commit 0d1530d95f0cbfa9e142697cff58ed04c2c04e24 Author: ModelHub XC Date: Sun Jul 19 02:03:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: EphAsad/Atem-SageCoder-1.5B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..227f4ef --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +Atem-Wisdom-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Atem-Wisdom-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-Wisdom-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-SageCoder-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-SageCoder-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atem-SageCoder-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Atem-SageCoder-1.5B.Q4_K_M.gguf b/Atem-SageCoder-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..2b317f1 --- /dev/null +++ b/Atem-SageCoder-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71fe0be4099cdaea980e34ca3f2a149443d9b7dc40b607cc13f6691edd8255eb +size 986048544 diff --git a/Atem-SageCoder-1.5B.Q5_K_M.gguf b/Atem-SageCoder-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..9af42f6 --- /dev/null +++ b/Atem-SageCoder-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dec11f94e71c9807169e092b9ea7f136a03c840c7af9194797f1bb427bac510 +size 1125050400 diff --git a/Atem-SageCoder-1.5B.Q8_0.gguf b/Atem-SageCoder-1.5B.Q8_0.gguf new file mode 100644 index 0000000..866ffc4 --- /dev/null +++ b/Atem-SageCoder-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83737eb32ada80d125b46933d69d84c04c07453a6fd9af0968b1b91c4cabe0d6 +size 1646573088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eabe559 --- /dev/null +++ b/README.md @@ -0,0 +1,380 @@ +--- +base_model: EphAsad/Atem-Wisdom-1.5B +language: +- en +license: apache-2.0 +tags: +- qwen2 +- unsloth +- lora +- llama.cpp +- reasoning +- chain-of-thought +- thinking +- coding +- code-generation +- distillation +- conversational +- text-generation-inference +datasets: +- nvidia/OpenCodeReasoning +pipeline_tag: text-generation +--- + +![Atem Logo](https://huggingface.co/EphAsad/Atem-v1-1.5B/resolve/main/Logo.png) + +# Atem-SageCoder + +*Ancient logic. Modern intelligence. Applied to code.* + +A 1.5B code reasoning model that thinks before it writes — trained on verified competitive programming traces from frontier models. + +![Base Model](https://img.shields.io/badge/Base-Atem--Wisdom--1.5B-blue) +![Stage](https://img.shields.io/badge/Stage-Code%20Specialisation-purple) +![Parameters](https://img.shields.io/badge/Parameters-1.5B-orange) +![License](https://img.shields.io/badge/License-Apache%202.0-green) + +--- + +## Overview + +Atem-SageCoder is a code-specialised variant of [Atem-Wisdom-1.5B](https://huggingface.co/EphAsad/Atem-Wisdom-1.5B), fine-tuned on verified chain-of-thought coding traces from [nvidia/OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning). It inherits Atem-Wisdom's explicit reasoning capability and applies it specifically to programming tasks — working through algorithm choice, edge cases, and complexity analysis before producing an implementation. + +The core behaviour: when given a coding problem, the model reasons through it fully inside a `` block before writing any code. This makes its reasoning auditable and reduces the frequency of structurally plausible but logically incorrect solutions. + +**When to choose Atem-SageCoder over Atem-Wisdom:** + +- Programming problems where reasoning about approach matters before implementation +- Competitive programming and algorithmic tasks +- Situations where you want to see the model's design decisions, not just its output +- Code that requires edge case analysis or complexity reasoning + +**When to choose Atem-Wisdom instead:** + +- General reasoning, mathematics, and analytical tasks outside of coding +- Mixed-domain workloads where code is one of many task types +- Environments where output length is a constraint + +--- + +## The Atem Series + +| Model | Stage | Capability | Status | +|---|---|---|---| +| [Atem v1](https://huggingface.co/EphAsad/Atem-v1-1.5B) | Stage 1 — SFT | Fast, direct reasoning | ✅ | +| [Atem-Wisdom](https://huggingface.co/EphAsad/Atem-Wisdom-1.5B) | Stage 2 — CoT | Explicit thinking traces | ✅ | +| **Atem-SageCoder** | Specialisation — Code | Think-then-code on algorithms | ✅ | +| Atem-Pharaoh *(planned)* | Stage 3 — DPO/IPO | Preference-aligned reasoning | 🔄 | + +Atem-SageCoder is a domain-specialised branch off Atem-Wisdom, not a continuation of the main series progression toward Atem-Pharaoh. + +--- + +## Model Details + +| Property | Value | +|---|---| +| **Base model** | EphAsad/Atem-Wisdom-1.5B | +| **Root architecture** | Qwen/Qwen2.5-1.5B-Instruct | +| **Training method** | LoRA SFT — Code Reasoning Specialisation | +| **LoRA config** | r=32, alpha=64, dropout=0.05 | +| **Parameters** | ~1.54B | +| **Training records** | 15,427 (after filtering) | +| **Think / no-think split** | 90% / 10% | +| **Epochs** | 2 | +| **Total steps** | 484 | +| **Final train loss** | 0.8477 | +| **Final val