commit f41096960dad53e32a45b18159143d06efbca3f8 Author: ModelHub XC Date: Sat Aug 1 07:59:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: EphAsad/Atem-v1-1.5B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9dad320 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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 +qwen2.5-1.5b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-1.5b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-1.5b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-1.5b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Logo.png filter=lfs diff=lfs merge=lfs -text diff --git a/Atem-1.5b.Q4_K_M.gguf b/Atem-1.5b.Q4_K_M.gguf new file mode 100644 index 0000000..b19134e --- /dev/null +++ b/Atem-1.5b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c67ac50d5467d6d4502de1a7c0b7652902f665cff0e29a2dce9fc47d53705025 +size 986048544 diff --git a/Atem-1.5b.Q5_K_M.gguf b/Atem-1.5b.Q5_K_M.gguf new file mode 100644 index 0000000..b49350d --- /dev/null +++ b/Atem-1.5b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376b7245319c4c160b8650de626d7461c3165ff2d3408efbba438597894c8d04 +size 1125050400 diff --git a/Atem-1.5b.Q8_0.gguf b/Atem-1.5b.Q8_0.gguf new file mode 100644 index 0000000..169f865 --- /dev/null +++ b/Atem-1.5b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e943e8a2f0b25043f5d89952454aa32b838a954152c417b44933bd1a0062da22 +size 1646573088 diff --git a/Logo.png b/Logo.png new file mode 100644 index 0000000..2f31b1d --- /dev/null +++ b/Logo.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036d268ac79d1a5355a5ea602fc02ba312f4938c3506ddfa148ec7de44b69607 +size 981796 diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..0d16c1c --- /dev/null +++ b/Modelfile @@ -0,0 +1,56 @@ +FROM Atem-1.5b.Q4_K_M.gguf +TEMPLATE """{{- if .Messages }} +{{- if or .System .Tools }}<|im_start|>system +{{- if .System }} +{{ .System }} +{{- end }} +{{- if .Tools }} + +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within XML tags: + +{"name": , "arguments": } + +{{- end }}<|im_end|> +{{ end }} +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 -}} +{{- if eq .Role "user" }}<|im_start|>user +{{ .Content }}<|im_end|> +{{ else if eq .Role "assistant" }}<|im_start|>assistant +{{ if .Content }}{{ .Content }} +{{- else if .ToolCalls }} +{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} +{{ end }} +{{- end }}{{ if not $last }}<|im_end|> +{{ end }} +{{- else if eq .Role "tool" }}<|im_start|>user + +{{ .Content }} +<|im_end|> +{{ end }} +{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant +{{ end }} +{{- end }} +{{- else }} +{{- if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""" +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|endoftext|>" +PARAMETER temperature 0.7 +PARAMETER min_p 0.1 +SYSTEM """You are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.""" \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..33da019 --- /dev/null +++ b/README.md @@ -0,0 +1,423 @@ +--- +language: +- en +license: apache-2.0 +base_model: +- Qwen/Qwen2.5-1.5B-Instruct +tags: +- text-generation +- qwen2 +- unsloth +- lora +- gguf +- llama.cpp +- reasoning +- distillation +- conversational +pipeline_tag: text-generation +library_name: transformers +datasets: +- EphAsad/QWENMillenium-SF +- EphAsad/Phi4Millennium-SF +- EphAsad/MistralMillenium-SF +- Modotte/CodeX-2M-Thinking +- Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned +- WithinUsAI/MiniMax_M2.7_Distilled_5k +- tuanha1305/DeepSeek-R1-Distill +- open-r1/OpenThoughts-114k-math +- flytech/python-codes-25k +- FreedomIntelligence/medical-o1-reasoning-SFT +model-index: +- name: Atem v1 + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: ARC-Challenge + type: ai2_arc + config: ARC-Challenge + split: test + metrics: + - type: acc_norm + value: 0.455 + name: Accuracy (normalised) + verified: false + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8K + type: gsm8k + split: test + metrics: + - type: exact_match + value: 0.530 + name: Exact Match (strict, zero-shot) + verified: false + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag + type: hellaswag + split: validation + metrics: + - type: acc_norm + value: 0.644 + name: Accuracy (normalised) + verified: false +--- +

