初始化项目，由ModelHub XC社区提供模型
Model: cs-552-2026-claude-bots/group_model Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
45
.ipynb_checkpoints/README-checkpoint.md
Normal file
45
.ipynb_checkpoints/README-checkpoint.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
base_model:
|
||||
- cs-552-2026-claude-bots/general_knowledge_model
|
||||
- cs-552-2026-claude-bots/safety_model
|
||||
- cs-552-2026-claude-bots/math_model
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# Untitled Model (1)
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge method.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [cs-552-2026-claude-bots/general_knowledge_model](https://huggingface.co/cs-552-2026-claude-bots/general_knowledge_model)
|
||||
* [cs-552-2026-claude-bots/safety_model](https://huggingface.co/cs-552-2026-claude-bots/safety_model)
|
||||
* [cs-552-2026-claude-bots/math_model](https://huggingface.co/cs-552-2026-claude-bots/math_model)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: cs-552-2026-claude-bots/math_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-claude-bots/general_knowledge_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-claude-bots/safety_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
merge_method: linear
|
||||
dtype: float16
|
||||
```
|
||||
12
.ipynb_checkpoints/mergekit_config-checkpoint.yml
Normal file
12
.ipynb_checkpoints/mergekit_config-checkpoint.yml
Normal file
@@ -0,0 +1,12 @@
|
||||
models:
|
||||
- model: cs-552-2026-claude-bots/math_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-claude-bots/general_knowledge_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
- model: cs-552-2026-claude-bots/safety_model
|
||||
parameters:
|
||||
weight: 1.0
|
||||
merge_method: linear
|
||||
dtype: float16
|
||||
149
README.md
Normal file
149
README.md
Normal file
@@ -0,0 +1,149 @@
|
||||
---
|
||||
base_model:
|
||||
- cs-552-2026-claude-bots/general_knowledge_model
|
||||
- cs-552-2026-claude-bots/safety_model
|
||||
- Qwen/Qwen3-1.7B
|
||||
- cs-552-2026-claude-bots/math_model
|
||||
- cs-552-2026-claude-bots/multilingual_model
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
|
||||
---
|
||||
# Group Model
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Method
|
||||
|
||||
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) as a base.
|
||||
|
||||
### Models Merged
|
||||
|
||||
The following models were included in the merge:
|
||||
* [cs-552-2026-claude-bots/general_knowledge_model](https://huggingface.co/cs-552-2026-claude-bots/general_knowledge_model)
|
||||
* [cs-552-2026-claude-bots/safety_model](https://huggingface.co/cs-552-2026-claude-bots/safety_model)
|
||||
* [cs-552-2026-claude-bots/math_model](https://huggingface.co/cs-552-2026-claude-bots/math_model)
|
||||
* [cs-552-2026-claude-bots/multilingual_model](https://huggingface.co/cs-552-2026-claude-bots/multilingual_model)
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
# TIES merge configuration for 4 specialized Qwen fine-tunes
|
||||
# Goal:
|
||||
# - Preserve strong domain expertise from each model
|
||||
# - Reduce destructive interference between skills
|
||||
# - Keep general reasoning stability from the base model
|
||||
#
|
||||
# Recommended for:
|
||||
# - Qwen2 / Qwen2.5 instruction-tuned variants
|
||||
# - Same architecture + same parameter count
|
||||
# - Same tokenizer + same base checkpoint lineage
|
||||
|
||||
models:
|
||||
# ---------------------------
|
||||
# Math specialist
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/math_model
|
||||
parameters:
|
||||
# High density because math capabilities are usually sparse
|
||||
# and easily lost during merging
|
||||
density:
|
||||
- filter: self_attn
|
||||
value: 0.72
|
||||
- filter: mlp
|
||||
value: 0.82
|
||||
|
||||
# Strong contribution in reasoning-heavy blocks
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 1.25
|
||||
- filter: mlp
|
||||
value: 1.15
|
||||
- value: 1.10
|
||||
|
||||
# ---------------------------
|
||||
# Knowledge / factual model
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/general_knowledge_model
|
||||
parameters:
|
||||
# Moderate density:
|
||||
# factual tuning tends to be more distributed
|
||||
density: 0.58
|
||||
|
||||
# Slightly lower than math to avoid overwriting reasoning
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 1.00
|
||||
- filter: mlp
|
||||
value: 0.95
|
||||
- value: 0.95
|
||||
|
||||
# ---------------------------
|
||||
# Multilingual specialist
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/multilingual_model
|
||||
parameters:
|
||||
# Language capabilities are often spread broadly,
|
||||
# so use reasonably high density
|
||||
density:
|
||||
- filter: embed_tokens
|
||||
value: 0.90
|
||||
- filter: self_attn
|
||||
value: 0.68
|
||||
- filter: mlp
|
||||
value: 0.62
|
||||
|
||||
# Stronger influence on embeddings and attention
|
||||
weight:
|
||||
- filter: embed_tokens
|
||||
value: 1.30
|
||||
- filter: self_attn
|
||||
value: 1.10
|
||||
- value: 1.00
|
||||
|
||||
# ---------------------------
|
||||
# Safety / alignment model
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/safety_model
|
||||
parameters:
