初始化项目,由ModelHub XC社区提供模型

Model: burtenshaw/Qwen3-30B-A3B-python-coder
Source: Original Platform
This commit is contained in:
ModelHub XC committed 2026-11-16 05:18:18 +08:00
commit 3dcc180e0b
27 files changed
+170959

No files matched your search

+36
View 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
+59
View File
@@ -0,0 +1,59 @@
---
base_model: Qwen/Qwen3-30B-A3B
datasets: burtenshaw/tulu-3-sft-personas-code-no-prompt
library_name: transformers
model_name: Qwen3-30B-A3B-python-coder
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Qwen3-30B-A3B-python-coder
This model is a fine-tuned version of [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) on the [burtenshaw/tulu-3-sft-personas-code-no-prompt](https://huggingface.co/datasets/burtenshaw/tulu-3-sft-personas-code-no-prompt) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="burtenshaw/Qwen3-30B-A3B-python-coder", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/smartwithfood/huggingface/runs/m22i87x1)
This model was trained with SFT.
### Framework versions
- TRL: 0.17.0
- Transformers: 4.51.3
- Pytorch: 2.7.0
- Datasets: 3.5.1
- Tokenizers: 0.21.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
+28
View File
@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|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
}
+38
View File
@@ -0,0 +1,38 @@
{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 48,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}
+13
View 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": "4.51.3"
}
+151388
View File
File diff suppressed because it is too large. Load diff
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:290d474bdbbc8e52e90494cfd27181cb16520a88fbfade22501777d515ae128d
size 4997184968
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:608406ced27bda08d0174299b4ceaec6b095b9345a620bf4ff9a31f3b4fa78c8
size 4997741608
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58dc2604a1c87fb101b4f635c67be710231aa4aea696d2d0336c0fd373318473
size 4997742208
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3249e9802eed31e05ae80d6da08b6762a7d4405dec45455641ca78e28ddefc5b
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b1c8f041dabebdfbeb913ac1a456d62c8627534419605e18b0316d895e5bba4
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d09aedef31577d8620411a7575179b0ee3705bce80f77ffff717ca577ff75b9
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a5e0f1e4bef1df995974b35fbcb6a0eddcdb36263c7d81221f1e6dba3ff5e92
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79554d2b20f30332817ab44e7fa5d566e38ad630a804ec38f3f4d68c859256c8
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e3b271dcb14b65d7711c424366a91b513cb342e57f9ccecc8f18a23852d6927c
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:815658b4044f4ea9a6dc846d35fbbe44c52fef3f41b9e48dfbb51f7c94560dcf
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c67a5b0dc8f770ae76b55886679ea84007749a686b9ac7d3cbb7f727fbc5f6b
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:392136838244a7f1153a91fbecde66f840c4bdd75a7937104a3e85a5e3e4be37
size 4997743184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82e09aa5c14b63281f9d75106a4ff0be14863d328835d78ad099df8a1a88c077
size 1094220288
File diff suppressed because it is too large. Load diff
+12
View File
@@ -0,0 +1,12 @@
datasets
httpx
huggingface-hub
setuptools
transformers
torch
accelerate
trl
peft
wandb
torchvision
torchaudio
+25
View File
@@ -0,0 +1,25 @@
{
"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": "<|im_end|>",
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}
BIN
View File
Binary file not shown.
+240
View File
@@ -0,0 +1,240 @@
{
"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 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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 {{- 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 {%- 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",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}
+200
View File
@@ -0,0 +1,200 @@
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "datasets",
# "httpx",
# "huggingface - hub",
# "setuptools",
# "transformers",
# "torch",
# "accelerate",
# "trl",
# "peft",
# "wandb",
# "torchvision",
# "torchaudio"
# ]
# ///
"""## Import libraries"""
import torch
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import SFTConfig, SFTTrainer, setup_chat_format
from peft import LoraConfig
"""# Load Dataset"""
dataset_name = "allenai/tulu-3-sft-personas-code" # Example dataset
# Load dataset
dataset = load_dataset(dataset_name, split="train")
print(f"Dataset loaded: {dataset}")
# Let's look at a sample
print("\nSample data:")
print(dataset[0])
dataset = dataset.remove_columns("prompt")
dataset = dataset.train_test_split(test_size=0.2)
print(
f"Train Samples: {len(dataset['train'])}\nTest Samples: {len(dataset['test'])}"
)
"""## Configuration
Set up the configuration parameters for the fine-tuning process.
