Upload 7 files

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 21,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 2,
+  "transformers_version": "5.2.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b517d4a950a083dfac9aa1d16f3c05103b3b00a83f926ee6f8d2fc2dbb717293
+size 121699864

readme.md

@@ -0,0 +1,124 @@
+**Model Card: Stentor Python 30M**
+
+**Model Description**
+
+Stentor Python 30M is a compact language model specifically fine-tuned for Python code generation and autocompletion tasks. Based on the Stentor-30M architecture, this model contains 30 million parameters and is designed to run efficiently on resource-constrained devices including mobile phones and embedded systems.
+
+**Model Details**
+
+- **Developed by:** Experimental fine-tuning project
+- **Model type:** Causal language model (LlamaForCausalLM)
+- **Language:** Python code, English instructions
+- **Parameters:** 30,419,712
+- **Context length:** 512 tokens
+- **Model size:** 60 MB (FP16), 30 MB (INT8)
+- **License:** Apache 2.0
+
+**Training Data**
+
+The model was fine-tuned on a curated dataset of 872 Python examples, including:
+
+- Basic algorithms (factorial, prime numbers, list operations)
+- Class implementations (Stack, BankAccount, Rectangle, Circle)
+- Recursive functions (quicksort, Fibonacci)
+- String manipulation (palindrome, anagram, vowel counting)
+- MBPP (Mostly Basic Python Problems) dataset tasks
+
+All examples follow a consistent format with "### Task:" instruction and "### Solution:" code block.
+
+**Training Process**
+
+The fine-tuning process involved multiple stages:
+
+1. Base model: Stentor-30M pre-trained checkpoint
+2. Initial fine-tuning on 50k examples (checkpoint-1000 selected as best)
+3. Multiple correction rounds with progressively lower learning rates
+4. Final detoxification training with learning rate 3e-7 to remove undesirable patterns
+
+**Evaluation Results**
+
+The model was evaluated on several test categories:
+
+| Category | Pass Rate | Notes |
+|----------|-----------|-------|
+| Basic functions | 80% | Factorial, prime check, etc. |
+| Classes from training set | 100% | Stack, BankAccount, Rectangle |
+| New complex classes | 33% | Graph, Queue, inheritance |
+| Function signatures (MBPP) | 100% | Correctly generates def statements |
+
+**Capabilities**
+
+- Generates Python functions from natural language descriptions
+- Implements basic algorithms (factorial, prime check, palindrome)
+- Creates class definitions with methods (Stack, BankAccount, Rectangle)
+- Handles recursive functions (quicksort, Fibonacci)
+- Produces syntactically correct function signatures
+
+**Limitations**
+
+- May produce repeated or redundant code after the main solution
+- Struggles with complex data structures (graphs, trees, queues)
+- Does not reliably handle class inheritance patterns
+- Can generate incorrect list indexing operations
+- May continue generating text beyond the intended solution
+- Limited to 512 token context window
+- Not suitable for production use without output post-processing
+
+**Recommended Use Cases**
+
+- Code autocompletion in lightweight IDEs
+- Educational tool for Python beginners
+- Rapid prototyping of simple functions
+- Embedded systems with limited computational resources
+- Offline code assistance on mobile devices
+
+**Not Recommended For**
+
+- Complex algorithm implementation
+- Production code generation without human review
+- Tasks requiring deep contextual understanding
+- Generating large codebases
+- Security-critical applications
+
+**Usage Example**
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_path = "path/to/stentor-python-30m"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+
+prompt = "### Task: Write a function that checks if a number is even\n\n### Solution:\n"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.2)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+**Hardware Requirements**
+
+- **Inference:** CPU only (no GPU required)
+- **RAM:** < 100 MB for inference
+- **Storage:** 60 MB (FP16), 30 MB (INT8 quantized)
+
+**Ethical Considerations**
+
+This model is intended for educational and development assistance purposes. Users should verify all generated code before deployment, particularly for security-sensitive applications. The model may occasionally produce incorrect or inefficient code and should not be relied upon as the sole source of truth for programming tasks.
+
+**Citation**
+
+If you use this model in your work, please cite:
+
+```
+@misc{stentor-python-30m-2026,
+  author = {Fine-tuning Experiment},
+  title = {Stentor Python 30M: A Compact Model for Python Code Generation},
+  year = {2026},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/username/stentor-python-30m}
+}
+```
+
+**Contact**
+
+For questions or feedback about this model, please open an issue on the Hugging Face repository.

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": false,
+  "model_max_length": 512,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}