初始化项目，由ModelHub XC社区提供模型
Model: ai-sage/GigaChat3.1-10B-A1.8B-bf16 Source: Original Platform
This commit is contained in:
ModelHub XC
55
.gitattributes
vendored
Normal file
55
.gitattributes
vendored
Normal file
@@ -0,0 +1,55 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00000-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
426
README.md
Normal file
426
README.md
Normal file
@@ -0,0 +1,426 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- ru
|
||||
- en
|
||||
base_model:
|
||||
- ai-sage/GigaChat3-10B-A1.8B-base
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- instruct
|
||||
- moe
|
||||
- multilingual
|
||||
- fp8
|
||||
- tool-use
|
||||
- long-context
|
||||
---
|
||||
|
||||
# GigaChat 3.1 Lightning
|
||||
|
||||
`GigaChat 3.1 Lightning` is the compact instruct model of the GigaChat 3.1 family. It is a Mixture-of-Experts (MoE) model with 10B total parameters and 1.8B active parameters, designed for fast multilingual assistant workloads, reasoning, code, function calling, and product-style deployment.
|
||||
|
||||
This repository contains the BF16 version of the model. The FP8 checkpoint is available at [GigaChat3.1-10B-A1.8B](https://huggingface.co/ai-sage/GigaChat3.1-10B-A1.8B), and a GGUF version is available at [GigaChat3.1-10B-A1.8B-GGUF](https://huggingface.co/ai-sage/GigaChat3.1-10B-A1.8B-GGUF).
|
||||
|
||||
More details can be found in the [Habr article](https://habr.com/en/companies/sberbank/articles/1014146/).
|
||||
|
||||
## Model architecture
|
||||
|
||||
GigaChat 3.1 Lightning uses a custom MoE architecture with the following key components.
|
||||
|
||||
### Mixture-of-Experts (MoE)
|
||||
|
||||
The model has 10B total parameters with 1.8B active parameters at inference time. This allows it to scale model capacity aggressively while keeping the active compute budget much lower than that of an equally large dense model.
|
||||
|
||||
### Multi-head Latent Attention (MLA)
|
||||
|
||||
Instead of standard multi-head attention, the model uses MLA, which compresses the KV cache into a latent representation. This reduces memory usage and improves inference throughput, especially in long-context settings.
|
||||
|
||||
### Multi-Token Prediction (MTP)
|
||||
|
||||
The model is trained with MTP, which allows it to predict multiple tokens per forward pass. In production systems, this can be used with speculative or parallel decoding techniques to improve throughput.
|
||||
|
||||
## Training data
|
||||
|
||||
The base GigaChat 3 training corpus spans 10 languages and includes books, academic material, code datasets, and mathematics datasets. All data goes through deduplication, language filtering, and automatic quality checks based on heuristics and classifiers.
|
||||
|
||||
Synthetic data remains a major contributor to quality. Across the broader training corpus, we used approximately 5.5 trillion synthetic tokens, including:
|
||||
|
||||
- question-answer data generated from source texts,
|
||||
- reverse-prompt chains for structured data generation,
|
||||
- model-authored notes embedded inside texts,
|
||||
- millions of synthetic tasks with solutions in mathematics and olympiad-style programming,
|
||||
- synthetic tests for code and reasoning tasks.
|
||||
|
||||
For the 3.1 release, we made major data improvements:
|
||||
|
||||
- Hard-domain expansion at Stage 1.5: stronger coverage of mathematics, finance, physics, engineering, biology, chemistry, and medicine.
|
||||
- Stricter quality validation: our internal `Revisor` pipeline was extended with stronger checks for Markdown, LaTeX, and answer-format correctness.
|
||||
- LLM-judge validation: SFT and DPO data is validated with judges selected for the task type and response structure.
|
||||
- On-policy DPO data: preference pairs were generated from preview-model behavior, making them better aligned with real model failure modes.
|
||||
- Better product-oriented data: we expanded data for search-and-citation scenarios, file-aware code interpretation, personalization, and agentic dialogues with executable tool calls.
|
||||
- Improved answer style: we also revised formatting and writing guidelines to improve readability, correctness, and overall response quality.
|
||||
|
||||
|
||||
## Post-training improvements
|
||||
|
||||
### DPO in native FP8
|
||||
|
||||
Unlike the preview release, `GigaChat 3.1 Lightning` includes a full DPO stage. This stage was redesigned for the MoE setup and trained in native FP8, not just quantized after training.
|
||||
|
||||
Important changes include:
|
||||
|
||||
- MTP heads trained during DPO for better consistency between main-model predictions and MTP predictions,
|
||||
- weighted gamma with exponential decay over long sequences,
|
||||
- stronger tuning of batch size and DPO contribution,
|
||||
- better robustness against loop-inducing failure modes.
