Text Generation
PEFT
Safetensors
English
lora
multi-agent
collaborative-learning
jca
qwen3
conversational
Instructions to use SJTUFreshman/collaborativelearning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SJTUFreshman/collaborativelearning with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B") model = PeftModel.from_pretrained(base_model, "SJTUFreshman/collaborativelearning") - Notebooks
- Google Colab
- Kaggle
Add a loadable root adapter and default loading entry point
Browse filesExpose the existing final MuSiQue Qwen3-1.7B SLS adapter at the root with matching tokenizer files. Preserve checkpoint paths and record root aliases in the manifest and checksum list.
- .gitattributes +1 -0
- README.md +12 -9
- SHA256SUMS +0 -0
- adapter_config.json +45 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +89 -0
- load_adapter.py +21 -4
- manifest.json +0 -0
- tokenizer.json +3 -0
- tokenizer_config.json +30 -0
.gitattributes
CHANGED
|
@@ -275,3 +275,4 @@ assets/figures/Figure1.pdf filter=lfs diff=lfs merge=lfs -text
|
|
| 275 |
assets/figures/Figure2.pdf filter=lfs diff=lfs merge=lfs -text
|
| 276 |
assets/figures/Figure4.pdf filter=lfs diff=lfs merge=lfs -text
|
| 277 |
assets/figures/Figure5.pdf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 275 |
assets/figures/Figure2.pdf filter=lfs diff=lfs merge=lfs -text
|
| 276 |
assets/figures/Figure4.pdf filter=lfs diff=lfs merge=lfs -text
|
| 277 |
assets/figures/Figure5.pdf filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -130,6 +130,8 @@ At each step, the current task state is processed by one model from the sliced-m
|
|
| 130 |
|
| 131 |
| Path | Contents |
|
| 132 |
| --- | --- |
|
|
|
|
|
|
|
| 133 |
| `<benchmark>/PD/<Qwen3-model>/<checkpoint>/` | Protocol distillation (SFT) adapters |
|
| 134 |
| `<benchmark>/SLS/<Qwen3-model>/<checkpoint>/` | Step-level supervision (RL) adapters |
|
| 135 |
| `assets/figures/` | Study figures and previews |
|
|
@@ -140,6 +142,8 @@ At each step, the current task state is processed by one model from the sliced-m
|
|
| 140 |
|
| 141 |
The release contains **233 surviving checkpoints across 29 model-stage groups**, approximately **41.39 GiB** including tokenizer assets and configuration. Each selected final training run retains all its surviving `checkpoint-*` exports and its `final` export. Some checkpoints place the adapter in a nested `policy_adapter/` directory, with the tokenizer in the parent directory. MultiPL-E 1.7B is PD-only.
|
| 142 |
|
|
|
|
|
|
|
| 143 |
Weights are byte-for-byte unchanged. Adapter configurations use the corresponding `Qwen/Qwen3-*` base-model IDs, and JSON metadata has local server paths normalized and credential fields removed. Baseline, ablation, and homogeneous-model weights are outside this release, as are optimizer/RNG states, pickled training arguments, and training data.