+ Atem Logo +

+ +

Atem v1

+ +

+ Ancient logic. Modern intelligence. +

+ +

+ A 1.5B reasoning model trained via multi-source knowledge distillation from frontier teacher models. +

+ +

+ Base Model + Method + Parameters + License +

+ +--- + +## Overview + +Atem is a 1.5B parameter reasoning model built via supervised fine-tuning on a curated corpus of approximately 115,000 examples distilled from multiple frontier teacher models. Starting from Qwen2.5-1.5B-Instruct, Atem was trained using LoRA to preserve base model capabilities while improving performance on reasoning, mathematics, and coding tasks. + +This is **Stage 1** of a planned multi-stage training series. Stage 1 focuses on establishing strong general reasoning across domains. Stage 2 layers chain-of-thought thinking traces on top of this foundation. +Stage 2 is [Atem-Wisdom](https://huggingface.co/EphAsad/Atem-Wisdom-1.5B) which builds on this foundation by adding explicit chain-of-thought reasoning — the model works through problems inside tags before producing its final answer. + +--- + +## Model Details + +| Property | Value | +|----------|-------| +| **Base model** | Qwen/Qwen2.5-1.5B-Instruct | +| **Training method** | LoRA Supervised Fine-Tuning (Stage 1) | +| **LoRA config** | r=32, alpha=64, dropout=0.05 | +| **Target modules** | q, k, v, o, gate, up, down projections | +| **Parameters** | ~1.54B | +| **Training records** | ~114,932 | +| **Epochs** | 1 | +| **Effective batch size** | 64 (batch 8 × grad accum 8) | +| **Learning rate** | 2e-4, cosine schedule, 5% warmup | +| **Final train loss** | 0.940 | +| **Final val loss** | 0.890 | +| **Hardware** | NVIDIA A100-SXM4 80GB | +| **Max sequence length** | 4,096 tokens | +| **Precision** | bfloat16 | +| **License** | Apache 2.0 | + +--- + +## Intended Use + +Atem is designed for open-ended reasoning tasks where structured, accurate thinking adds value: + +- Code explanation, implementation, and debugging +- Mathematical problem solving with working shown +- Analytical reasoning and hypothesis evaluation +- Concept explanation and comparative analysis +- Logic, argument, and fallacy identification + +Atem is **not** designed for retrieval-heavy factual lookup, real-time information, or tasks requiring broad knowledge breadth beyond its training domains. + +--- + +## Training Data + +Atem was trained on a corpus assembled from eleven sources, combining domain-specific generated datasets and publicly available distillation datasets from frontier models. All outputs containing `` reasoning traces were stripped to clean final responses for Stage 1 training. + +| Dataset | Records | Source / Teacher | +|---------|---------|-----------------| +| EphAsad/QWENMillenium-SF | 5,000 | Qwen2.5-14B — Analytical & Scientific | +| EphAsad/Phi4Millennium-SF | 2,932 | Phi-4 14B — Mathematical Reasoning | +| EphAsad/MistralMillenium-SF | 5,000 | Mistral-Nemo-12B — Language & Comprehension | +| Modotte/CodeX-2M-Thinking | 30,000 | Mixed — Coding | +| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned | 23,000 | Kimi K2.5 — General Distillation (English filtered) | +| WithinUsAI/MiniMax_M2.7_Distilled_5k | 5,000 | MiniMax M2.7 | +| tuanha1305/DeepSeek-R1-Distill | 9,000 | DeepSeek-R1 | +| open-r1/OpenThoughts-114k-math | 10,000 | Mixed — Mathematics (correct answers only) | +| flytech/python-codes-25k | 10,000 | Python coding | +| FreedomIntelligence/medical-o1-reasoning-SFT | 10,000 | Medical reasoning (English config) | +| Private dataset | 5,000 | Undisclosed | +| **Total** | **~114,932** | | + +The QWENMillenium-SF, Phi4Millennium-SF, and MistralMillenium-SF datasets were generated specifically for this project via batched inference on Colab A100. OpenThoughts-114k-math was filtered to verified correct solutions only before sampling. + +--- + +## Training Configuration + +```python +# Key hyperparameters +lora_r = 32 +lora_alpha = 64 +lora_dropout = 0.05 +max_seq_length = 4096 +learning_rate = 2e-4 +lr_scheduler = 'cosine' +warmup_ratio = 0.05 +batch_size = 8 +grad_accumulation = 8 # effective batch size: 64 +num_epochs = 1 +dtype = bfloat16 +load_in_4bit = True # during training +``` + +Training used Unsloth with `train_on_responses_only` masking, ensuring loss was computed exclusively on assistant response tokens. A three-part pre-training validation was run before training: chat template replacement verification, think tag strip confirmation, and mask sanity check. + +After training, LoRA