|
||||
|
||||
In our experiments, native FP8 DPO not only recovered the quality that could be lost with post-training FP8 quantization, but in some cases even exceeded the BF16 result while using substantially less memory.
|
||||
|
||||
### Faster post-training
|
||||
|
||||
We also optimized the SFT pipeline with a combination of sequence packing, dynamic sequence parallelism, and additional pipeline optimizations. This reduced training cost significantly and improved GPU utilization, especially on long-context workloads.
|
||||
|
||||
## Inference
|
||||
|
||||
One of the key advantages of `GigaChat3.1-10B-A1.8B` is its inference speed. The model (especially in MTP mode) demonstrates throughput comparable to that of significantly smaller dense models.
|
||||
We measured this using vllm 0.17.1rc1.dev158+g600a039f5, concurrency=32, 1xH100 80gb SXM5.
|
||||
[Link to code.](https://gist.github.com/chameleon-lizard/07c5fdc658da63b0fdf105ae5a752344)
|
||||
|
||||
| Model | Output tps | Total tps | TPOT | Diff vs Lightning BF16 |
|
||||
|---|---|---|---|---|
|
||||
| GigaChat-3.1-Lightning BF16 | 2 866 | 5 832 | 9.52 | +0.0% |
|
||||
| GigaChat-3.1-Lightning BF16 + MTP | 3 346 | 6 810 | 8.25 | +16.7% |
|
||||
| GigaChat-3.1-Lightning FP8 | 3 382 | 6 883 | 7.63 | +18.0% |
|
||||
| GigaChat-3.1-Lightning FP8 + MTP | 3 958 | 8 054 | 6.92 | +38.1% |
|
||||
| YandexGPT-5-Lite-8B | 3 081 | 6 281 | 7.62 | +7.5% |
|
||||
|
||||
|
||||
## Benchmark Results
|
||||
|
||||
| Domain | Metric | GigaChat-3-Lightning | **GigaChat-3.1-Lightning** | Qwen3-1.7B-Instruct | Qwen3-4B-Instruct | SmolLM3 | gemma-3-4b-it |
|
||||
|---|---|---:|---:|---:|---:|---:|---:|
|
||||
| General | MMLU RU | 0.683 | 0.6803 | - | 0.597 | 0.500 | 0.519 |
|
||||
| General | RUBQ | 0.652 | 0.6646 | - | 0.317 | 0.636 | 0.382 |
|
||||
| General | MMLU PRO | 0.606 | 0.6176 | 0.410 | 0.685 | 0.501 | 0.410 |
|
||||
| General | MMLU EN | 0.740 | 0.7298 | 0.600 | 0.708 | 0.599 | 0.594 |
|
||||
| General | BBH | 0.453 | 0.5758 | 0.3317 | 0.717 | 0.416 | 0.131 |
|
||||
| General | SuperGPQA | 0.273 | 0.2939 | 0.209 | 0.375 | 0.246 | 0.201 |
|
||||
| Code | Human Eval Plus | 0.695 | 0.7317 | 0.628 | 0.878 | 0.701 | 0.713 |
|
||||
| Total | Average | 0.586 | 0.631 | 0.458 | 0.612 | 0.514 | 0.421 |
|
||||
|
||||
|
||||
## Arena Results
|
||||
|
||||
| Arena | GigaChat-2-Lite-30.1 | GigaChat-3-Lightning | **GigaChat-3.1-Lightning** | YandexGPT-5-Lite-8B | SmolLM3 | gemma-3-4b-it | Qwen3-4B | Qwen3-4B-Instruct-2507 |
|
||||
|---|---:|---:|---:|---:|---:|---:|---:|---:|
|
||||
| Arena Hard Logs V3 | 23.700 | 14.3 | 46.700 | 17.9 | 18.1 | 38.7 | 27.7 | 61.5 |
|
||||
| Validator SBS Pollux | 32.500 | 24.3 | 55.700 | 10.3 | 13.7 | 34.000 | 19.8 | 56.100 |
|
||||
| Total Average | 28.100 | 19.3 | 51.200 | 14.1 | 15.9 | 36.35 | 23.75 | 58.800 |
|
||||
|
||||
|
||||
## Usage Example
|
||||
|
||||
### 1. `transformers`
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
||||
|
||||
model_name = "ai-sage/GigaChat3.1-10B-A1.8B-bf16"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto",
|
||||
)
|
||||
model.generation_config = GenerationConfig.from_pretrained(model_name)
|
||||
messages = [
|
||||
{"role": "user", "content": "Докажи теорему о неподвижной точке"}
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
inputs = {k: v.to(model.device) for k, v in inputs.items()}
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1000,
|
||||
)
|
||||
prompt_len = inputs["input_ids"].shape[1]
|
||||
result = tokenizer.decode(
|
||||
outputs[0][prompt_len:],
|
||||
skip_special_tokens=True,
|
||||
)
|
||||
print(result)
|
||||
```
|
||||
|
||||
### 2. `vLLM`
|
||||
|
||||
Start the server
|
||||
```shell
|
||||
vllm serve ai-sage/GigaChat3.1-10B-A1.8B-bf16 \
|
||||
--dtype "auto" \
|
||||
--speculative-config '{"method": "mtp", "num_speculative_tokens": 1, "disable_padded_drafter_batch": false}'
|
||||
```
|
||||
|
||||
Request example
|
||||
```shell
|
||||
curl http://localhost:8000/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "ai-sage/GigaChat3.1-10B-A1.8B-bf16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Докажи теорему о неподвижной точке"
|
||||
}