"""
# Model configuration
model_name = "Qwen/Qwen3-30B-A3B" # You can change this to any model you want to fine-tune
# # Other compatible Qwen3 models
# model_name = "Qwen/Qwen3-32B"
# model_name = "Qwen/Qwen3-14B"
# model_name = "Qwen/Qwen3-8B"
# model_name = "Qwen/Qwen3-4B"
# model_name = "Qwen/Qwen3-1.7B"
# model_name = "Qwen/Qwen3-0.6B"
# Training configuration
output_dir = "./tmp/sft-model"
num_train_epochs = 1
per_device_train_batch_size = 1
gradient_accumulation_steps = 1
learning_rate = 2e-4
"""## Load model and tokenizer"""
# Load model
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
use_cache=False, # Disable KV cache during training
device_map="auto",
)
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
# # Set up chat formatting (if the model doesn't have a chat template)
# if tokenizer.chat_template is None:
# model, tokenizer = setup_chat_format(model, tokenizer, format="chatml")
# # Set padding token
# if tokenizer.pad_token is None:
# tokenizer.pad_token = tokenizer.eos_token
"""## Configure PEFT (if enabled)"""
# Set up PEFT configuration if enabled
peft_config = LoraConfig(
r=32, # Rank
lora_alpha=16, # Alpha parameter for LoRA scaling
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM",
target_modules="all-linear",
)
"""## Configure SFT Trainer"""
# Training arguments
training_args = SFTConfig(
output_dir=output_dir,
num_train_epochs=num_train_epochs,
per_device_train_batch_size=per_device_train_batch_size,
gradient_accumulation_steps=gradient_accumulation_steps,
learning_rate=learning_rate,
gradient_checkpointing=True,
logging_steps=25,
save_strategy="epoch",
optim="adamw_torch",
lr_scheduler_type="cosine",
warmup_ratio=0.1,
max_length=1024,
packing=True, # Enable packing to increase training efficiency
eos_token=tokenizer.eos_token,
bf16=True,
fp16=False,
max_steps=1000,
report_to="wandb", # Disable reporting to avoid wandb prompts
)
"""## Initialize and run the SFT Trainer"""
# Create SFT Trainer
trainer = SFTTrainer(
model=model,
args=training_args,
train_dataset=dataset["train"],
eval_dataset=dataset["test"] if "test" in dataset else None,
peft_config=peft_config,
processing_class=tokenizer,
)
# Train the model
trainer.train()
"""## Save the fine-tuned model"""
# Save the model
trainer.save_model(output_dir)
"""## Test the fine-tuned model"""
from peft import PeftModel, PeftConfig
# Load the base model
base_model = AutoModelForCausalLM.from_pretrained(
model_name, trust_remote_code=True, torch_dtype=torch.bfloat16
)
# Load the fine-tuned PEFT model
model = PeftModel.from_pretrained(base_model, output_dir)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
# Test the model with an example
prompt = """Write a function called is_palindrome that takes a single string as input and returns True if the string is a palindrome, and False otherwise.
Palindrome Definition:
A palindrome is a word, phrase, number, or other sequence of characters that reads the same forward and backward, ignoring spaces, punctuation, and capitalization.
