From b5d8a32002a7d2bd946d5db0849f95dc698ddd4d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 29 Sep 2026 10:19:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mims-harvard/bio-posttrain-qwen3-1.7b-rna-sft Source: Original Platform --- .gitattributes | 36 ++++++++++++++ README.md | 46 ++++++++++++++++++ chat_template.jinja | 84 +++++++++++++++++++++++++++++++++ config.json | 63 +++++++++++++++++++++++++ generation_config.json | 13 +++++ missing_and_unexpected_keys.txt | 3 ++ model.safetensors | 3 ++ rna_model_config.json | 29 ++++++++++++ rna_projection.pt | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 19 ++++++++ 11 files changed, 302 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 missing_and_unexpected_keys.txt create mode 100644 model.safetensors create mode 100644 rna_model_config.json create mode 100644 rna_projection.pt create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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..7a3e18d --- /dev/null +++ b/README.md @@ -0,0 +1,46 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-1.7B +tags: + - biology + - bio-posttrain + - rna-sft + - rna +library_name: transformers +--- + +# Bio-posttrain Qwen3-1.7B RNA SFT + +RNA 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` +- **RNA embeddings:** Precomputed TranscriptFormer (2048-d), projected via `rna_projection.pt` +- **LoRA:** rank 32, alpha 64 +- **Validation loss:** 0.5394 + +## Files + +| File | Description | +|------|-------------| +| `model.safetensors` | Merged LLM weights | +| `rna_projection.pt` | Linear map RNA embed (2048) → text hidden | +| `rna_model_config.json` | Architecture metadata | + +## Loading + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained("mims-harvard/bio-posttrain-qwen3-1.7b-rna-sft", trust_remote_code=True) +tokenizer = AutoTokenizer.from_pretrained("mims-harvard/bio-posttrain-qwen3-1.7b-rna-sft") +proj = torch.load("rna_projection.pt", map_location="cpu") +``` + +RNA sequence embeddings are supplied offline at inference time. See the `rna_models` code in the BioReason repository. + +## 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..7dff26d --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,84 @@ +{%- set rna_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 == 'rna' or 'rna' in content %}{%- set rna_count.value = rna_count.value + 1 %}{%- if add_rna_id %}RNA Sequence {{- rna_count.value }}: {%- endif %}<|rna_start|><|rna_pad|><|rna_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/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..4a9c39c --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324e41cb8ddeb37fc0ead5fdded91dab65ea436f7d20423c7515a4aeb32dcfa5 +size 8126995136 diff --git a/rna_model_config.json b/rna_model_config.json new file mode 100644 index 0000000..c23063b --- /dev/null +++ b/rna_model_config.json @@ -0,0 +1,29 @@ +{ + "model_type": "rna_llm", + "text_model_name": "Qwen/Qwen3-1.7B", + "chat_template_family": "qwen", + "rna_embed_dim": 2048, + "max_rna_seq_len": 1, + "max_length_text": 4096, + "lora_rank": 32, + "lora_alpha": 64, + "lora_dropout": 0.05, + "source_checkpoint": "/n/holylfs06/LABS/mzitnik_lab/Lab/lfesser/evo_tfm/hf_upload_models/Qwen3-1.7B-RNA-SFT-paper-e5-val_loss-0.5394.ckpt", + "epoch": 2, + "global_step": 515, + "hyper_parameters": { + "text_model_name": "Qwen/Qwen3-1.7B", + "rna_embed_dim": 2048, + "lora_rank": 32, + "lora_alpha": 64, + "lora_dropout": 0.05, + "max_length_text": 4096, + "chat_template_family": "qwen" + }, + "special_tokens": [ + "<|rna_start|>", + "<|rna_pad|>", + "<|rna_end|>" + ], + "notes": "RNA embeddings are precomputed offline (TranscriptFormer, 2048-d) and projected via rna_projection.pt. Use the evo_tfm/rna_models inference code to load." +} \ No newline at end of file diff --git a/rna_projection.pt b/rna_projection.pt new file mode 100644 index 0000000..3feda7a --- /dev/null +++ b/rna_projection.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187eb2dfaebc9b4d52419542d996d8120cc3c942456e6bfe48df1dadd5ee6e52 +size 16787357 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..579a987 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f404de3ab57bf86dc45e79781aa017f200bf28bb699d24eef7bc459b3e71cdfb +size 11423216 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..fbdc581 --- /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": [ + "<|rna_start|>", + "<|rna_pad|>", + "<|rna_end|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}