adapters were merged into the base weights and exported as a full merged model. + +**Loss curve:** + +| Step | Train Loss | Val Loss | +|------|-----------|----------| +| 500 | 0.990 | 0.920 | +| 1000 | 1.020 | 0.900 | +| 1500 | 0.960 | 0.890 | +| Final | **0.940** | **0.890** | + +Validation loss converged at 0.890, with a final train/val gap of 0.050 — indicating no overfitting over the single epoch. + +--- + +## Evaluation + +### Benchmark Results + +Evaluated against Qwen2.5-1.5B-Instruct (base model) using lm-evaluation-harness with identical conditions: 4-bit inference, batch size 16, zero-shot strict evaluation. + +| Task | Base (1.5B) | Atem v1 (1.5B) | Delta | +|------|------------|----------------|-------| +| ARC-Challenge | 43.7% | 45.5% | +1.8% ✓ | +| GSM8K | 23.0% | **53.0%** | **+30.0%** ✓ | +| HellaSwag | 66.8% | 64.4% | -2.4% | + +The GSM8K result is the primary finding. A +30 percentage point improvement on grade school mathematics reflects the targeted training on verified correct mathematical reasoning examples from multiple frontier teacher models. + +The HellaSwag regression of 2.4% is within normal benchmark variance and represents a significant improvement over a prior exploratory training run using full fine-tune, which produced a 16.2% regression on the same benchmark. LoRA preserved base model commonsense capabilities as intended. + +### Comparison vs Qwen2.5-7B-Instruct + +To contextualise the GSM8K result, Atem was benchmarked against Qwen2.5-7B-Instruct under the same zero-shot strict evaluation conditions. + +| Model | Parameters | GSM8K (zero-shot strict) | +|-------|-----------|--------------------------| +| Qwen2.5-1.5B-Instruct | 1.5B | 23.0% | +| **Atem v1** | **1.5B** | **53.0%** | +| Qwen2.5-7B-Instruct | 7B | 74.9% | + +At baseline, the 1.5B model sits 51.9 points below the 7B. After training, Atem sits 21.9 points below — closing approximately **58% of the capability gap** between 1.5B and 7B on mathematical reasoning. Atem achieves **71% of Qwen2.5-7B's GSM8K performance at 22% of its parameter count**. + +Note: Official Qwen2.5-7B-Instruct scores (91.6% GSM8K) use 4-shot chain-of-thought prompting. The 74.9% figure above reflects the same zero-shot strict evaluation format used for Atem, ensuring a fair direct comparison. + +### Qualitative Evaluation + +Atem was evaluated against Qwen2.5-1.5B-Instruct across 30 domain-representative questions using matched system prompts, ensuring differences in output reflect trained capability rather than prompt engineering. + +| Domain | Questions | Outcome | +|--------|-----------|---------| +| Coding | 8 | Atem stronger — more thorough, better structured, catches edge cases | +| Mathematics | 6 | Comparable — both accurate on standard problems | +| Analytical Reasoning | 6 | Atem stronger — better structured arguments | +| General Knowledge | 5 | Comparable | +| Language & Logic | 5 | Atem stronger — correct fallacy identification, greater depth | + +--- + +## Usage + +### Transformers + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_name = "EphAsad/Atem-v1-1.5B" + +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +messages = [ + { + "role": "user", + "content": "Write a Python function that checks whether a number is prime." + } +] + +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt" +).to(model.device) + +with torch.no_grad(): + output = model.generate( + input_ids=inputs, + max_new_tokens=1000, + temperature=0.7, + top_p=0.9, + repetition_penalty=1.1, + do_sample=True, + ) + +response = tokenizer.decode( + output[0][inputs.shape[1]:], + skip_special_tokens=True +) +print(response) +``` + +### Unsloth (faster inference) + +```python +from unsloth import FastLanguageModel +import torch + +model, tokenizer = FastLanguageModel.from_pretrained( + model_name="EphAsad/Atem-v1-1.5B", + max_seq_length=4096, + dtype=torch.bfloat16, + load_in_4bit=True, +) +FastLanguageModel.for_inference(model) + +messages = [ + { + "role": "user", + "content": "Explain the difference between a stack and a queue, with examples." + } +] + +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt" +).to("cuda") + +with torch.no_grad(): + output = model.generate( + input_ids=inputs, + max_new_tokens=1000, + temperature=0.7, + top_p=0.9, + do_sample=True, + ) + +print(tokenizer.decode( + output[0][inputs.shape[1]:], + skip_special_tokens=True +)) +``` + +### Ollama + +```bash +# Recommended — best speed/quality balance +ollama run