Example:
```
is_palindrome("racecar") # Returns True
is_palindrome("hello") # Returns False
is_palindrome("A man, a plan, a canal: Panama") # Returns True
```
"""
# Format the chat prompt using the tokenizer's chat template
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt},
]
formatted_prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
print(f"Formatted prompt: {formatted_prompt}")
# Generate response
model.eval()
inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=500,
temperature=0.7,
top_p=0.9,
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print("\nGenerated Response:")
print(response)
model.push_to_hub("burtenshaw/Qwen3-30B-A3B-python-code")
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:530d75515728e5b50537b8578139e6d2102ba7d965be8b8efe4433401d64e63c
size 7377
+1
View File
@@ -0,0 +1 @@
{"!":0,"\"":1,"#":2,"$":3,"%":4,"&":5,"'":6,"(":7,")":8,"*":9,"+":10,",":11,"-":12,".":13,"/":14,"0":15,"1":16,"2":17,"3":18,"4":19,"5":20,"6":21,"7":22,"8":23,"9":24,":":25,";":26,"<":27,"=":28,">":29,"?":30,"@":31,"A":32,"B":33,"C":34,"D":35,"E":36,"F":37,"G":38,"H":39,"I":40,"J":41,"K":42,"L":43,"M":44,"N":45,"O":46,"P":47,"Q":48,"R":49,"S":50,"T":51,"U":52,"V":53,"W":54,"X":55,"Y":56,"Z":57,"[":58,"\\":59,"]":60,"^":61,"_":62,"`":63,"a":64,"b":65,"c":66,"d":67,"e":68,"f":69,"g":70,"h":71,"i":72,"j":73,"k":74,"l":75,"m":76,"n":77,"o":78,"p":79,"q":80,"r":81,"s":82,"t":83,"u":84,"v":85,"w":86,"x":87,"y":88,"z":89,"{":90,"|":91,"}":92,"~":93,"¡":94,"¢":95,"£":96,"¤":97,"¥":98,"¦":99,"§":100,"¨":101,"©":102,"ª":103,"«":104,"¬":105,"®":106,"¯":107,"°":108,"±":109,"²":110,"³":111,"´":112,"µ":113,"¶":114,"·":115,"¸":116,"¹":117,"º":118,"»":119,"¼":120,"½":121,"¾":122,"¿":123,"À":124,"Á":125,"Â":126,"Ã":127,"Ä":128,"Å":129,"Æ":130,"Ç":131,"È":132,"É":133,"Ê":134,"Ë":135,"Ì":136,"Í":137,"Î":138,"Ï":139,"Ð":140,"Ñ":141,"Ò":142,"Ó":143,"Ô":144,"Õ":145,"Ö":146,"×":147,"Ø":148,"Ù":149,"Ú":150,"Û":151,"Ü":152,"Ý":153,"Þ":154,"ß":155,"à":156,"á":157,"â":158,"ã":159,"ä":160,"å":161,"æ":162,"ç":163,"è":164,"é":165,"ê":166,"ë":167,"ì":168,"í":169,"î":170,"ï":171,"ð":172,"ñ":173,"ò":174,"ó":175,"ô":176,"õ":177,"ö":178,"÷":179,"ø":180,"ù":181,"ú":182,"û":183,"ü":184,"ý":185,"þ":186,"ÿ":187,"Ā":188,"ā":189,"Ă":190,"ă":191,"Ą":192,"ą":193,"Ć":194,"ć":195,"Ĉ":196,"ĉ":197,"Ċ":198,"ċ":199,"Č":200,"č":201,"Ď":202,"ď":203,"Đ":204,"đ":205,"Ē":206,"ē":207,"Ĕ":208,"ĕ":209,"Ė":210,"ė":211,"Ę":212,"ę":213,"Ě":214,"ě":215,"Ĝ":216,"ĝ":217,"Ğ":218,"ğ":219,"Ġ":220,"ġ":221,"Ģ":222,"ģ":223,"Ĥ":224,"ĥ":225,"Ħ":226,"ħ":227,"Ĩ":228,"ĩ":229,"Ī":230,"ī":231,"Ĭ":232,"ĭ":233,"Į":234,"į":235,"İ":236,"ı":237,"IJ":238,"ij":239,"Ĵ":240,"ĵ":241,"Ķ":242,"ķ":243,"ĸ":244,"Ĺ":245,"ĺ":246,"Ļ":247,"ļ":248,"Ľ":249,"ľ":250,"Ŀ":251,"ŀ":252,"Ł":253,"ł":254,"Ń":255,"ĠĠ":256,"ĠĠĠĠ":