初始化项目，由ModelHub XC社区提供模型
Model: mohar07/qwen3-0.6b-kg-triplets 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
|
||||
qwen3-0.6b.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
59
Modelfile
Normal file
59
Modelfile
Normal file
@@ -0,0 +1,59 @@
|
||||
|
||||
FROM qwen3-0.6b.F16.gguf
|
||||
TEMPLATE """{{- if .Messages }}
|
||||
{{- if or .System .Tools }}<|im_start|>system
|
||||
{{- if .System }}
|
||||
{{ .System }}
|
||||
{{- end }}
|
||||
{{- if .Tools }}
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{{- range .Tools }}
|
||||
{"type": "function", "function": {{ .Function }}}
|
||||
{{- end }}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- range $i, $_ := .Messages }}
|
||||
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||
{{- if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ if .Content }}{{ .Content }}
|
||||
{{- else if .ToolCalls }}<tool_call>
|
||||
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||
{{ end }}</tool_call>
|
||||
{{- end }}{{ if not $last }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||
<tool_response>
|
||||
{{ .Content }}
|
||||
</tool_response><|im_end|>
|
||||
{{ end }}
|
||||
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER stop "<|im_start|>"
|
||||
PARAMETER temperature 0.6
|
||||
PARAMETER min_p 0.0
|
||||
PARAMETER top_k 20
|
||||
PARAMETER top_p 0.95
|
||||
PARAMETER repeat_penalty 1
|
||||
383
README.md
Normal file
383
README.md
Normal file
@@ -0,0 +1,383 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
base_model: unsloth/qwen3-0.6b
|
||||
tags:
|
||||
- qwen3
|
||||
- lora
|
||||
- knowledge-graph
|
||||
- relation-extraction
|
||||
- information-extraction
|
||||
- graph-rag
|
||||
- triplet-extraction
|
||||
- structured-generation
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# Qwen3-0.6B-KG-Triplets
|
||||
|
||||
Qwen3-0.6B-KG-Triplets is a LoRA finetuned version of Qwen3-0.6B specialized for ontology-constrained knowledge graph extraction.
|
||||
|
||||
Given a passage of text, the model generates structured triplets in the form:
|
||||
|
||||
```
|
||||
source -> relation -> target
|
||||
```
|
||||
|
||||
where:
|
||||
|
||||
- `"source"` contains an entity title and type
|
||||
- `"relation"` contains a relation type and confidence weight
|
||||
- `"target"` contains an entity title and type
|
||||
|
||||
The output is designed for direct ingestion into graph databases and GraphRAG pipelines with minimal post-processing.
|
||||
|
||||
---
|
||||
|
||||
## Motivation
|
||||
|
||||
Most instruction-tuned LLMs can extract entities and relations, but their outputs are difficult to ingest directly into graph databases because of:
|
||||
|
||||
- inconsistent entity naming
|
||||
- out-of-schema relations
|
||||
- poorly calibrated confidence scores
|
||||
- inconsistent JSON formatting
|
||||
|
||||
This model was finetuned specifically to produce:
|
||||
|
||||
- ontology-constrained outputs
|
||||
- normalized entity names
|
||||
- calibrated relation confidence weights
|
||||
- graph-ingestable JSON
|
||||
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
| Property | Value |
|
||||
|---|---|
|
||||
| Base Model | unsloth/qwen3-0.6b |
|
||||
| Finetuning | LoRA |
|
||||
| Rank (r) | 32 |
|
||||
| Alpha | 32 |
|
||||
| Context Length | 2048 |
|
||||
| Epochs | 5 |
|
||||
| Optimizer | AdamW 8-bit |
|
||||
| Framework | Unsloth + TRL |
|
||||
| Training Type | Instruction Finetuning |
|
||||
| License | MIT |
|
||||
|
||||
---
|
||||
|
||||
## Training Configuration
|
||||
|
||||
```python
|
||||
model = FastLanguageModel.get_peft_model(
|
||||
model,
|
||||
r=32,
|
||||
target_modules=[
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
],
|
||||
lora_alpha=32,
|
||||
lora_dropout=0,
|
||||
bias="none",
|
||||
use_gradient_checkpointing="unsloth",
|
||||
)
|
||||
```
|
||||
|
||||
| Parameter | Value |
|
||||
|---|---|
|
||||
| Batch size | 2 |
|
||||
| Gradient accumulation | 4 |
|
||||
| Learning rate | 5e-5 |
|
||||
| Epochs | 5 |
|
||||
| Warmup steps | 50 |
|
||||
| Max sequence length | 2048 |
|
||||
| Optimizer | AdamW 8-bit |
|
||||
| Seed | 42 |
|
||||
|
||||
---
|
||||
|
||||
## Dataset
|
||||
|
||||
The model was trained on a custom instruction dataset for structured knowledge graph extraction.