|
||||
# Lower density prevents excessive refusals
|
||||
# while still preserving alignment behavior
|
||||
density: 0.34
|
||||
|
||||
# Important but intentionally constrained
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 0.82
|
||||
- filter: mlp
|
||||
value: 0.72
|
||||
- value: 0.75
|
||||
|
||||
merge_method: ties
|
||||
|
||||
# IMPORTANT:
|
||||
# Use the ORIGINAL shared pretrained base model
|
||||
# from which all four fine-tunes were derived.
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
|
||||
parameters:
|
||||
# Critical for TIES stability
|
||||
normalize: true
|
||||
|
||||
# Helps reduce memory usage and improves masking behavior
|
||||
int8_mask: true
|
||||
|
||||
# Trim very small parameter deltas
|
||||
# Good default for 4-way merges
|
||||
prune_threshold: 0.015
|
||||
|
||||
dtype: bfloat16
|
||||
|
||||
# Optional:
|
||||
# tokenizer_source: base
|
||||
# chat_template: auto
|
||||
```
|
||||
90
chat_template.jinja
Normal file
90
chat_template.jinja
Normal file
@@ -0,0 +1,90 @@
|
||||
{%- set enable_thinking = true %}
|
||||
{%- 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 %}
|
||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.9.0",
|
||||
"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": "4.51.0"
|
||||
}
|
||||
113
mergekit_config.yml
Normal file
113
mergekit_config.yml
Normal file
@@ -0,0 +1,113 @@
|
||||
# TIES merge configuration for 4 specialized Qwen fine-tunes
|
||||
# Goal:
|
||||
# - Preserve strong domain expertise from each model
|
||||
# - Reduce destructive interference between skills
|
||||
# - Keep general reasoning stability from the base model
|
||||
#
|
||||
# Recommended for:
|
||||
# - Qwen2 / Qwen2.5 instruction-tuned variants
|
||||
# - Same architecture + same parameter count
|
||||
# - Same tokenizer + same base checkpoint lineage
|
||||
|
||||
models:
|
||||
# ---------------------------
|
||||
# Math specialist
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/math_model
|
||||
parameters:
|
||||
# High density because math capabilities are usually sparse
|
||||
# and easily lost during merging
|
||||
density:
|
||||
- filter: self_attn
|
||||
value: 0.72
|
||||
- filter: mlp
|
||||
value: 0.82
|
||||
|
||||
# Strong contribution in reasoning-heavy blocks
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 1.25
|
||||
- filter: mlp
|
||||
value: 1.15
|
||||
- value: 1.10
|
||||
|
||||
# ---------------------------
|
||||
# Knowledge / factual model
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/general_knowledge_model
|
||||
parameters:
|
||||
# Moderate density:
|
||||
# factual tuning tends to be more distributed
|
||||
density: 0.58
|
||||
|
||||
# Slightly lower than math to avoid overwriting reasoning
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 1.00
|
||||
- filter: mlp
|
||||
value: 0.95
|
||||
- value: 0.95
|
||||
|
||||
# ---------------------------
|
||||
# Multilingual specialist
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/multilingual_model
|
||||
parameters:
|
||||
# Language capabilities are often spread broadly,
|
||||
# so use reasonably high density
|
||||
density:
|
||||
- filter: embed_tokens
|
||||
value: 0.90
|
||||
- filter: self_attn
|
||||
value: 0.68
|
||||
- filter: mlp
|
||||
value: 0.62
|
||||
|
||||
# Stronger influence on embeddings and attention
|
||||
weight:
|
||||
- filter: embed_tokens
|
||||
value: 1.30
|
||||
- filter: self_attn
|
||||
value: 1.10
|
||||
- value: 1.00
|
||||
|
||||
# ---------------------------
|
||||
# Safety / alignment model
|
||||
# ---------------------------
|
||||
- model: cs-552-2026-claude-bots/safety_model
|
||||
parameters:
|
||||
# Lower density prevents excessive refusals
|
||||
# while still preserving alignment behavior
|
||||
density: 0.34
|
||||
|
||||
# Important but intentionally constrained
|
||||
weight:
|
||||
- filter: self_attn
|
||||
value: 0.82
|
||||
- filter: mlp
|
||||
value: 0.72
|
||||
- value: 0.75
|
||||
|
||||
merge_method: ties
|
||||
|
||||
# IMPORTANT:
|
||||
# Use the ORIGINAL shared pretrained base model
|
||||
# from which all four fine-tunes were derived.
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
|
||||
parameters:
|
||||
# Critical for TIES stability
|
||||
normalize: true
|
||||
|
||||
# Helps reduce memory usage and improves masking behavior
|
||||
int8_mask: true
|
||||
|
||||
# Trim very small parameter deltas
|
||||
# Good default for 4-way merges
|
||||
prune_threshold: 0.015
|
||||
|
||||
dtype: bfloat16
|
||||
|
||||
# Optional:
|
||||
# tokenizer_source: base
|
||||
# chat_template: auto
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:417536711e095c42836913ebd0b4128231ab80364450c2e2175382dd280dba80
|
||||
size 4063515640
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- 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>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user