|
||||
],
|
||||
"max_tokens": 400,
|
||||
"temperature": 0
|
||||
}'
|
||||
```
|
||||
|
||||
### 3. `SGLang`
|
||||
|
||||
Start the server
|
||||
```shell
|
||||
python -m sglang.launch_server \
|
||||
--model-path ai-sage/GigaChat3.1-10B-A1.8B-bf16 \
|
||||
--host 0.0.0.0 \
|
||||
--port 30000 \
|
||||
--dtype auto \
|
||||
--mem-fraction-static 0.88 \
|
||||
--speculative-algorithm EAGLE \
|
||||
--speculative-num-steps 1 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 2
|
||||
```
|
||||
|
||||
Request example
|
||||
```shell
|
||||
curl http://localhost:30000/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "ai-sage/GigaChat3.1-10B-A1.8B-bf16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Докажи теорему о неподвижной точке"
|
||||
}
|
||||
],
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0
|
||||
}'
|
||||
```
|
||||
|
||||
## Function calling
|
||||
|
||||
### 1. `transformers`
|
||||
|
||||
<details><summary>Click for a dropdown</summary>
|
||||
|
||||
```python
|
||||
import torch
|
||||
import json
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
||||
|
||||
FUNCTION_CALL_TOKEN = "<|function_call|>"
|
||||
|
||||
def parse_function_and_content(completion_str: str):
|
||||
completion_str = completion_str.strip()
|
||||
|
||||
if FUNCTION_CALL_TOKEN not in completion_str:
|
||||
return None, completion_str or None
|
||||
|
||||
content_part, function_part = completion_str.split(FUNCTION_CALL_TOKEN, 1)
|
||||
|
||||
content = content_part.strip() or None
|
||||
function_part = function_part.strip()
|
||||
|
||||
for suffix in ("</s>", "<s>"):
|
||||
if function_part.endswith(suffix):
|
||||
function_part = function_part[: -len(suffix)].strip()
|
||||
|
||||
try:
|
||||
function_call = json.loads(function_part)
|
||||
except json.JSONDecodeError:
|
||||
return None, content if content is not None else completion_str
|
||||
|
||||
if not (
|
||||
isinstance(function_call, dict)
|
||||
and "name" in function_call
|
||||
and "arguments" in function_call
|
||||
and isinstance(function_call["arguments"], dict)
|
||||
):
|
||||
return None, content
|
||||
|
||||
return function_call, content
|
||||
|
||||
|
||||
model_name = "ai-sage/GigaChat3.1-10B-A1.8B-bf16"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto",
|
||||
)
|
||||
model.generation_config = GenerationConfig.from_pretrained(model_name)
|
||||
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_weather",
|
||||
"description": "Получить информацию о текущей погоде в указанном городе.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"city": {
|
||||
"type": "string",
|
||||
"description": "Название города (например, Москва, Казань)."
|
||||
}
|
||||
},
|
||||
"required": ["city"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Какая сейчас погода в Москве?"}
|
||||
]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tools=tools,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
inputs = {k: v.to(model.device) for k, v in inputs.items()}
|
||||
|
||||
with torch.inference_mode():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1000,
|
||||
)
|
||||
|
||||
prompt_len = inputs["input_ids"].shape[1]
|
||||
completion = tokenizer.decode(
|
||||
outputs[0][prompt_len:],
|
||||
skip_special_tokens=False,
|
||||
)
|
||||
|
||||
function_call, content = parse_function_and_content(completion)
|
||||
print(function_call, content)
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
### 2. `vLLM`
|
||||
|
||||
commit>=[293f036](https://github.com/vllm-project/vllm/tree/293f036e6d83ba05236d948e9800bc6d4d58a727)
|
||||
|
||||
Start the server
|
||||
```shell
|
||||
vllm serve ai-sage/GigaChat3.1-10B-A1.8B-bf16 \
|
||||
--dtype "auto" \
|
||||
--speculative-config '{"method": "mtp", "num_speculative_tokens": 1, "disable_padded_drafter_batch": false}' \
|
||||
--enable-auto-tool-choice \
|
||||
--tool-call-parser gigachat3
|
||||
```
|
||||
|
||||
Request example
|
||||
```shell
|
||||
curl http://localhost:8000/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "ai-sage/GigaChat3.1-10B-A1.8B-bf16",
|
||||
"temperature": 0,
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Какая сейчас погода в Москве?"
