Clear v1 outputs (60 files) before uploading v2
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- README.md +0 -58
- chat_template.jinja +0 -61
- checkpoint-1000/chat_template.jinja +0 -61
- checkpoint-1000/config.json +0 -71
- checkpoint-1000/generation_config.json +0 -12
- checkpoint-1000/model.safetensors +0 -3
- checkpoint-1000/optimizer.bin +0 -3
- checkpoint-1000/pytorch_model_fsdp.bin +0 -3
- checkpoint-1000/rng_state_0.pth +0 -3
- checkpoint-1000/rng_state_1.pth +0 -3
- checkpoint-1000/scheduler.pt +0 -3
- checkpoint-1000/tokenizer.json +0 -3
- checkpoint-1000/tokenizer_config.json +0 -29
- checkpoint-1000/trainer_state.json +0 -0
- checkpoint-1000/training_args.bin +0 -3
- checkpoint-2000/chat_template.jinja +0 -61
- checkpoint-2000/config.json +0 -71
- checkpoint-2000/generation_config.json +0 -12
- checkpoint-2000/model.safetensors +0 -3
- checkpoint-2000/optimizer.bin +0 -3
- checkpoint-2000/pytorch_model_fsdp.bin +0 -3
- checkpoint-2000/rng_state_0.pth +0 -3
- checkpoint-2000/rng_state_1.pth +0 -3
- checkpoint-2000/scheduler.pt +0 -3
- checkpoint-2000/tokenizer.json +0 -3
- checkpoint-2000/tokenizer_config.json +0 -29
- checkpoint-2000/trainer_state.json +0 -0
- checkpoint-2000/training_args.bin +0 -3
- checkpoint-3000/chat_template.jinja +0 -61
- checkpoint-3000/config.json +0 -71
- checkpoint-3000/generation_config.json +0 -12
- checkpoint-3000/model.safetensors +0 -3
- checkpoint-3000/optimizer.bin +0 -3
- checkpoint-3000/pytorch_model_fsdp.bin +0 -3
- checkpoint-3000/rng_state_0.pth +0 -3
- checkpoint-3000/rng_state_1.pth +0 -3
- checkpoint-3000/scheduler.pt +0 -3
- checkpoint-3000/tokenizer.json +0 -3
- checkpoint-3000/tokenizer_config.json +0 -29
- checkpoint-3000/trainer_state.json +0 -0
- checkpoint-3000/training_args.bin +0 -3
- checkpoint-3948/chat_template.jinja +0 -61
- checkpoint-3948/config.json +0 -71
- checkpoint-3948/generation_config.json +0 -12
- checkpoint-3948/model.safetensors +0 -3
- checkpoint-3948/optimizer.bin +0 -3
- checkpoint-3948/pytorch_model_fsdp.bin +0 -3
- checkpoint-3948/rng_state_0.pth +0 -3
- checkpoint-3948/rng_state_1.pth +0 -3
- checkpoint-3948/scheduler.pt +0 -3
README.md
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
-
library_name: transformers
|
| 4 |
-
model_name: Qwen3-8B_n3000_math
|
| 5 |
-
tags:
|
| 6 |
-
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
-
- trl
|
| 9 |
-
licence: license
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
-
# Model Card for Qwen3-8B_n3000_math
|
| 13 |
-
|
| 14 |
-
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
| 15 |
-
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
-
|
| 17 |
-
## Quick start
|
| 18 |
-
|
| 19 |
-
```python
|
| 20 |
-
from transformers import pipeline
|
| 21 |
-
|
| 22 |
-
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
-
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
-
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
-
print(output["generated_text"])
|
| 26 |
-
```
|
| 27 |
-
|
| 28 |
-
## Training procedure
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
This model was trained with SFT.
