Upload folder using huggingface_hub

.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 +1,105 @@
+---
+base_model: kd13/Coder-o1-mini-reasoning
+library_name: transformers
+pipeline_tag: text-generation
+license: mit
+language:
+- en
+tags:
+- awq
+- w4a16
+- compressed-tensors
+- quantized
+- vllm
+- code
+- text-generation
+---
+
+# Coder-o1-mini-reasoning - AWQ
+
+4-bit AWQ quantization of [kd13/Coder-o1-mini-reasoning](https://huggingface.co/kd13/Coder-o1-mini-reasoning), a compact
+Python-focused reasoning model for coding assistance, debugging, code explanation, and
+math/logic reasoning.
+
+Quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) using
+`AWQModifier` + `W4A16_ASYM`. Calibrated on 256 code-instruction samples at
+2048 tokens, with the model's own chat template applied.
+
+`lm_head` is left at full precision. Weights are 4-bit; activations stay 16-bit.
+
+## Format
+
+This is **compressed-tensors** format, which is what current AWQ tooling produces.
+vLLM and transformers both detect it automatically from `config.json` — you do not need
+to pass `--quantization awq`. The older AutoAWQ format is not interchangeable with this
+one; if a loader expects `quant_config.json`, it wants the legacy format and will not
+read this repo.
+
+## Usage
+
+### vLLM
+
+```bash
+vllm serve kd13/Coder-o1-mini-reasoning-AWQ --max-model-len 8192
+```
+
+### Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("kd13/Coder-o1-mini-reasoning-AWQ", device_map="auto")
+tok = AutoTokenizer.from_pretrained("kd13/Coder-o1-mini-reasoning-AWQ")
+
+msgs = [
+    {"role": "system", "content": "You are a helpful Python coding assistant."},
+    {"role": "user", "content": "Explain list comprehensions with an example."},
+]
+prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
+ids = tok(prompt, return_tensors="pt").to(model.device)
+print(tok.decode(model.generate(**ids, max_new_tokens=300)[0]))
+```
+
+Requires `pip install compressed-tensors`.
+
+## Hardware
+
+A CUDA GPU is required — AWQ has no CPU path. For local or CPU inference use the GGUF
+build instead.
+
+On Ampere or newer (compute capability 8.0+) vLLM uses the Marlin kernel, which is where
+the throughput gains come from. Turing cards such as the T4 fall back to a slower kernel
+and see much less benefit.
+
+## Chat template
+
+ChatML, with Qwen-style tool calling:
+
+```
+<|im_start|>system
+{system}<|im_end|>
+<|im_start|>user
+{message}<|im_end|>
+<|im_start|>assistant
+```
+
+Tool definitions are injected into the system message inside `<tools>` tags, and the
+model replies with a JSON object inside `<tool_call>` tags. Tool results are returned
+wrapped in `<tool_response>`. vLLM exposes this through its OpenAI-compatible `tools`
+parameter.
+
+A default system prompt is applied when you do not supply one. Pass an explicit system
+prompt to control the assistant's stated identity.
+
+## Limitations
+
+Everything in the [base model card](https://huggingface.co/kd13/Coder-o1-mini-reasoning) applies. This is
+a small experimental reasoning model: good for Python learning, debugging help, code
+explanation, and basic-to-intermediate problems. Not suited to hard competitive
+programming, complex algorithmic work, non-Python languages, security-sensitive code, or
+production use without review.
+
+4-bit quantization does not improve any of that. Expect 1-3% degradation on most tasks,
+concentrated in exactly the long multi-step reasoning this model is already weakest at.
+If quality matters more than memory, use the unquantized model or an 8-bit build.
+Always test generated code.

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are MUA o1 Pro, created by OumuamuaAI. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are MUA o1 Pro, created by OumuamuaAI. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "group",
+          "symmetric": false,
+          "type": "int",
+          "zp_dtype": "torch.int8"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.17.1"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "5.10.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc30d06f1691109894ae79f37cc0a7146972f08c1908a9af6fd5001803347d5
+size 1147001472

recipe.yaml

@@ -0,0 +1,23 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*v_proj$
+        balance_layers: ['re:.*o_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+        activation_hook_target: null
+      duo_scaling: both
+      n_grid: 20
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: W4A16_ASYM
+      bypass_divisibility_checks: false

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}