|
||||
}
|
||||
],
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_weather",
|
||||
"description": "Получить информацию о текущей погоде в указанном городе.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"city": {
|
||||
"type": "string",
|
||||
"description": "Название города (например, Москва, Казань)."
|
||||
}
|
||||
},
|
||||
"required": ["city"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
### 3. `SGLang`
|
||||
|
||||
commit>=[30a35ec](https://github.com/sgl-project/sglang/tree/30a35ecd90227216a72833aa29ef02dc067db827)
|
||||
|
||||
Start the server
|
||||
```shell
|
||||
python -m sglang.launch_server \
|
||||
--model-path ai-sage/GigaChat3.1-10B-A1.8B-bf16 \
|
||||
--host 0.0.0.0 \
|
||||
--port 30000 \
|
||||
--dtype auto \
|
||||
--mem-fraction-static 0.88 \
|
||||
--speculative-algorithm EAGLE \
|
||||
--speculative-num-steps 1 \
|
||||
--speculative-eagle-topk 1 \
|
||||
--speculative-num-draft-tokens 2
|
||||
--tool-call-parser gigachat3
|
||||
```
|
||||
|
||||
Request example
|
||||
```shell
|
||||
curl http://localhost:30000/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "ai-sage/GigaChat3.1-10B-A1.8B-bf16",
|
||||
"temperature": 0,
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Какая сейчас погода в Москве?"
|
||||
}
|
||||
],
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_weather",
|
||||
"description": "Получить информацию о текущей погоде в указанном городе.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"city": {
|
||||
"type": "string",
|
||||
"description": "Название города (например, Москва, Казань)."
|
||||
}
|
||||
},
|
||||
"required": ["city"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
348
chat_template.jinja
Normal file
348
chat_template.jinja
Normal file
@@ -0,0 +1,348 @@
|
||||
{#--------TOOL RENDERING FUNCTIONS---------#}
|
||||
|
||||
{#---------------------------------------------------------------
|
||||
Converts JSON Schema (dict) to a TypeScript type definition
|
||||
----------------------------------------------------------------#}
|
||||
{%- macro json_schema_to_typescript(schema, indent="") -%}
|
||||
{%- set ADDITIONAL_JSON_KEYS = ['format', 'maxItems', 'maximum', 'minItems', 'minimum', 'pattern'] -%}
|
||||
{%- set ty = schema.get("type") -%}
|
||||
|
||||
{# ---------------- OBJECT ---------------- #}
|
||||
{%- if ty == "object" -%}
|
||||
{{- "{\n" -}}
|
||||
|
||||
{# Start building property list #}
|
||||
{%- set props = schema.get("properties", {}) -%}
|
||||
{%- set required = schema.get("required", []) -%}
|
||||
{%- set has_additional_props = schema.get("additionalProperties") is defined -%}
|
||||
{%- set additional_props_type = none -%}
|
||||
{%- if has_additional_props -%}
|
||||
{%- if schema.additionalProperties == true -%}
|
||||
{%- set additional_props_type = {'type': 'any'} -%}
|
||||
{%- elif schema.additionalProperties is mapping -%}
|
||||
{%- set additional_props_type = schema.additionalProperties -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- for key, val in props.items() -%}
|
||||
{# ---------- Description Comments ---------- #}
|
||||
{%- if "description" in val -%}
|
||||
{%- for line in val['description'].split('\n') -%}
|
||||
{%- if line.strip() -%}
|
||||
{{- indent + '// ' + line + '\n' -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------- Additional JSON Keys ---------- #}
|
||||
{%- for add_key, add_val in val.items() -%}
|
||||
{%- if add_key in ADDITIONAL_JSON_KEYS -%}
|
||||
{%- if add_val is string -%}
|
||||
{{- indent + '// ' + add_key + ': "' + add_val + '"' + '\n' -}}
|
||||
{%- else -%}
|
||||
{{- indent + '// ' + add_key + ': ' ~ add_val ~ '\n' -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{# ---------- Property Definition ---------- #}
|
||||
{%- set type_str = json_schema_to_typescript(
|
||||
val,
|
||||
indent + " "
|
||||
) -%}
|
||||
|
||||
{{- indent + key + ('' if key in required else '?') + ': ' + type_str + ',' -}}
|
||||
|
||||
{%- if "default" in val or "defalut_value" in val -%}
|
||||
