初始化项目，由ModelHub XC社区提供模型
Model: SPAISS6F1/qwen-1b-pruned-th 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
|
||||
125
README.md
Normal file
125
README.md
Normal file
@@ -0,0 +1,125 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language: [th]
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags: [thai, pruning, depth-pruning, layer-dropping]
|
||||
---
|
||||
|
||||
# qwen-1b-pruned-th
|
||||
|
||||
โมเดลภาษาไทยขนาดเล็กที่ได้จากการ **Depth Pruning (Layer Dropping)** ของ `Qwen/Qwen2.5-3B`
|
||||
แล้วทำ **Healing SFT** เพื่อกู้ความสามารถกลับมา
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Base model | `Qwen/Qwen2.5-3B` |
|
||||
| Base size | 3.09B (36 layers) |
|
||||
| **โมเดลนี้** | **1.70B** (เก็บ 18 layers) |
|
||||
| Layers ที่เก็บ | [0-8, 27-35] (ตัด layer กลาง เก็บหัว+ท้าย) |
|
||||
| Healing data | SEA-PILE v2 Thai (~8,000 docs) |
|
||||
| Hardware | NVIDIA A100-40GB (Lanta HPC) |
|
||||
| Requires | `transformers>=4.44`, accelerate |
|
||||
|
||||
---
|
||||
|
||||
## Pipeline การสร้างโมเดล (ทำซ้ำได้)
|
||||
|
||||
### ขั้นที่ 1 — Depth Pruning (Layer Dropping)
|
||||
ตัด decoder layer ตรงกลางทิ้ง (มักทำงานซ้ำซ้อน) เก็บเฉพาะ layer หัว (เข้าใจ input)
|
||||
และ layer ท้าย (สร้าง output) — **embedding / lm_head / norm คงเดิม** จึงไม่พัง dimension
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B", torch_dtype=torch.bfloat16)
|
||||
|
||||
# หา text-decoder layer list (เลี่ยง vision encoder กรณี multimodal)
|
||||
holder, layers = None, None
|
||||
for _, mod in model.named_modules():
|
||||
L = getattr(mod, "layers", None)
|
||||
if isinstance(L, torch.nn.ModuleList) and len(L) and hasattr(L[0], "self_attn"):
|
||||
holder, layers = mod, L
|
||||
if "language" in _.lower() or "text" in _.lower():
|
||||
break
|
||||
N = len(layers)
|
||||
|
||||
# เก็บ 18 จาก 36 layers: หัว + ท้าย
|
||||
keep = [0,1,2,3,4,5,6,7,8, 27,28,29,30,31,32,33,34,35]
|
||||
holder.layers = torch.nn.ModuleList([layers[i] for i in keep])
|
||||
|
||||
# อัปเดต config (รองรับ nested text_config ของ Gemma3)
|
||||
for c in {model.config, getattr(model.config, "text_config", model.config)}:
|
||||
if getattr(c, "num_hidden_layers", None) is not None:
|
||||
c.num_hidden_layers = len(keep)
|
||||
lt = getattr(c, "layer_types", None)
|
||||
if isinstance(lt, list) and len(lt) == N:
|
||||
c.layer_types = [lt[i] for i in keep]
|
||||
|
||||
# reindex layer_idx ของแต่ละ block (สำคัญต่อ KV cache)
|
||||
for i, lyr in enumerate(holder.layers):
|
||||
if hasattr(lyr, "self_attn") and hasattr(lyr.self_attn, "layer_idx"):
|
||||
lyr.self_attn.layer_idx = i
|
||||
```
|
||||
ผลลัพธ์: 3.09B -> **1.70B** (ยังไม่ถึง 1B เป๊ะ เพราะ embedding+lm_head+vocab ไม่ลดตาม layer)
|
||||
|
||||
> หลัง prune โมเดลจะพ่น gibberish ทันที (เส้นประสาทถูกตัดขาด) -> ต้อง Healing ต่อ
|
||||
|
||||
### ขั้นที่ 2 — Healing SFT
|
||||
เทรนต่อด้วย causal-LM บน Thai corpus เพื่อให้ layer ที่เหลือกลับมาทำงานร่วมกัน
|
||||
|
||||
```python
|
||||
from transformers import Trainer, TrainingArguments, DataCollatorForLanguageModeling
|
||||
from datasets import load_dataset