|
| 144 |
|
| 145 |
## 🚀 Quickstart
|
|
@@ -152,24 +156,23 @@ python -m pip install -U torch transformers peft accelerate huggingface_hub
|
|
| 152 |
|
| 153 |
### 2️⃣ Download and load one adapter
|
| 154 |
|
|
|
|
|
|
|
| 155 |
```python
|
| 156 |
-
from huggingface_hub import snapshot_download
|
| 157 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 158 |
-
from peft import PeftModel
|
| 159 |
|
| 160 |
repo_id = "SJTUFreshman/collaborativelearning"
|
| 161 |
-
|
| 162 |
-
snapshot = snapshot_download(repo_id, allow_patterns=[f"{subfolder}/*"])
|
| 163 |
-
adapter_path = f"{snapshot}/{subfolder}"
|
| 164 |
|
| 165 |
-
tokenizer = AutoTokenizer.from_pretrained(
|
| 166 |
base_model = AutoModelForCausalLM.from_pretrained(
|
| 167 |
-
|
| 168 |
)
|
| 169 |
-
model = PeftModel.from_pretrained(base_model,
|
| 170 |
```
|
| 171 |
|
| 172 |
-
Choose the matching base model recorded in `manifest.json`. For a nested `policy_adapter` checkpoint,
|
| 173 |
|
| 174 |
To download all published checkpoints:
|
| 175 |
|
|
|
|
| 130 |
|
| 131 |
| Path | Contents |
|
| 132 |
| --- | --- |
|
| 133 |
+
| `adapter_config.json`, `adapter_model.safetensors` | Default adapter: MuSiQue SLS, Qwen3-1.7B, `final` |
|
| 134 |
+
| `tokenizer.json`, `tokenizer_config.json`, `chat_template.jinja` | Tokenizer for the default adapter |
|
| 135 |
| `<benchmark>/PD/<Qwen3-model>/<checkpoint>/` | Protocol distillation (SFT) adapters |
|
| 136 |
| `<benchmark>/SLS/<Qwen3-model>/<checkpoint>/` | Step-level supervision (RL) adapters |
|
| 137 |
| `assets/figures/` | Study figures and previews |
|
|
|
|
| 142 |
|
| 143 |
The release contains **233 surviving checkpoints across 29 model-stage groups**, approximately **41.39 GiB** including tokenizer assets and configuration. Each selected final training run retains all its surviving `checkpoint-*` exports and its `final` export. Some checkpoints place the adapter in a nested `policy_adapter/` directory, with the tokenizer in the parent directory. MultiPL-E 1.7B is PD-only.
|
| 144 |
|
| 145 |
+
The repository root provides a directly loadable copy of `MuSiQue/SLS/Qwen3-1.7B/final`. It is one agent's adapter for that task, not a combined model for all benchmarks. Its five root files are byte-identical aliases of the checkpoint assets, adding no new trained checkpoint. All checkpoint subfolder paths remain available.
|
| 146 |
+
|
| 147 |
Weights are byte-for-byte unchanged. Adapter configurations use the corresponding `Qwen/Qwen3-*` base-model IDs, and JSON metadata has local server paths normalized and credential fields removed. Baseline, ablation, and homogeneous-model weights are outside this release, as are optimizer/RNG states, pickled training arguments, and training data.
|
| 148 |
|
| 149 |
## 🚀 Quickstart
|
|
|
|
| 156 |
|
| 157 |
### 2️⃣ Download and load one adapter
|
| 158 |
|
| 159 |
+
The default root adapter uses **Qwen3-1.7B** and the final **MuSiQue SLS** checkpoint:
|
| 160 |
+
|
| 161 |
```python
|
|
|
|
| 162 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 163 |
+
from peft import PeftConfig, PeftModel
|
| 164 |
|
| 165 |
repo_id = "SJTUFreshman/collaborativelearning"
|
| 166 |
+
adapter_config = PeftConfig.from_pretrained(repo_id)
|
|
|
|
|
|
|
| 167 |
|
| 168 |
+
tokenizer = AutoTokenizer.from_pretrained(repo_id)
|
| 169 |
base_model = AutoModelForCausalLM.from_pretrained(
|
| 170 |
+
adapter_config.base_model_name_or_path, torch_dtype="auto", device_map="auto"
|
| 171 |
)
|
| 172 |
+
model = PeftModel.from_pretrained(base_model, repo_id)
|
| 173 |
```
|
| 174 |
|
| 175 |
+
For another checkpoint, use [load_adapter.py](load_adapter.py) with its subfolder, for example `load_adapter("MATH/SLS/Qwen3-4B/final")`. Calling `load_adapter()` without a subfolder loads only the five root adapter/tokenizer files. Choose the matching base model recorded in `manifest.json`. For a nested `policy_adapter` checkpoint, the helper loads the adapter from that directory and the tokenizer from its parent. The frozen base-model weights are downloaded from the original Qwen repositories.