loss** | 0.8591 | +| **Hardware** | NVIDIA A100-SXM4 80GB | +| **Max sequence length** | 8,192 tokens | +| **Precision** | bfloat16 | +| **License** | Apache 2.0 | + +--- + +## Output Format + +Atem-SageCoder produces responses in one of two formats: + +**With reasoning trace (90% of training examples):** + +``` + +[Reasoning through the problem — algorithm selection, edge cases, +complexity analysis, implementation approach] + + +[Final implementation — clean, correct code with explanation] +``` + +**Direct answer (simple queries):** + +``` +[Concise code response — no reasoning trace needed] +``` + +The 10% no-think training pool prevents the model from refusing to answer simple queries without extended reasoning. On straightforward questions it responds directly; the think trace activates proportionally to problem complexity. + +--- + +## Training Data + +Atem-SageCoder was trained on 15,427 examples drawn from `nvidia/OpenCodeReasoning` (split_0), after streaming 40,000 candidates and applying two sequential filters. + +**Filter 1 — Truncation gate:** Records were rejected if `` was absent from the output (CoT cut off mid-trace) or if fewer than 30 characters of code followed `` (code truncated). This is the primary source of attrition — OpenCodeReasoning CoT traces are long, and 8,192 tokens captures roughly 38% of the raw stream. + +**Filter 2 — Bad input gate:** Records with `input` fields under 20 characters were rejected. A known data quality issue in split_1 caused that entire split to be excluded; all training data comes from split_0. + +**Filter 3 — Token length:** Examples exceeding 8,192 tokens after chat template application were removed rather than truncated. + +| Property | Value | +|---|---| +| Dataset | nvidia/OpenCodeReasoning (split_0) | +| Streamed | 40,000 | +| After truncation filter | ~24,000 | +| After token length filter | 15,427 | +| Train / Val split | 14,627 / 800 | +| Domain | Competitive programming (algorithmic problems) | + +**CoT extraction:** The `output` column in OpenCodeReasoning contains `...code` format. CoT and code were extracted into separate fields before formatting. The `` tags were removed from the raw output to avoid double-tag injection during chat template application, then manually reinserted during `build_text` construction with `enable_thinking=False`. + +**Loss curve:** + +| Step | Train Loss | Val Loss | +|---|---|---| +| 250 | 0.8564 | 0.8757 | +| 484 (final) | **0.8477** | **0.8591** | + +Train/val gap of 0.012 at completion — no overfitting signal. Loss values in the 0.85 range are expected for complex CoT+code targets; simple instruction SFT typically reaches 0.3–0.5, but verified reasoning traces carry genuine entropy. + +--- + +## Training Configuration + +```python +# Key hyperparameters +lora_r = 32 +lora_alpha = 64 +lora_dropout = 0.05 +max_seq_length = 8192 # doubled vs Atem-Wisdom — CoT traces are long +learning_rate = 1e-4 +lr_scheduler = 'cosine' +warmup_ratio = 0.05 +batch_size = 4 # halved vs Atem-Wisdom to account for 2× seq length +grad_accumulation = 16 # effective batch size: 64 +num_epochs = 2 +dtype = bfloat16 +load_in_4bit = True # during training +nothink_ratio = 0.10 # 10% direct-answer training pool +``` + +Training used Unsloth (`unsloth==2026.5.5`, `unsloth_zoo==2026.5.5`) with `train_on_responses_only` masking. Loss was computed exclusively on assistant response tokens. A three-part pre-training validation was run before training: identity confirmation, double `` tag detection, and mask sanity check. All checks passed before training was confirmed. + +--- + +## Evaluation + +### Qualitative Coding Evaluation (8 / 30 questions shown) + +Atem-SageCoder was evaluated against a (Qwen/Qwen2.5-1.5B-Instruct) baseline across 30 coding questions covering implementation tasks, concept explanations, and algorithm design. The 8 coding-domain questions from that evaluation are shown below. + +| # | Question | Base | SageCoder | Notes | +|---|---|---|---|---| +| 1 | `is_even(n)` function | ✓ No think | ✓ Think | Both correct | +| 2 | Count vowels in string | ✓ No think | ✓ Think | SageCoder more Pythonic (generator expression) | +| 3 | List vs tuple differences | ✓ No think | ⚠ Think | SageCoder error: claims tuples cannot contain duplicates (incorrect) | +| 4 | Sum list without `sum()` | ✓ No think | ✓ Think | SageCoder more thorough, both correct | +| 5 | Reverse a string | ✓ No think | ✓ Think | Both correct; SageCoder more verbose | +| 6 | `if` / `elif` / `else` | ⚠ No think | ✓ Think | Base error: predicts wrong output for age=25 example | +| 7 | `find_max()` with empty list | ✓ No think | ✓ Think | SageCoder provides two implementations | +| 8 | `for` vs `while` loop | ✓ No think | ✓ Think | SageCoder more structured | + +**Summary across 8 questions:** + +| Metric | Baseline | Atem-SageCoder | +|---|---|---| +| Think traces | 0 / 8 | 8 / 8 | +| Avg response (words) | ~177 | ~470 | +| Factual errors observed | 1 (Q6 output prediction) | 1 (Q3 