{%- set default = val.get("default", val.get("defalut_value")) -%}
|
||||
{%- if default is string -%}
|
||||
{{- ' // default: "' + default + '"' -}}
|
||||
{%- else -%}
|
||||
{{- ' // default: ' ~ default -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
|
||||
{{- "\n" -}}
|
||||
{%- endfor -%}
|
||||
|
||||
{# Handle additionalProperties as index signature #}
|
||||
{%- if has_additional_props and additional_props_type is not none -%}
|
||||
{%- set additional_type_str = json_schema_to_typescript(
|
||||
additional_props_type,
|
||||
indent + " "
|
||||
) -%}
|
||||
{{- indent + '[key: string]: ' + additional_type_str + '\n' -}}
|
||||
{%- endif -%}
|
||||
|
||||
{{- indent[: (indent|length - " "|length) ] + '}' -}}
|
||||
|
||||
{# ---------------- STRING ---------------- #}
|
||||
{%- elif ty == "string" -%}
|
||||
{%- if schema.get("enum") -%}
|
||||
{%- set ns = namespace(enum = []) -%}
|
||||
{%- for en in schema['enum'] -%}
|
||||
{%- set ns.enum = ns.enum + ['"' ~ en ~ '"'] -%}
|
||||
{%- endfor -%}
|
||||
{{- ns.enum | join(' | ') -}}
|
||||
{%- elif schema.get("format", "none") in ['date-time', 'date'] -%}
|
||||
{{- 'Date' -}}
|
||||
{%- else -%}
|
||||
{{- 'string' -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------------- NUMBER / INTEGER ---------------- #}
|
||||
{%- elif ty in ["number", "integer"] -%}
|
||||
{%- if schema.get("enum") -%}
|
||||
{{- schema.enum | join(' | ') -}}
|
||||
{%- else -%}
|
||||
{{- 'number' -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------------- BOOLEAN ---------------- #}
|
||||
{%- elif ty == "boolean" -%}
|
||||
{{- 'boolean' -}}
|
||||
|
||||
{# ---------------- ARRAY ---------------- #}
|
||||
{%- elif ty == "array" -%}
|
||||
{%- if "items" in schema -%}
|
||||
{{- json_schema_to_typescript(schema['items'], indent) + '[]' -}}
|
||||
{%- else -%}
|
||||
{{- 'Array<any>' -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------------- FALLBACK ---------------- #}
|
||||
{%- else -%}
|
||||
{{- 'any' -}}
|
||||
{%- endif -%}
|
||||
{%- endmacro -%}
|
||||
|
||||
{#---------------------------------------------------------------
|
||||
Renders a namespace and its tool definitions in TypeScript style
|
||||
----------------------------------------------------------------#}
|
||||
|
||||
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
||||
{%- set ns = namespace(sections = ['namespace ' ~ namespace_name ~ ' {']) -%}
|
||||
|
||||
{%- for tool in tools -%}
|
||||
{%- if tool.function -%}
|
||||
{%- set tool = tool.function -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- set ns_tool = namespace(content_lines=[]) -%}
|
||||
|
||||
{# ---------- TOOL DESCRIPTION ---------- #}
|
||||
{%- if tool.get('description') -%}
|
||||
{%- for line in tool['description'].split('\n') -%}
|
||||
{%- if line.strip() -%}
|
||||
{%- set ns_tool.content_lines = ns_tool.content_lines + ['// ' ~ line] -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------- TOOL SIGNATURE ---------- #}
|
||||
{%- set main_body = "" -%}
|
||||
{%- set params = tool.get("parameters") -%}
|
||||
{%- if params and params.get("properties") -%}
|
||||
{%- set param_type = json_schema_to_typescript(params, " ") -%}
|
||||
{%- set main_body = 'type ' ~ tool.name ~ ' = (_: ' ~ param_type ~ ') => ' -%}
|
||||
{%- else -%}
|
||||
{%- set main_body = 'type ' ~ tool.name ~ ' = () => ' -%}
|
||||
{%- endif -%}
|
||||
|
||||
{# ---------- RETURN TYPE ---------- #}
|
||||
{%- set return_params = tool.get("return_parameters") -%}
|
||||
{%- if return_params and return_params.get("properties") -%}
|
||||
{%- set return_type = json_schema_to_typescript(return_params, " ") -%}
|
||||
{%- set main_body = main_body ~ return_type -%}
|
||||
{%- else -%}
|
||||
{%- set main_body = main_body ~ 'any' -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- set main_body = main_body ~ ';\n' -%}
|
||||
|
||||
{%- set ns_tool.content_lines = ns_tool.content_lines + [main_body] -%}
|
||||
|
||||
{# ---------- ADD TOOL TO SECTIONS ---------- #}
|
||||