hf.co/EphAsad/Atem-v1-1.5B:Q4_K_M + +# Higher quality +ollama run hf.co/EphAsad/Atem-v1-1.5B:Q5_K_M + +# Near-lossless +ollama run hf.co/EphAsad/Atem-v1-1.5B:Q8_0 +``` + +### llama.cpp + +```bash +llama-server -hf EphAsad/Atem-v1-1.5B:Q4_K_M +``` + +### System Prompt + +Atem's identity is baked into the chat template and activates automatically when no system message is provided. For manual override: + +``` +You are Atem, a precise and analytical reasoning assistant. You approach +every problem methodically — identifying core concepts, reasoning step by +step, and arriving at well-supported conclusions. You show your thinking +clearly and are thorough, direct, and intellectually honest. +``` + +### Available Files + +| File | Size | Description | +|------|------|-------------| +| `model.safetensors` | ~3.1 GB | Full bfloat16 merged weights | +| `Atem-1.5b.Q4_K_M.gguf` | ~986 MB | 4-bit quantised — recommended | +| `Atem-1.5b.Q5_K_M.gguf` | ~1.1 GB | 5-bit quantised | +| `Atem-1.5b.Q8_0.gguf` | ~1.6 GB | 8-bit quantised — near-lossless | + +--- + +## Known Limitations + +**No thinking traces (Stage 1 by design).** Think tags were stripped from all training data for Stage 1. The model does not produce extended `` reasoning traces. Stage 2 training will layer this capability on top of the Stage 1 foundation. + +**Mathematical precision on complex problems.** On multi-step calculations, the model may make arithmetic slips in intermediate steps while arriving at a structurally correct approach. Answers to high-stakes mathematical problems should be independently verified. + +**HellaSwag regression.** A 2.4% regression on HellaSwag commonsense completion is observed. This is minor and substantially better than the 16.2% regression produced by the earlier exploratory full fine-tune run, confirming that LoRA preserved base commonsense capability effectively. + +--- + +## Roadmap + +Atem v1 establishes the Stage 1 foundation. Planned next steps: + +- **Stage 2:** LoRA SFT on curated chain-of-thought data to add thinking trace capability — using `Complex_CoT`, `inverted_reasoning`, and reasoning trace columns held out from Stage 1 training +- **Extended benchmarks:** MMLU, BBH, IFEval, WinoGrande, MBPP post-Stage 2 +- **Atem v2:** Expanded corpus, further domain coverage + +--- + +## Citation + +```bibtex +@misc{atem_v1_2026, + author = {Asad, Zain}, + title = {Atem v1: A 1.5B Reasoning Model via + Multi-Source Knowledge Distillation}, + year = {2026}, + publisher = {HuggingFace}, + howpublished = {\url{https://huggingface.co/EphAsad/Atem-v1-1.5B}}, +} +``` +--- + +## Support + +If you find this model useful for your research or projects, +you can support further development of my datasets and models here: +☕ [ko-fi.com/ephraim123](https://ko-fi.com/ephraim123) + +--- + +## License + +Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), consistent with the base model Qwen2.5-1.5B-Instruct. + +--- + +

+ Built independently by EphAsad +

\ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c37cec5 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.' }} + {%- 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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|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 Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.<|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\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..6fe314c --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "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": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "unsloth_version": "2026.5.9", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5f32a68 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 32768, + "pad_token_id": 151665, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..82c7c25 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03933817bebd1ea2faa8434f923cc5aeccf4a8bd07a2793aeab0d98ad69f77dd +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5340d81 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4122bec --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,202 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + }, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.' }}\n {%- endif %}\n {{- \"\\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 XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\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{%- endif %}\n" +} \ No newline at end of file