|
||||
|
||||
### Corpus Sources
|
||||
|
||||
- Wikipedia
|
||||
- arXiv papers
|
||||
|
||||
### Dataset Statistics
|
||||
|
||||
| Split | Examples |
|
||||
|---|---|
|
||||
| Train | 2575 |
|
||||
| Validation | 75 |
|
||||
| Test | 700 |
|
||||
| **Total** | **3350** |
|
||||
|
||||
Additional properties:
|
||||
|
||||
- 20 ontology relations
|
||||
- 15% hard negatives in training
|
||||
- Entity-level train/test decontamination
|
||||
- Curriculum ordering (easy → hard)
|
||||
- Zero schema errors
|
||||
|
||||
---
|
||||
|
||||
## Relation Schema
|
||||
|
||||
The model predicts only the following ontology:
|
||||
|
||||
```
|
||||
implements
|
||||
trained_on
|
||||
evaluates
|
||||
part_of
|
||||
introduces
|
||||
extends
|
||||
depends_on
|
||||
contrasts_with
|
||||
applied_to
|
||||
measured_by
|
||||
founded_by
|
||||
developed_by
|
||||
defined_as
|
||||
consists_of
|
||||
is_type_of
|
||||
based_on
|
||||
used_for
|
||||
created_by
|
||||
located_in
|
||||
predecessor_of
|
||||
```
|
||||
|
||||
Relations outside this ontology are intentionally not generated.
|
||||
|
||||
---
|
||||
|
||||
## Dataset Creation Pipeline
|
||||
|
||||
The training corpus was built using a multi-stage pipeline:
|
||||
|
||||
1. Corpus collection from Wikipedia and arXiv
|
||||
2. Language and quality filtering
|
||||
3. MinHash deduplication
|
||||
4. LLM triplet generation using DeepSeek V4-Flash
|
||||
5. Schema validation
|
||||
6. Semantic validation
|
||||
7. Hard negative generation
|
||||
8. Curriculum ordering
|
||||
9. Entity-level train/test decontamination
|
||||
10. Train / Validation / Test split
|
||||
|
||||
---
|
||||
|
||||
## Training Example
|
||||
|
||||
Input:
|
||||
|
||||
```json
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Extract knowledge graph triplets..."
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"source": {
|
||||
"title": "September",
|
||||
"type": "entity"
|
||||
},
|
||||
"relation": {
|
||||
"type": "part_of",
|
||||
"weight": 0.92
|
||||
},
|
||||
"target": {
|
||||
"title": "Gregorian calendar",
|
||||
"type": "entity"
|
||||
}
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
"title": "September",
|
||||
"type": "entity"
|
||||
},
|
||||
"relation": {
|
||||
"type": "defined_as",
|
||||
"weight": 0.92
|
||||
},
|
||||
"target": {
|
||||
"title": "ninth month",
|
||||
"type": "concept"
|
||||
}
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Evaluation
|
||||
|
||||
Evaluation was performed using a custom triplet extraction benchmark with Hungarian bipartite matching alignment on 700 held-out entries.
|
||||
|
||||
### Metrics
|
||||
|
||||
| Metric | Score | Weight |
|
||||
|---|---|---|
|
||||
| Schema score | 1.000 | 0.30 |
|
||||
| Entity F1 | 0.179 | 0.25 |
|
||||
| Relation accuracy | 0.680 | 0.20 |
|
||||
| Grounding | 0.969 | 0.15 |
|
||||
| Weight score | 0.526 | 0.10 |
|
||||
| Triplet F1 *(info only)* | 0.122 | — |
|
||||
| Type agreement *(info only)* | 0.854 | — |
|
||||
| Hallucination rate | 0.033 | — |
|
||||
|
||||
**Composite Score: 0.6583**
|
||||
|
||||
---
|
||||
|
||||
## What Finetuning Fixed
|
||||
|
||||
Finetuning addressed three major failure modes of the base model.
|
||||
|
||||
### 1. Entity Normalization
|
||||
|
||||
Input passage:
|
||||
|
||||
> *Studies of the Cambrian period document the rapid diversification of animal life and the emergence of most major animal phyla, with some researchers proposing that a celestial body impact may have triggered the extinction events that preceded this radiation.*
|
||||
|
||||
Base entity title extracted:
|
||||
|
||||
```
|
||||
After a thorough research on the circumstantial changes and the great evolution of life in the Cambrian period
|
||||
```
|
||||
|
||||
Finetuned entity title extracted:
|
||||
|
||||
```
|
||||
Celestial body impact hypothesis
|
||||
```
|
||||
|
||||
The finetuned model learns reusable and atomic graph nodes rather than copying passage fragments.
|
||||
|
||||
---
|
||||
|
||||
### 2. Schema Adherence
|
||||
|
||||
Base relations generated:
|
||||
|
||||
```
|
||||
released
|
||||
benefited_from
|
||||
```
|
||||
|
||||
Finetuned relations generated:
|
||||
|
||||
```
|
||||
based_on
|
||||
used_for
|
||||
applied_to
|
||||
introduces
|
||||
```
|
||||
|
||||
All generated relations belong to the predefined ontology.
|
||||
|
||||
---
|
||||
|
||||
### 3. Confidence Calibration
|
||||
|
||||
Base weights:
|
||||
|
||||
```
|
||||
0.8
|
||||
0.8
|
||||
0.8
|
||||
0.8
|
||||
```
|
||||
|
||||
Finetuned weights:
|
||||
|
||||
```
|
||||
0.23
|
||||
0.41
|
||||
0.59
|
||||
0.77
|
||||
```
|
||||
|
||||
The model learns meaningful confidence distributions where stronger relations receive higher scores.
