|
"--worker-launch-time-ms=1783417678762",
|
||||||
|
"--node-id=b3697bb10a4bde39e123b02833b464511dfb63d91161ab1941efdec2",
|
||||||
|
"--runtime-env-hash=1347060993"
|
||||||
|
],
|
||||||
|
"program": "/mnt/mole/SDPO/L2T/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||||
|
"codePath": ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||||
|
"codePathLocal": ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||||
|
"git": {
|
||||||
|
"remote": "https://github.com/jungseongryong/L2T.git",
|
||||||
|
"commit": "e8dabdc5a612ea73ece3fe796283fb3b85543235"
|
||||||
|
},
|
||||||
|
"email": "jungsr1116@cau.ac.kr",
|
||||||
|
"root": "/mnt/mole/SDPO/L2T",
|
||||||
|
"host": "mole-workspace-rw",
|
||||||
|
"executable": "/mnt/mole/SDPO/L2T/.venv/bin/python",
|
||||||
|
"cpu_count": 64,
|
||||||
|
"cpu_count_logical": 128,
|
||||||
|
"gpu": "NVIDIA H200",
|
||||||
|
"gpu_count": 8,
|
||||||
|
"disk": {
|
||||||
|
"/": {
|
||||||
|
"total": "46086056050688",
|
||||||
|
"used": "24274080555008"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"memory": {
|
||||||
|
"total": "2163980390400"
|
||||||
|
},
|
||||||
|
"gpu_nvidia": [
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-c0451621-891c-7169-976d-71d81958db34"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-e2a29dfa-7dad-6cd7-fb05-79d0060f27f0"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-d69bb741-f2a7-a375-7f56-5c0d09d797b2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-1bbbea1e-7541-3126-1bfc-51b43a67577e"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-6e0055af-452d-3f46-ce21-0c71e347a608"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-317fdb5b-b280-71d8-398e-a843ad897437"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-f19d8161-d2dd-49a1-dcb8-5c341b5e4514"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "NVIDIA H200",
|
||||||
|
"memoryTotal": "150754820096",
|
||||||
|
"cudaCores": 16896,
|
||||||
|
"architecture": "Hopper",
|
||||||
|
"uuid": "GPU-961f5ebf-4bf8-6855-828b-c065af57b87c"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"cudaVersion": "13.0",
|
||||||
|
"writerId": "fltolk325cjtvo6eedi9e8ma3foc43yp"
|
||||||
|
}
|
||||||
1
artifacts/wandb-summary.json
Normal file
1
artifacts/wandb-summary.json
Normal file
File diff suppressed because one or more lines are too long
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": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"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": true,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "4.57.1"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:20fdc52ed9f3ed01c13989eb61702ee936e6755917cd2633fd9e4e6ba1cc0811
|
||||||
|
size 4962027264
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:12304934bdc1d2e452d39068c7720bc478e7533bbe29a6a982b27442684f94c3
|
||||||
|
size 3860867248
|
||||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 4411424256,
|
||||||
|
"total_size": 8822848512
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00001-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
results/training_score.png
Normal file
3
results/training_score.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:71ccc08d4675905705e178b45e3b5b05ffd6e77b35e5efc39d6bb287bb19a9ca
|
||||||
|
size 138388
|
||||||
91
results/training_scores.csv
Normal file
91
results/training_scores.csv
Normal file
@@ -0,0 +1,91 @@
|
|||||||
|
step,critic_score_mean
|
||||||
|
1,0.58203125
|
||||||
|
2,0.36328125
|
||||||
|
3,0.4765625
|
||||||
|
4,0.32421875
|
||||||
|
5,0.4765625
|
||||||
|
6,0.46484375
|
||||||
|
7,0.37109375
|
||||||
|
8,0.53125
|
||||||
|
9,0.3671875
|
||||||
|
11,0.44921875
|
||||||
|
12,0.5390625
|
||||||
|
13,0.421875
|
||||||
|
14,0.41796875
|
||||||
|
15,0.484375
|
||||||
|
16,0.45703125
|
||||||
|
17,0.35546875
|
||||||
|
18,0.40234375
|
||||||
|
19,0.5390625
|
||||||
|
21,0.375
|
||||||
|
22,0.32421875
|
||||||
|
23,0.55078125
|
||||||
|
24,0.56640625
|
||||||
|
25,0.43359375
|
||||||
|
26,0.5546875
|
||||||
|
27,0.44921875
|
||||||
|
28,0.53515625
|
||||||
|
29,0.36328125
|
||||||
|
31,0.5625
|
||||||
|
32,0.5078125
|
||||||
|
33,0.47265625
|
||||||
|
34,0.48828125
|
||||||
|
35,0.4453125
|
||||||
|
36,0.51953125
|
||||||
|
37,0.41015625
|
||||||
|
38,0.4765625
|
||||||
|
39,0.48046875
|
||||||
|
41,0.35546875
|
||||||
|
42,0.40625
|
||||||
|
43,0.484375
|
||||||
|
44,0.61328125
|
||||||
|
45,0.578125
|
||||||
|
46,0.40234375
|
||||||
|
47,0.484375
|
||||||
|
48,0.41015625
|
||||||
|
49,0.5546875
|
||||||
|
51,0.640625
|
||||||
|
52,0.4375
|
||||||
|
53,0.59375
|
||||||
|
54,0.34765625
|
||||||
|
55,0.55859375
|
||||||
|
56,0.45703125
|
||||||
|
57,0.46875
|
||||||
|
58,0.50390625
|
||||||
|
59,0.4375
|
||||||
|
61,0.51953125
|
||||||
|
62,0.5078125
|
||||||
|
63,0.53515625
|
||||||
|
64,0.6328125
|
||||||
|
65,0.5859375
|
||||||
|
66,0.5390625
|
||||||
|
67,0.5703125
|
||||||
|
68,0.3359375
|
||||||
|
69,0.5859375
|
||||||
|
71,0.54296875
|
||||||
|
72,0.56640625
|
||||||
|
73,0.5703125
|
||||||
|
74,0.52734375
|
||||||
|
75,0.6875
|
||||||
|
76,0.55859375
|
||||||
|
77,0.59765625
|
||||||
|
78,0.578125
|
||||||
|
79,0.47265625
|
||||||
|
81,0.453125
|
||||||
|
82,0.61328125
|
||||||
|
83,0.48828125
|
||||||
|
84,0.58203125
|
||||||
|
85,0.6484375
|
||||||
|
86,0.4375
|
||||||
|
87,0.3984375
|
||||||
|
88,0.53515625
|
||||||
|
89,0.5625
|
||||||
|
91,0.45703125
|
||||||
|
92,0.546875
|
||||||
|
93,0.6875
|
||||||
|
94,0.64453125
|
||||||
|
95,0.59375
|
||||||
|
96,0.5078125
|
||||||
|
97,0.48046875
|
||||||
|
98,0.4609375
|
||||||
|
99,0.4921875
|
||||||
|
11
results/validation_mean16.csv
Normal file
11
results/validation_mean16.csv
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
step,val_mean16
|
||||||
|
10,0.442261904762
|
||||||
|
20,0.490773809524
|
||||||
|
30,0.488392857143
|
||||||
|
40,0.514880952381
|
||||||
|
50,0.530654761905
|
||||||
|
60,0.527678571429
|
||||||
|
70,0.555654761905
|
||||||
|
80,0.560416666667
|
||||||
|
90,0.576488095238
|
||||||
|
100,0.591666666667
|
||||||
|
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
|
||||||
|
}
|
||||||
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