commit 4b10f252d625e5556ae049d346a238cd6ee375c0 Author: ModelHub XC Date: Tue Sep 29 10:05:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mims-harvard/bio-posttrain-qwen3-1.7b-dna-sft Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c565b8 --- /dev/null +++ b/README.md @@ -0,0 +1,52 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-1.7B +tags: + - biology + - bio-posttrain + - dna-sft + - dna +library_name: transformers +--- + +# Bio-posttrain Qwen3-1.7B DNA SFT + +DNA supervised fine-tuning (SFT) checkpoint from [How Post-Training Shapes Biological Reasoning Models](https://huggingface.co/collections/mims-harvard/bio-posttrain). + +## Model details + +- **Base model:** `Qwen/Qwen3-1.7B` +- **DNA encoder:** Evo2 `evo2_1b_base` (frozen; not included in this repo) +- **Embedding layer:** `blocks.20.mlp.l3` +- **LoRA:** rank 64, alpha 128 +- **Validation loss:** 0.4687 + +This repo contains the **merged text LLM** (LoRA fused into base weights) plus `dna_projection.pt`. + +## Files + +| File | Description | +|------|-------------| +| `model.safetensors` | Merged Qwen3-1.7B weights | +| `dna_projection.pt` | Linear map from Evo2 hidden (1920) → text hidden (2048) | +| `dna_model_config.json` | DNA encoder + projection metadata | + +## Loading + +Use the [BioReason](https://github.com/mims-harvard/BioReason) `DNALLMModel` loader: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +text_model = AutoModelForCausalLM.from_pretrained("mims-harvard/bio-posttrain-qwen3-1.7b-dna-sft") +tokenizer = AutoTokenizer.from_pretrained("mims-harvard/bio-posttrain-qwen3-1.7b-dna-sft") +proj = torch.load("mims-harvard/bio-posttrain-qwen3-1.7b-dna-sft/dna_projection.pt", map_location="cpu") +# Load Evo2 separately: evo2_1b_base +``` + +See `dna_model_config.json` for encoder settings. + +## Collection + +Part of the [Bio-posttrain](https://huggingface.co/collections/mims-harvard/bio-posttrain) collection. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..42fd04c --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,84 @@ +{%- set dna_count = namespace(value=0) %}{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and not(message.content is string and message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' }} {%- if message.content is string %}{{- message.content + '<|im_end|>' + '\n' }}{%- else %}{%- for content in message.content %}{%- if content.type == 'dna' or 'dna' in content %}{%- set dna_count.value = dna_count.value + 1 %}{%- if add_dna_id %}DNA Sequence {{- dna_count.value }}: {%- endif %}<|dna_start|><|dna_pad|><|dna_end|>{%- elif 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{{- '<|im_end|>' + '\n' }}{%- endif %}{%- elif message.role == "assistant" %} + {%- set content = message.content[0].text %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is defined and message.reasoning_content is not none %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in message.content %} + {%- set content = message.content[0].text.split('')[-1].lstrip('\n') %} + {%- set reasoning_content = message.content[0].text.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first 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' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..e51b76b --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "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": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.1.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/dna_model_config.json b/dna_model_config.json new file mode 100644 index 0000000..e72a7eb --- /dev/null +++ b/dna_model_config.json @@ -0,0 +1,20 @@ +{ + "model_type": "dna_llm", + "dna_model_name": "evo2_1b_base", + "dna_is_evo2": true, + "dna_embedding_layer": "blocks.20.mlp.l3", + "dna_hidden_size": 1920, + "text_hidden_size": 2048, + "max_length_dna": 2048, + "max_length_text": 2048, + "special_tokens": [ + "<|dna_start|>", + "<|dna_pad|>", + "<|dna_end|>" + ], + "notes": "DNA encoder weights are not bundled. Load Evo2 evo2_1b_base separately and apply dna_projection.pt to map encoder embeddings into the text model.", + "stage": "sft", + "lora_rank": 64, + "lora_alpha": 128, + "val_loss": 0.4687 +} diff --git a/dna_projection.pt b/dna_projection.pt new file mode 100644 index 0000000..71dea65 --- /dev/null +++ b/dna_projection.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b45b3d4b47d1f75fd44ce8c6617153a52b706c92028a79676b86d02f33f291 +size 15738781 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d9d057d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.1.0" +} diff --git a/missing_and_unexpected_keys.txt b/missing_and_unexpected_keys.txt new file mode 100644 index 0000000..5f48989 --- /dev/null +++ b/missing_and_unexpected_keys.txt @@ -0,0 +1,3 @@ +Missing keys: + +Unexpected keys: diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d8e5fdd --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfe0e2e558aea2696592149b4bc430967b3cb13a3a6d9f7da44eaecf49f420d +size 8126995136 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..6675e5f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4abfdbaefdacf23a53129abdc73b56451806c0de7f5ebffd7463bf2c96db11 +size 11423216 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9557489 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,19 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|dna_start|>", + "<|dna_pad|>", + "<|dna_end|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}