Upload quantized model Olmo-3.1-32B-Instruct-SFT-AutoRound-W4A16-Tuning

README.md

@@ -0,0 +1,178 @@
+---
+base_model:
+- allenai/Olmo-3.1-32B-Instruct-SFT
+pipeline_tag: text-generation
+tags:
+- quantized
+- w4a16
+- tuning
+- low-bit-open-llm-leaderboard
+---
+
+# Olmo-3.1-32B-Instruct-SFT-AutoRound-W4A16-Tuning
+
+## Model Details
+
+This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of [allenai/Olmo-3.1-32B-Instruct-SFT](https://huggingface.co/allenai/Olmo-3.1-32B-Instruct-SFT) generated by TUNING. Please follow the license of the original model.
+
+## Quantization Details
+
+| Attribute | Value |
+|-----------|-------|
+| Base Model | [allenai/Olmo-3.1-32B-Instruct-SFT](https://huggingface.co/allenai/Olmo-3.1-32B-Instruct-SFT) |
+| Quantization Tool | TUNING |
+| Quantization Scheme | W4A16 |
+| Quantized Size | 17422 MB |
+
+## Evaluation Results
+
+| Task | Accuracy |
+|------|----------|
+| hellaswag | 0.6119 |
+| mmlu | 0.6864 |
+| mmlu_abstract_algebra | 0.4900 |
+| mmlu_anatomy | 0.5704 |
+| mmlu_astronomy | 0.8289 |
+| mmlu_business_ethics | 0.7200 |
+| mmlu_clinical_knowledge | 0.7660 |
+| mmlu_college_biology | 0.8611 |
+| mmlu_college_chemistry | 0.4300 |
+| mmlu_college_computer_science | 0.6900 |
+| mmlu_college_mathematics | 0.5400 |
+| mmlu_college_medicine | 0.6763 |
+| mmlu_college_physics | 0.5686 |
+| mmlu_computer_security | 0.7900 |
+| mmlu_conceptual_physics | 0.7574 |
+| mmlu_econometrics | 0.5965 |
+| mmlu_electrical_engineering | 0.6759 |
+| mmlu_elementary_mathematics | 0.6164 |
+| mmlu_formal_logic | 0.5873 |
+| mmlu_global_facts | 0.4500 |
+| mmlu_high_school_biology | 0.8581 |
+| mmlu_high_school_chemistry | 0.6404 |
+| mmlu_high_school_computer_science | 0.8500 |
+| mmlu_high_school_european_history | 0.7879 |
+| mmlu_high_school_geography | 0.8535 |
+| mmlu_high_school_government_and_politics | 0.9119 |
+| mmlu_high_school_macroeconomics | 0.7462 |
+| mmlu_high_school_mathematics | 0.4963 |
+| mmlu_high_school_microeconomics | 0.8277 |
+| mmlu_high_school_physics | 0.5894 |
+| mmlu_high_school_psychology | 0.8936 |
+| mmlu_high_school_statistics | 0.6944 |
+| mmlu_high_school_us_history | 0.8382 |
+| mmlu_high_school_world_history | 0.8523 |
+| mmlu_human_aging | 0.7085 |
+| mmlu_human_sexuality | 0.7481 |
+| mmlu_humanities | 0.5915 |
+| mmlu_international_law | 0.8017 |
+| mmlu_jurisprudence | 0.8241 |
+| mmlu_logical_fallacies | 0.8589 |
+| mmlu_machine_learning | 0.6518 |
+| mmlu_management | 0.8252 |
+| mmlu_marketing | 0.8803 |
+| mmlu_medical_genetics | 0.7700 |
+| mmlu_miscellaneous | 0.8365 |
+| mmlu_moral_disputes | 0.7543 |
+| mmlu_moral_scenarios | 0.2927 |
+| mmlu_nutrition | 0.8268 |
+| mmlu_other | 0.7367 |
+| mmlu_philosophy | 0.7396 |
+| mmlu_prehistory | 0.7593 |
+| mmlu_professional_accounting | 0.4894 |
+| mmlu_professional_law | 0.4817 |
+| mmlu_professional_medicine | 0.7096 |
+| mmlu_professional_psychology | 0.7353 |
+| mmlu_public_relations | 0.6455 |
+| mmlu_security_studies | 0.7673 |
+| mmlu_social_sciences | 0.7966 |
+| mmlu_sociology | 0.8308 |
+| mmlu_stem | 0.6708 |
+| mmlu_us_foreign_policy | 0.8900 |
+| mmlu_virology | 0.5241 |
+| mmlu_world_religions | 0.8304 |
+| piqa | 0.7867 |
+
+## How to Use
+
+### HF Usage
+
+**Step 1: Install [AutoRound](https://github.com/intel/auto-round)**
+
+```bash
+pip install auto-round
+```
+
+**Step 2: Load and run the quantized model**
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Olmo-3.1-32B-Instruct-SFT-AutoRound-W4A16-Tuning"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+
+# prepare the model input
+prompt = "Write a quick sort algorithm."
+messages = [{"role": "user", "content": prompt}]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(**model_inputs, max_new_tokens=512)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()
+
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+print("content:", content)
+```
+
+### VLLM Usage
+
+```bash
+vllm serve Olmo-3.1-32B-Instruct-SFT-AutoRound-W4A16-Tuning \
+    --trust-remote-code \
+    --dtype bfloat16 \
+    --tensor_parallel_size 1
+```
+
+If you encounter any issues, feel free to open an issue on the [AutoRound GitHub repo](https://github.com/intel/auto-round/issues) or provide feedback on the [Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard).
+
+## Ethical Considerations and Limitations
+
+The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
+Therefore, before deploying any applications of the model, developers should perform safety testing.
+
+## Caveats and Recommendations
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
+Here are a couple of useful links to learn more about Intel's AI software:
+
+- [Intel Neural Compressor](https://github.com/intel/neural-compressor)
+- [AutoRound](https://github.com/intel/auto-round)
+
+## Disclaimer
+
+The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
+
+## Cite
+
+```
+@article{cheng2023optimize,
+  title={Optimize weight rounding via signed gradient descent for the quantization of llms},
+  author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
+  journal={arXiv preprint arXiv:2309.05516},
+  year={2023}
+}
+```
+
+[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
+
+---
+
+*This model is part of the [Intel Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard) initiative.*