|
| 35 |
-
|
| 36 |
-
### Framework versions
|
| 37 |
-
|
| 38 |
-
- TRL: 0.29.0
|
| 39 |
-
- Transformers: 5.5.3
|
| 40 |
-
- Pytorch: 2.8.0
|
| 41 |
-
- Datasets: 4.5.0
|
| 42 |
-
- Tokenizers: 0.22.2
|
| 43 |
-
|
| 44 |
-
## Citations
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
Cite TRL as:
|
| 49 |
-
|
| 50 |
-
```bibtex
|
| 51 |
-
@software{vonwerra2020trl,
|
| 52 |
-
title = {{TRL: Transformers Reinforcement Learning}},
|
| 53 |
-
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
| 54 |
-
license = {Apache-2.0},
|
| 55 |
-
url = {https://github.com/huggingface/trl},
|
| 56 |
-
year = {2020}
|
| 57 |
-
}
|
| 58 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "float32",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151662,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.5.3",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_sample": true,
|
| 3 |
-
"eos_token_id": [
|
| 4 |
-
151645,
|
| 5 |
-
151643
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 151662,
|
| 8 |
-
"temperature": 0.7,
|
| 9 |
-
"top_k": 20,
|
| 10 |
-
"top_p": 0.8,
|
| 11 |
-
"transformers_version": "5.5.3"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:16cf530a69292d5ebcdc898ff6e27f40e9fa97d07ec9a6fff92606a1cbec50f4
|
| 3 |
-
size 17645743048
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/optimizer.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ad09a9b1f9d56fb5e24fccb31bc61995bcb8aa26d3d4e5771bcd332a90d2d66e
|
| 3 |
-
size 32180124005
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/pytorch_model_fsdp.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cde7e1f8a53dcc9407e8636dd3c4261b755f26602abf7c70e6eb4291c93496bd
|
| 3 |
-
size 17645897996
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4dd7671ce88d469c49c0530724ac76b2306574002d1ecd1ca9294e41621fd96a
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3246ef1170ccca541a03b89ad6f20e01c51eb6834a2c2211c78c71c70f896879
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3e3184dc815b4354af3c63c9b5b618608d5206305b4414657ef8e0195f7ad089
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": false,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|fim_pad|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb9e429a6dba8782c1beb1411b31fa91f0c01ec6e0b1441e21d679f8a8b2c021
|
| 3 |
-
size 6225
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "float32",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151662,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.5.3",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_sample": true,
|
| 3 |
-
"eos_token_id": [
|
| 4 |
-
151645,
|
| 5 |
-
151643
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 151662,
|
| 8 |
-
"temperature": 0.7,
|
| 9 |
-
"top_k": 20,
|
| 10 |
-
"top_p": 0.8,
|
| 11 |
-
"transformers_version": "5.5.3"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1b1ce241be74f81ade1793d7d1184e1cf7ce2e9afe46f5dd9418012bd1861b43
|
| 3 |
-
size 17645743048
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/optimizer.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:07e07657f743306d7736d8218c799dfc731283d7dedfca7eb48d4dcc64c64623
|
| 3 |
-
size 32180124005
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/pytorch_model_fsdp.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:27df8f98b77baf9afbd9bdac0a9ff6cc9e53f4d44310a5d8c665d45656911b2e
|
| 3 |
-
size 17645897996
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7c70c34042f727a1ef06eb662d77f90fe87f01cf21415dce97c8cb4c779b5625
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": false,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|fim_pad|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb9e429a6dba8782c1beb1411b31fa91f0c01ec6e0b1441e21d679f8a8b2c021
|
| 3 |
-
size 6225
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "float32",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151662,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.5.3",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_sample": true,
|
| 3 |
-
"eos_token_id": [
|
| 4 |
-
151645,
|
| 5 |
-
151643
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 151662,
|
| 8 |
-
"temperature": 0.7,
|
| 9 |
-
"top_k": 20,
|
| 10 |
-
"top_p": 0.8,
|
| 11 |
-
"transformers_version": "5.5.3"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0a87a133eb5ec5af0878395bc45e179834b11224819f981211f70acdd015060b
|
| 3 |
-
size 17645743048
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/optimizer.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0ff8e5977667fc938b297528391c931889487050b2acf34a78a42a820912cd38
|
| 3 |
-
size 32180124005
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/pytorch_model_fsdp.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3023a52ce183c0d2cddf839ebf937f5047e153db9c651eb9f295b9a386e6b589
|
| 3 |
-
size 17645897996
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:61e957b4cd785256be4cb26eb03060ef689e1d58f1766d7f26ca36a62bec4994
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:550c54d430b44b77b0abe44c6e3ceba90a155305315c081b7616b35e2c18d1ce
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b07c9eca675fb8c47d0c01728c4ef879c66a752ffdace85e7e9feac32b48ac4b
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": false,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|fim_pad|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3000/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb9e429a6dba8782c1beb1411b31fa91f0c01ec6e0b1441e21d679f8a8b2c021
|
| 3 |
-
size 6225
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\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" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "float32",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151662,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.5.3",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_sample": true,
|
| 3 |
-
"eos_token_id": [
|
| 4 |
-
151645,
|
| 5 |
-
151643
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 151662,
|
| 8 |
-
"temperature": 0.7,
|
| 9 |
-
"top_k": 20,
|
| 10 |
-
"top_p": 0.8,
|
| 11 |
-
"transformers_version": "5.5.3"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e7db19800bbcf792dcb25dea9b5ae39f4e934a0d56f64ed6f74d7d89e87ae928
|
| 3 |
-
size 17645743048
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/optimizer.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:656d334c407ae1443fcaeda271d597e51249875fdde8e1a12a024812f6de73ab
|
| 3 |
-
size 32180124005
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/pytorch_model_fsdp.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:51d19fbc90bb938bf3c747a8b9c2b23f00398029d4ab146ca0ca0a0ea7d8885c
|
| 3 |
-
size 17645897996
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:61e957b4cd785256be4cb26eb03060ef689e1d58f1766d7f26ca36a62bec4994
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:550c54d430b44b77b0abe44c6e3ceba90a155305315c081b7616b35e2c18d1ce
|
| 3 |
-
size 14917
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-3948/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:deaab1725fa5d6abb332a09b31b7c4d93808c0289cb39a32cd5102547b98e285
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|