|
| 176 |
|
| 177 |
To download all published checkpoints:
|
| 178 |
|
SHA256SUMS
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
adapter_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-1.7B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 64,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"k_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"q_proj"
|
| 37 |
+
],
|
| 38 |
+
"target_parameters": null,
|
| 39 |
+
"task_type": "CAUSAL_LM",
|
| 40 |
+
"trainable_token_indices": null,
|
| 41 |
+
"use_bdlora": null,
|
| 42 |
+
"use_dora": false,
|
| 43 |
+
"use_qalora": false,
|
| 44 |
+
"use_rslora": false
|
| 45 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d148e71ce3b277ecc47fb67b736e0c5d57c3f5e7121b45f7d5a65d9d4bed233
|
| 3 |
+
size 102790608
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- 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>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
load_adapter.py
CHANGED
|
@@ -7,10 +7,27 @@ from peft import PeftModel
|
|
| 7 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 8 |
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
repo_id = 'SJTUFreshman/collaborativelearning'
|
|
|
|
|
|
|
|
|
|
| 12 |
tokenizer_folder = str(Path(subfolder).parent).replace('\\', '/') if subfolder.endswith('/policy_adapter') else subfolder
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
adapter_dir = Path(snapshot)/subfolder
|
| 15 |
config = json.loads((adapter_dir/'adapter_config.json').read_text())
|
| 16 |
tokenizer = AutoTokenizer.from_pretrained(Path(snapshot)/tokenizer_folder)
|
|
@@ -21,8 +38,8 @@ def load_adapter(subfolder, revision=None):
|
|
| 21 |
|
| 22 |
if __name__ == '__main__':
|
| 23 |
parser = argparse.ArgumentParser()
|
| 24 |
-
parser.add_argument('subfolder')
|
| 25 |
parser.add_argument('--revision')
|
| 26 |
args = parser.parse_args()
|
| 27 |
model, tokenizer = load_adapter(args.subfolder, args.revision)
|
| 28 |
-
print('Loaded', args.subfolder)
|
|
|
|
| 7 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 8 |
|
| 9 |
|
| 10 |
+
ROOT_FILES = [
|
| 11 |
+
'adapter_config.json',
|
| 12 |
+
'adapter_model.safetensors',
|
| 13 |
+
'tokenizer.json',
|
| 14 |
+
'tokenizer_config.json',
|
| 15 |
+
'chat_template.jinja',
|
| 16 |
+
]
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def load_adapter(subfolder=None, revision=None):
|
| 20 |
+
"""Load the root MuSiQue 1.7B SLS adapter, or a checkpoint subfolder."""
|
| 21 |
repo_id = 'SJTUFreshman/collaborativelearning'
|
| 22 |
+
subfolder = (subfolder or '').replace('\\', '/').strip('/')
|
| 23 |
+
if subfolder == '.':
|
| 24 |
+
subfolder = ''
|
| 25 |
tokenizer_folder = str(Path(subfolder).parent).replace('\\', '/') if subfolder.endswith('/policy_adapter') else subfolder
|
| 26 |
+
patterns = (
|
| 27 |
+
[subfolder+'/*', tokenizer_folder+'/tokenizer*', tokenizer_folder+'/chat_template.jinja', tokenizer_folder+'/special_tokens_map.json']
|
| 28 |
+
if subfolder else ROOT_FILES
|
| 29 |
+
)
|
| 30 |
+
snapshot = snapshot_download(repo_id, revision=revision, allow_patterns=patterns)
|
| 31 |
adapter_dir = Path(snapshot)/subfolder
|
| 32 |
config = json.loads((adapter_dir/'adapter_config.json').read_text())
|
| 33 |
tokenizer = AutoTokenizer.from_pretrained(Path(snapshot)/tokenizer_folder)
|
|
|
|
| 38 |
|
| 39 |
if __name__ == '__main__':
|
| 40 |
parser = argparse.ArgumentParser()
|
| 41 |
+
parser.add_argument('subfolder', nargs='?', help='Checkpoint directory; default: root MuSiQue 1.7B SLS adapter')
|
| 42 |
parser.add_argument('--revision')
|
| 43 |
args = parser.parse_args()
|
| 44 |
model, tokenizer = load_adapter(args.subfolder, args.revision)
|
| 45 |
+
print('Loaded', args.subfolder or 'root (MuSiQue/SLS/Qwen3-1.7B/final)')
|
manifest.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9015c7b9bcc5ac57906c55460048b82b9dfcdef34eb1f781c079da50de99f3d0
|
| 3 |
+
size 11422749
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|