257,"in":258,"Ġt":259,"ĠĠĠĠĠĠĠĠ":260,"er":261,"ĠĠĠ":262,"on":263,"Ġa":264,"re":265,"at":266,"st":267,"en":268,"or":269,"Ġth":270,"ĊĊ":271,"Ġc":272,"le":273,"Ġs":274,"it":275,"an":276,"ar":277,"al":278,"Ġthe":279,";Ċ":280,"Ġp":281,"Ġf":282,"ou":283,"Ġ=":284,"is":285,"ĠĠĠĠĠĠĠ":286,"ing":287,"es":288,"Ġw":289,"ion":290,"ed":291,"ic":292,"Ġb":293,"Ġd":294,"et":295,"Ġm":296,"Ġo":297,"ĉĉ":298,"ro":299,"as":300,"el":301,"ct":302,"nd":303,"Ġin":304,"Ġh":305,"ent":306,"id":307,"Ġn":308,"am":309,"ĠĠĠĠĠĠĠĠĠĠĠ":310,"Ġto":311,"Ġre":312,"--":313,"Ġ{":314,"Ġof":315,"om":316,");Ċ":317,"im":318,"čĊ":319,"Ġ(":320,"il":321,"//":322,"Ġand":323,"ur":324,"se":325,"Ġl":326,"ex":327,"ĠS":328,"ad":329,"Ġ\"":330,"ch":331,"ut":332,"if":333,"**":334,"Ġ}":335,"em":336,"ol":337,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":338,"th":339,")Ċ":340,"Ġ{Ċ":341,"Ġg":342,"ig":343,"iv":344,",Ċ":345,"ce":346,"od":347,"Ġv":348,"ate":349,"ĠT":350,"ag":351,"ay":352,"Ġ*":353,"ot":354,"us":355,"ĠC":356,"Ġst":357,"ĠI":358,"un":359,"ul":360,"ue":361,"ĠA":362,"ow":363,"Ġ'":364,"ew":365,"Ġ<":366,"ation":367,"()":368,"Ġfor":369,"ab":370,"ort":371,"um":372,"ame":373,"Ġis":374,"pe":375,"tr":376,"ck":377,"âĢ":378,"Ġy":379,"ist":380,"----":381,".ĊĊ":382,"he":383,"Ġe":384,"lo":385,"ĠM":386,"Ġbe":387,"ers":388,"Ġon":389,"Ġcon":390,"ap":391,"ub":392,"ĠP":393,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":394,"ass":395,"int":396,">Ċ":397,"ly":398,"urn":399,"Ġ$":400,";ĊĊ":401,"av":402,"port":403,"ir":404,"->":405,"nt":406,"ction":407,"end":408,"Ġde":409,"ith":410,"out":411,"turn":412,"our":413,"ĠĠĠĠĠ":414,"lic":415,"res":416,"pt":417,"==":418,"Ġthis":419,"Ġwh":420,"Ġif":421,"ĠD":422,"ver":423,"age":424,"ĠB":425,"ht":426,"ext":427,"=\"":428,"Ġthat":429,"****":430,"ĠR":431,"Ġit":432,"ess":433,"ĠF":434,"Ġr":435,"os":436,"and":437,"Ġas":438,"ect":439,"ke":440,"rom":441,"Ġ//":442,"con":443,"ĠL":444,"(\"":445,"qu":446,"lass":447,"Ġwith":448,"iz":449,"de":450,"ĠN":451,"Ġal":452,"op":453,"up":454,"get":455,"Ġ}Ċ":456,"ile":457,"Ġan":458,"ata":459,"ore":460,"ri":461,"Ġpro":462,";čĊ":463,"ĉĉĉĉ":464,"ter":465,"ain":466,"ĠW":467,"ĠE":468,"Ġcom":469,"Ġreturn":470,"art":471,"ĠH":472,"ack":473,"import":474,"ublic":475,"Ġor":476,"est":477,"ment":478,"ĠG":479,"able":480,"Ġ-":481,"ine":482,"ill":483,"ind":484,"ere":485,"::":486,"ity":487,"Ġ+":488,"Ġtr":489,"elf":490,"ight":491,"('":492,"orm":493,"ult":494,"str":495,"..":496,"\",":497,"Ġyou":498,"ype":499,"pl":500,"Ġnew":501,"Ġj":502,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":503,"Ġfrom":504,"Ġex":505,"ĠO":506,"ld":507,"Ġ[":508,"oc":509,":Ċ":510,"Ġse":511,"Ġle":512,"--------":513,".s":514,"{Ċ":515,"',":516,"ant":517,"Ġat":518,"ase":519,".c":520,"Ġch":521,"</":522,"ave":523,"ang":524,"Ġare":525,"Ġint":526,"âĢĻ":527,"_t":528,"Line truncated