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
|
||||
This model is intended for:
|
||||
|
||||
- Knowledge Graph Construction
|
||||
- GraphRAG pipelines
|
||||
- Structured Information Extraction
|
||||
- Entity-Relation Extraction
|
||||
- Automated KG population
|
||||
- Document-to-Graph conversion
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
While the model demonstrates strong schema adherence and grounding, several limitations remain.
|
||||
|
||||
**Shallow Entity Abstraction**
|
||||
|
||||
The model favors concise and reusable entities but may miss deeper semantic abstractions or hierarchical entity relationships.
|
||||
|
||||
**Limited Recall**
|
||||
|
||||
The model prioritizes schema correctness and grounded extraction over exhaustive triplet recall. Entity F1 of 0.179 reflects strict Hungarian-matching alignment on a 20-relation ontology-constrained task; recall is intentionally traded for precision and schema adherence.
|
||||
|
||||
**English-Centric Training**
|
||||
|
||||
Training was primarily conducted on English Wikipedia and arXiv passages.
|
||||
|
||||
**Ontology Constrained**
|
||||
|
||||
Only the predefined 20 relation types are supported.
|
||||
|
||||
**Model Size Constraints**
|
||||
|
||||
Despite the relatively small size (0.6B parameters) and a modest training corpus (~3K examples), the model learns stable ontology-constrained extraction behavior. Larger models may achieve deeper entity understanding and broader relation coverage.
|
||||
|
||||
---
|
||||
|
||||
## Repository
|
||||
|
||||
Evaluation Pipeline: https://github.com/mohar-xe/HGR-finetuned-model-evaluation-pipeline
|
||||
|
||||
Model: https://huggingface.co/mohar07/qwen3-0.6b-kg-triplets
|
||||
|
||||
---
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{das2026qwenkgtriplets,
|
||||
title={Qwen3-0.6B-KG-Triplets},
|
||||
author={Mohar Das},
|
||||
year={2026},
|
||||
publisher={Hugging Face},
|
||||
url={https://huggingface.co/mohar07/qwen3-0.6b-kg-triplets}
|
||||
}
|
||||
```
|
||||
52
adapter_config.json
Normal file
52
adapter_config.json
Normal file
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": {
|
||||
"base_model_class": "Qwen3ForCausalLM",
|
||||
"parent_library": "transformers.models.qwen3.modeling_qwen3",
|
||||
"unsloth_fixed": true
|
||||
},
|
||||
"base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 32,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 32,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
adapter_model.safetensors
Normal file
3
adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5d63d109bc039634570b29b4deff16253d9889bca49c27407084fd5f9b00fb32
|
||||
size 80792456
|
||||
99
chat_template.jinja
Normal file
99
chat_template.jinja
Normal file
@@ -0,0 +1,99 @@
|
||||
{%- 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 forward_message in messages %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- set message = messages[index] %}
|
||||
{%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
|
||||
{%- set tool_start = '<tool_response>' %}
|
||||
{%- set tool_start_length = tool_start|length %}
|
||||
{%- set start_of_message = current_content[:tool_start_length] %}
|
||||
{%- set tool_end = '</tool_response>' %}
|
||||
{%- set tool_end_length = tool_end|length %}
|
||||
{%- set start_pos = (current_content|length) - tool_end_length %}
|
||||
{%- if start_pos < 0 %}
|
||||
{%- set start_pos = 0 %}
|
||||
{%- endif %}
|
||||
{%- set end_of_message = current_content[start_pos:] %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
|
||||
{%- set content = m_content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in m_content %}
|
||||
{%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
|
||||
{%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
|
||||
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
|
||||
{{- '<|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' }}
|
||||
{{- message.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 %}
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"torch_dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"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": 151669,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.5.10",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 40960,
|
||||
"pad_token_id": 151669,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9f8ce2716b3e13ef963cc34daa5064282b1989b4d3d8f0726a4cb41851f8b32
|
||||
size 1192135096
|
||||
3
qwen3-0.6b.F16.gguf
Normal file
3
qwen3-0.6b.F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e3a444995e614ad66c569346811d6315591b5529ae891022221e49b8de97a26
|
||||
size 1198182976
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
|
||||
size 11423114
|
||||
234
tokenizer_config.json
Normal file
234
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user