Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,41 @@
+---
+base_model: burtenshaw/Qwen3-30B-A3B-python-coder
+datasets: burtenshaw/tulu-3-sft-personas-code-no-prompt
+library_name: mlx
+model_name: Qwen3-30B-A3B-python-coder
+tags:
+- generated_from_trainer
+- trl
+- sft
+- mlx
+licence: license
+pipeline_tag: text-generation
+---
+
+# jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx
+
+This model [jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx](https://huggingface.co/jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx) was
+converted to MLX format from [burtenshaw/Qwen3-30B-A3B-python-coder](https://huggingface.co/burtenshaw/Qwen3-30B-A3B-python-coder)
+using mlx-lm version **0.24.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

added_tokens.json

@@ -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
+}

config.json

@@ -0,0 +1,46 @@
+{
+    "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,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "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
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2bbd7c5fdd8307218e1e3607e6f5b497e5a4ad662ba9dceba618e5092bc4dc
+size 5319507334

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becbd72fa9283968ba3e7760995d6734d6ad1559965e0e1046cead1c012e55f9
+size 5364678700

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ba2116ec4346ebe76fd1fa529020c57570241783e41de3c50012c8277ac116
+size 5274790267

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e33952a2c12628255116e5a55dce40a34501f4c87a87257e834f55cf206496
+size 1215804237

special_tokens_map.json

@@ -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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -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
+}

train.py

@@ -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")