{%- set ns.sections = ns.sections + [ns_tool.content_lines | join('\n')] -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{%- set ns.sections = ns.sections + ['} // namespace ' ~ namespace_name] -%}
|
||||
|
||||
{{- ns.sections | join('\n') -}}
|
||||
{%- endmacro -%}
|
||||
|
||||
|
||||
{# ----------- MESSAGE RENDERING HELPER FUNCTIONS ------------ #}
|
||||
|
||||
{%- macro render_function_call(call) -%}
|
||||
{%- if call.function -%}
|
||||
{%- set call = call.function -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- set arguments = call['arguments'] -%}
|
||||
{%- if arguments is not string -%}
|
||||
{%- set arguments = arguments| tojson(ensure_ascii=False) -%}
|
||||
{%- endif -%}
|
||||
|
||||
{{- '{"name": "' ~ call['name'] ~ '", "arguments": ' ~ arguments ~ '}' -}}
|
||||
{%- endmacro -%}
|
||||
|
||||
|
||||
{%- macro render_role_message(message, role=None) -%}
|
||||
{%- if not role -%}
|
||||
{%- set role = message["role"] -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- set message_content = message['content'] or '' -%}
|
||||
{%- if message_content is not string -%}
|
||||
{%- set message_content = message_content | tojson(ensure_ascii=False) -%}
|
||||
{%- endif -%}
|
||||
|
||||
{{- role + add_tokens.role_sep + message_content -}}
|
||||
|
||||
{%- if message.tool_calls is defined and message.tool_calls -%}
|
||||
{{- add_tokens.function_call + render_function_call(message.tool_calls[0]) -}}
|
||||
{%- endif -%}
|
||||
|
||||
{{- add_tokens.message_sep -}}
|
||||
|
||||
{%- endmacro -%}
|
||||
|
||||
|
||||
|
||||
{# ----- SPECIAL TOKENS ----- #}
|
||||
|
||||
{%- set add_tokens = namespace(
|
||||
role_sep="<|role_sep|>\n",
|
||||
message_sep="<|message_sep|>\n\n",
|
||||
function_call="<|function_call|>"
|
||||
) -%}
|
||||
|
||||
{# ----- DEFAULT DEVSYSTEM ----- #}
|
||||
|
||||
{%- set DEVSYSTEM -%}
|
||||
<role_description>
|
||||
Описание доступных в диалоге ролей.
|
||||
|
||||
`developer system`
|
||||
Сообщение, добавленное Сбером до основного диалога. Имеет самый высокий приоритет и определяет глобальные, неотменяемые условия (например, правила ведения диалога, политику безопасности, общий стиль ответов ассистента и пр.).
|
||||
|
||||
`system`
|
||||
Системная инструкция, добавляемая разработчиками или пользователем, но с приоритетом ниже, чем `developer system`. Обычно описывает инструкции ассистента, конкретный стиль ответа и другие условия для данного конкретного диалога.
|
||||
|
||||
`user`
|
||||
Сообщение или запрос от пользователя. Ассистент следует ему, если это не противоречит инструкциям более высокого приоритета (см. <instruction_priority>).
|
||||
|
||||
`user memory`
|
||||
Последовательность наиболее актуальных долговременных фактов о пользователе на момент его запроса, представленная в виде JSON‑списка строк. Факты в ней перечислены в хронологическом порядке, то есть более новые факты дописываются в конец последовательности. При этом при изменении или удалении фактов записи о предыдущих фактах остаются в последовательности. Ассистент сохраняет факты с помощью функции и использует их в соответствии с указаниями из блока <memory_guidelines> ниже.
|
||||
|
||||
`added files`
|
||||
Метаинформация о файлах, доступных для использования в диалоге, представленная в формате JSON. Содержит следующие ключи: id (уникальный идентификатор файла), name (имя файла), type (тип файла).
|
||||
|
||||
`assistant`
|
||||
Ответ ассистента на запрос пользователя. Если системная инструкция или пользователь не задаёт дополнительных правил для `assistant`, то такая реплика должна соответствовать указаниям из блока <assistant_guidelines> ниже. Список доступных для вызова функций содержится в последней реплике роли `available functions`. Название необходимой для вызова функции и аргументы будут сгенерированы после специального токена вызова функции. В своих репликах ассистент следует инструкциям в соответствии с <instruction_priority>.
|
||||
Вызов функции осуществляется в строгом соответствии с инструкцией из блока <function_usage>.