tuple claim) | +| Code correctness | 7 / 8 correct | 7 / 8 correct | + +The think-then-code pattern activates consistently on all coding questions. Response depth increases significantly — SageCoder examines edge cases, considers multiple approaches, and explains implementation choices that the baseline omits. Overall correctness is comparable across these 8 questions; the error types differ (baseline: incorrect output prediction; SageCoder: incorrect concept claim about tuples). + +--- + +## Usage + +### Transformers + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_name = "EphAsad/Atem-SageCoder-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 finds all prime numbers up to n using the Sieve of Eratosthenes." + } +] + +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=2048, + 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-SageCoder-1.5B", + max_seq_length=8192, + dtype=torch.bfloat16, + load_in_4bit=True, +) +FastLanguageModel.for_inference(model) + +messages = [ + { + "role": "user", + "content": "Given an array of integers, find the two numbers that sum to a target value. Return their indices." + } +] + +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=2048, + 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-SageCoder-1.5B:Q4_K_M + +# Higher quality +ollama run hf.co/EphAsad/Atem-SageCoder-1.5B:Q5_K_M + +# Near-lossless +ollama run hf.co/EphAsad/Atem-SageCoder-1.5B:Q8_0 +``` + +### llama.cpp + +```bash +llama-server -hf EphAsad/Atem-SageCoder-1.5B:Q4_K_M +``` + +### System Prompt + +Atem-SageCoder's identity and coding focus are baked into the chat template. To override manually: + +``` +You are Atem-SageCoder, a thoughtful programming assistant built on the +Atem foundation. You reason carefully through problems before writing code +— considering edge cases, algorithm choice, complexity, and implementation +details — then provide clean, correct, and well-structured implementations. +``` + +### Available Files + +| File | Size | Description | +|---|---|---| +| `model.safetensors` | ~3.1 GB | Full bfloat16 merged weights | +| `Atem-SageCoder-1.5B.Q4_K_M.gguf` | ~986 MB | 4-bit quantised — recommended | +| `Atem-SageCoder-1.5B.Q5_K_M.gguf` | ~1.1 GB | 5-bit quantised | +| `Atem-SageCoder-1.5B.Q8_0.gguf` | ~1.6 GB | 8-bit quantised — near-lossless | + +--- + +## Known Limitations + +**Training data scope.** All 15,427 training examples come from competitive programming problems in `nvidia/OpenCodeReasoning`. The model is strongest on algorithmic and data structure problems; general software engineering tasks (web APIs, OOP design, framework-specific code) were not represented in training and may produce lower quality output. + +**Factual concept errors.** The qualitative evaluation identified an incorrect claim about tuples (Q3: stated tuples cannot contain duplicates — they can). Concept explanation accuracy should be independently verified for correctness-critical applications. + +**Response length.** Think traces substantially increase output length. This is a fundamental property of the think-then-code design, not a fixable defect. For latency-constrained environments, Atem-Wisdom-1.5B with direct prompting may be preferable. + +**Single language bias.** OpenCodeReasoning solutions are predominantly Python. Performance on other languages has not been formally evaluated. + +**Small training set.** 15,427 examples is a focused dataset. Coverage of less common algorithmic patterns may be shallow. The high filter attrition rate (40k streamed → 15.4k retained) reflects the strict quality bar applied, not a shortage of data — the full split_0 contains substantially more examples at lower sequence lengths. + +--- + +## Roadmap + +| Stage | Status | Description | +|---|---|---| +| Stage 1 — SFT | ✅ Complete | Atem v1 — direct reasoning foundation | +| Stage 2 — CoT SFT | ✅ Complete | Atem-Wisdom — thinking traces | +| Specialisation — Code | ✅ Complete | **Atem-SageCoder — this model** | +| Stage 3 — DPO/IPO | 🔄 Planned | Atem-Pharaoh — preference-aligned reasoning | + +--- + +## Citation + +```bibtex +@misc{atem_sagecoder_2026, + author = {Asad, Zain}, + title = {Atem-SageCoder: A 1.5B Think-Then-Code Model + via Competitive Programming Trace Distillation}, + year = {2026}, + publisher = {HuggingFace}, + howpublished = {\url{https://huggingface.co/EphAsad/Atem-SageCoder-1.5B}}, +} +``` + +--- + +## License + +Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), consistent with the base model chain (Qwen2.5-1.5B-Instruct → Atem v1 → Atem-Wisdom → Atem-SageCoder). + +--- + +Built independently by [EphAsad](https://huggingface.co/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..a5e9778 --- /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": "2026.5.5", + "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..488cb36 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfc24e8d97db266ddb9d7eb5562a15aaaff7dcf7c1e742923878cf010e37c4e +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