|
||||
|
||||
ds = load_dataset("SPAISS6F1/spai-ss6-llm-1b-thai-corpus", split="train") # หรือ SEA-PILE v2 'th'
|
||||
tds = ds.map(lambda e: tok(e["text"], truncation=True, max_length=1024),
|
||||
batched=True, remove_columns=ds.column_names)
|
||||
|
||||
model.gradient_checkpointing_enable(); model.config.use_cache = False
|
||||
args = TrainingArguments(output_dir="out", num_train_epochs=2,
|
||||
per_device_train_batch_size=4, gradient_accumulation_steps=4,
|
||||
learning_rate=1e-4, lr_scheduler_type="cosine", warmup_ratio=0.03, bf16=True)
|
||||
Trainer(model=model, args=args, train_dataset=tds,
|
||||
data_collator=DataCollatorForLanguageModeling(tok, mlm=False)).train()
|
||||
```
|
||||
|
||||
**Hyperparameters:**
|
||||
- Learning rate: `1e-4` (สูงกว่าปกติเพื่อสมานแผล) | Epochs: 2
|
||||
- Batch 4 x grad-accum 4 (effective 16) | max_len 1024 | bf16
|
||||
- Optimizer: AdamW + cosine schedule, warmup 3%
|
||||
- Env: conda myenv (transformers 4.49)
|
||||
|
||||
### ขั้นที่ 3 — Save
|
||||
```python
|
||||
model.config.use_cache = True
|
||||
try:
|
||||
model.save_pretrained("out", safe_serialization=True)
|
||||
except RuntimeError: # Gemma3: tied embeddings -> fallback .bin
|
||||
model.save_pretrained("out", safe_serialization=False)
|
||||
```
|
||||
โมเดลนี้ save เป็น: `model.safetensors`
|
||||
|
||||
---
|
||||
|
||||
## วิธีใช้ (Inference)
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
m = "SPAISS6F1/qwen-1b-pruned-th"
|
||||
tok = AutoTokenizer.from_pretrained(m)
|
||||
model = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="cuda")
|
||||
ids = tok("ปัญญาประดิษฐ์ คือ", return_tensors="pt").to(model.device)
|
||||
out = model.generate(**ids, max_new_tokens=120, do_sample=True,
|
||||
temperature=0.7, top_p=0.9, repetition_penalty=1.3)
|
||||
print(tok.decode(out[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## ข้อควรรู้ / ข้อจำกัด
|
||||
- เป็น **pruned base ที่ heal ด้วย raw web corpus** -> ไวยากรณ์ไทยลื่นไหลดี
|
||||
แต่ **ข้อเท็จจริงและการคิดเลขยังอ่อน** (ยังไม่ผ่าน instruction tuning)
|
||||
- แนะนำ `repetition_penalty >= 1.2` กันการวนซ้ำ
|
||||
- เหมาะเป็น **base สำหรับ fine-tune ต่อด้วย instruction dataset** มากกว่าใช้ตอบตรง ๆ
|
||||
- การตัด layer 50% เป็นการตัดที่ค่อนข้างหนัก (งานวิจัย เช่น ShortGPT แนะ ~25%);
|
||||
ถ้าต้องการคุณภาพสูงขึ้นควร heal นานขึ้น/ตัดเบาลง
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-3B",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 18,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.49.0",
|
||||
"use_cache": true,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c3ed5fc8999d73e2ee7766d6c682a8fd92a1e0813daa506d6c653032e2262929
|
||||
size 3397130560
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"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|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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 {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.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{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user