|
||||
|
||||
`function descriptions`
|
||||
Описания функций в формате TypeScript. Функция — это специальный инструмент (или набор инструкций), который ассистент может вызвать для выполнения конкретных действий, вычислений или получения данных, необходимых для решения задачи пользователя. Каждое описание функции содержит блоки с именем, описанием, аргументами. Иногда описание содержит отдельные блоки с возвращаемыми параметрами и примерами применения, иллюстрирующими правильный вызов и аргументы.
|
||||
|
||||
`available functions`
|
||||
Список, который содержит названия функций, доступных для вызова. Если список не содержит элементов, то в следующем сообщении функции, доступные для вызова, отсутствуют.
|
||||
|
||||
`function result`
|
||||
Результат последнего вызова функции.
|
||||
</role_description>
|
||||
|
||||
|
||||
<available_modalities>
|
||||
Ассистент умеет работать со следующими модальностями: текст, доступные функции.
|
||||
</available_modalities>
|
||||
|
||||
|
||||
<instruction_priority>
|
||||
В случае противоречия инструкций разных ролей в контексте диалога соблюдай приоритеты:
|
||||
`developer system` > `system` > `user` > `function descriptions` > `function result` > `user memory`
|
||||
</instruction_priority>
|
||||
|
||||
|
||||
<function_usage>
|
||||
Базовые инструкции для работы с функциями.
|
||||
|
||||
Можно вызывать только те функции, которые доступны исходя из последнего сообщения `available functions`.
|
||||
|
||||
Вызывай доступные функции в случае, если согласно их описанию такой вызов поможет дать более полный и/или точный ответ на запрос пользователя. Заполняй аргументы функций, используя информацию из контекста диалога. Если функция может помочь ответить на запрос, но для её обязательного аргумента отсутствует информация в контексте, уточни у пользователя недостающие данные перед вызовом функции. При недоступности необходимой функции или ошибке — кратко сообщи об этом пользователю и по возможности предложи альтернативу.
|
||||
</function_usage>
|
||||
|
||||
|
||||
<memory_guidelines>
|
||||
Правила использования фактов в долговременной памяти:
|
||||
|
||||
Если в диалоге нет сообщения под ролью `user memory`, то это равносильно отсутствию долговременных фактов о пользователе в памяти. В таком случае информация о пользователе ограничена текущим диалогом, и новые факты не должны сохраняться.
|
||||
</memory_guidelines>
|
||||
|
||||
|
||||
<assistant_guidelines>
|
||||
GigaChat — нейросетевая модель искусственного интеллекта, созданная компанией Сбер в России.
|
||||
|
||||
GigaChat старается отвечать на языке, на котором пользователь задал запрос. Если из запроса пользователя и контекста диалога язык определить невозможно, GigaChat использует русский.
|
||||
GigaChat предоставляет подробные ответы на более сложные и открытые вопросы.
|
||||
GigaChat в ответе не использует названия доступных функций.
|
||||
GigaChat отвечает безопасно, в соответствии с действующим законодательством Российской Федерации, стараясь помочь пользователю решить задачу или поддержать беседу.
|
||||
|
||||
Ты — GigaChat.
|
||||
</assistant_guidelines>
|
||||
|
||||
|
||||
Ниже будет приведён диалог.
|
||||
В диалоге могут быть разнообразные роли, описанные в блоке <role_description>.
|
||||
Каждая реплика начинается с названия роли и специального токена, обозначающего конец полного наименования роли, а заканчивается специальным токеном конца реплики.
|
||||
Твоя задача — продолжить диалог от последней указанной роли в соответствии с контекстом диалога.