chat_template.jinja

@@ -0,0 +1,16 @@
+{%- set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 -%}{%- if not has_system -%}{{- '<|im_start|>system
+You are a helpful function-calling AI assistant. ' -}}{%- if tools is none or (tools | length) == 0 -%}{{- 'You do not currently have access to any functions. <functions></functions><|im_end|>
+' -}}{%- else -%}{{- 'You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Do not make assumptions about what values to plug into functions.' -}}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions><|im_end|>
+' -}}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system
+' + message['content'] -}}{%- if tools is not none -%}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions>' -}}{%- elif message.get('functions', none) is not none -%}{{- ' <functions>' + message['functions'] + '</functions>' -}}{%- endif -%}{{- '<|im_end|>
+' -}}{%- elif message['role'] == 'user' -%}{{- '<|im_start|>user
+' + message['content'] + '<|im_end|>
+' -}}{%- elif message['role'] == 'assistant' -%}{{- '<|im_start|>assistant
+' -}}{%- if message.get('content', none) is not none -%}{{- message['content'] -}}{%- endif -%}{%- if message.get('function_calls', none) is not none -%}{{- '<function_calls>' + message['function_calls'] + '</function_calls>' -}}{% elif message.get('tool_calls', none) is not none %}{{- '<function_calls>' -}}{%- for tool_call in message['tool_calls'] %}{%- if tool_call is mapping and tool_call.get('function', none) is not none %}{%- set args = tool_call['function']['arguments'] -%}{%- set ns = namespace(arguments_list=[]) -%}{%- for key, value in args.items() -%}{%- set ns.arguments_list = ns.arguments_list + [key ~ '=' ~ (value | tojson)] -%}{%- endfor -%}{%- set arguments = ns.arguments_list | join(', ') -%}{{- tool_call['function']['name'] + '(' + arguments + ')' -}}{%- if not loop.last -%}{{ '
+' }}{%- endif -%}{% else %}{{- tool_call -}}{%- endif %}{%- endfor %}{{- '</function_calls>' -}}{%- endif -%}{%- if not loop.last -%}{{- '<|im_end|>' + '
+' -}}{%- else -%}{{- eos_token -}}{%- endif -%}{%- elif message['role'] == 'environment' -%}{{- '<|im_start|>environment
+' + message['content'] + '<|im_end|>
+' -}}{%- elif message['role'] == 'tool' -%}{{- '<|im_start|>environment
+' + message['content'] + '<|im_end|>
+' -}}{%- endif -%}{%- if loop.last and add_generation_prompt -%}{{- '<|im_start|>assistant
+' -}}{%- endif -%}{%- endfor -%}

config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Olmo3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 65536,
+  "model_type": "olmo3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 100277,
+  "quantization_config": {
+    "autoround_version": "0.13.0",
+    "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "data_type": "int",
+    "group_size": 128,
+    "low_gpu_mem_usage": true,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "attention_factor": 1.2079441541679836,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 8.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "yarn"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_cache": true,
+  "vocab_size": 100278
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    100265,
+    100257
+  ],
+  "transformers_version": "5.10.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45ed574925f675fcb19fc738b55f13f2167101f669dd44467d461acdd585ede
+size 4987661680

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e46e5f0a110a68923a22979c2e648cb3180079f552d790d2ad8442478b75b12
+size 4993511008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def780c043d59cdea3bd7ccf80f13fe8b4d77eb909b3fa0c2a10f51834b3a1c3
+size 4993511016

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fd74993af7ac3c0b8df83b2215c732ba07b8432255f18534a0317dacbd6553
+size 3293596080

quantization_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "data_type": "int",
+  "group_size": 128,
+  "sym": true,
+  "low_gpu_mem_usage": true,
+  "autoround_version": "0.13.0",
+  "block_name_to_quantize": "model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 65536,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}