|
||||
{%- endset -%}
|
||||
|
||||
|
||||
{#- ---------------------- RENDERING STARTS HERE ---------------------- -#}
|
||||
|
||||
|
||||
{# ----- RENDER BOS TOKEN ----- #}
|
||||
{{- bos_token -}}
|
||||
|
||||
|
||||
{# ----- RENDER DEVSYSTEM ----- #}
|
||||
{{- render_role_message({"role": "developer system", "content": DEVSYSTEM}) -}}
|
||||
|
||||
{# ----- RENDER SYSTEM IF PRESENT ----- #}
|
||||
{%- if messages and messages[0]['role'] == 'system' -%}
|
||||
{{- render_role_message(messages[0]) -}}
|
||||
{%- set messages = messages[1:] -%}
|
||||
{%- else -%}
|
||||
{{- render_role_message({"role": "system", "content": ""}) -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ----- RENDER TOOLS ----- #}
|
||||
{%- if tools -%}
|
||||
{%- set tools_content = (
|
||||
render_tool_namespace('functions', tools)
|
||||
+ "\n\n"
|
||||
) -%}
|
||||
{{- render_role_message({'role': 'function descriptions', 'content': tools_content}) -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ----- MAIN MESSAGE LOOP ----- #}
|
||||
{%- for message in messages -%}
|
||||
|
||||
{# ----- TOOL MESSAGE -------#}
|
||||
{%- if message['role'] == 'tool' -%}
|
||||
{{- render_role_message(message, 'function result') -}}
|
||||
|
||||
{# ----- OTHER MESSAGES ----- #}
|
||||
{%- else -%}
|
||||
{{- render_role_message(message) -}}
|
||||
{%- endif -%}
|
||||
|
||||
{# ----- ADDING GENERATION PROMPT ----- #}
|
||||
|
||||
{%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
|
||||
{{- 'assistant' + add_tokens.role_sep -}}
|
||||
{%- endif -%}
|
||||
|
||||
{%- endfor -%}
|
||||
53
config.json
Normal file
53
config.json
Normal file
@@ -0,0 +1,53 @@
|
||||
{
|
||||
"vocab_size": 128256,
|
||||
"max_position_embeddings": 262144,
|
||||
"hidden_size": 1536,
|
||||
"intermediate_size": 8960,
|
||||
"moe_intermediate_size": 1280,
|
||||
"num_hidden_layers": 26,
|
||||
"num_nextn_predict_layers": 1,
|
||||
"num_attention_heads": 32,
|
||||
"n_shared_experts": 1,
|
||||
"n_routed_experts": 64,
|
||||
"ep_size": 1,
|
||||
"routed_scaling_factor": 1,
|
||||
"kv_lora_rank": 512,
|
||||
"q_lora_rank": null,
|
||||
"qk_rope_head_dim": 64,
|
||||
"v_head_dim": 192,
|
||||
"qk_nope_head_dim": 128,
|
||||
"topk_method": "noaux_tc",
|
||||
"n_group": 1,
|
||||
"topk_group": 1,
|
||||
"num_experts_per_tok": 4,
|
||||
"moe_layer_freq": 1,
|
||||
"first_k_dense_replace": 1,
|
||||
"norm_topk_prob": true,
|
||||
"scoring_func": "sigmoid",
|
||||
"num_key_value_heads": 32,
|
||||
"hidden_act": "silu",
|
||||
"initializer_range": 0.006,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"use_cache": true,
|
||||
"rope_theta": 100000,
|
||||
"rope_scaling": {
|
||||
"beta_fast": 32.0,
|
||||
"beta_slow": 1.0,
|
||||
"factor": 64.0,
|
||||
"mscale": 1.0,
|
||||
"mscale_all_dim": 1.0,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"rope_type": "yarn"
|
||||
},
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"tie_word_embeddings": false,
|
||||
"architectures": [
|
||||
"DeepseekV3ForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.57.3",
|
||||
"model_type": "deepseek_v3",
|
||||
"dtype": "bfloat16"
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.57.3",
|
||||
"_from_model_config": true
|
||||
}
|
||||
3
model-00000-of-00005.safetensors
Normal file
3
model-00000-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:612f84d11aca544694ef674e58781d0c39ae4b2046f9cadeada79f1d37e581b6
|
||||
size 4986065392
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f104115bca75cec67bcfb162a71f57b4ab97de66e168d03adeb97a7d9e4e2cf
|
||||
size 4085021224
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a3f9ffc60ec8e671687afb2260e7b6ab6b75267a4f50e39c494192edd15e1df
|
||||
size 4085022040
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fbb40d4301d9355248e37da641d03fa3633aad8c05b63dab3954d21a7b90071
|
||||
size 4085022240
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26c4261a7424c878e15e70c02d2429f1a16b39b74714068ac6e02aa2901879b0
|
||||
size 4085022240
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf53c1a4db179dd8769499fdd6126b4cfb856fdcdc9026bf5edb2f328c026f8c
|
||||
size 1634008560
|
||||
5330
model.safetensors.index.json
Normal file
5330
model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4b3d90c67830a4e566296ad8d0f6b5ac5a5cdbfd331b200d0ee8263aaaea1fe
|
||||
size 10680800
|
||||
131
tokenizer_config.json
Normal file
131
tokenizer_config.json
Normal file
@@ -0,0 +1,131 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128000": {
|
||||
"content": "<|role_sep|>\n",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128001": {
|
||||
"content": "<|message_sep|>\n\n",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128002": {
|
||||
"content": "<|file|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128003": {
|
||||
"content": "<|/file|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128004": {
|
||||
"content": "[image_token]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128005": {
|
||||
"content": "[video_image_token]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128006": {
|
||||
"content": "[audio_token]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128007": {
|
||||
"content": "[video_audio_token]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128008": {
|
||||
"content": "<point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128009": {
|
||||
"content": "</point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128010": {
|
||||
"content": "<bbox>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128011": {
|
||||
"content": "</bbox>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"128012": {
|
||||
"content": "<|function_call|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"tokenizer_class": "PreTrainedTokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user