初始化项目，由ModelHub XC社区提供模型

Model: mims-harvard/bio-posttrain-qwen3-1.7b-rna-sft
Source: Original Platform

.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

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.

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 <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- 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 '</think>' in message.content %}
+                {%- set content = message.content[0].text.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content[0].text.split('</think>')[0].rstrip('\n').split('<think>')[-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<think>\n' + reasoning_content.strip('\n') + '\n</think>\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 %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- 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 %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

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
+}

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"
+}

missing_and_unexpected_keys.txt

@@ -0,0 +1,3 @@
+Missing keys:
+
+Unexpected keys:

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324e41cb8ddeb37fc0ead5fdded91dab65ea436f7d20423c7515a4aeb32dcfa5
+size 8126995136

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."
+}

rna_projection.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187eb2dfaebc9b4d52419542d996d8120cc3c942456e6bfe48df1dadd5ee6e52
+size 16787357

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f404de3ab57bf86dc45e79781aa017f200bf28bb699d24eef7bc459b3e71cdfb
+size 11423216

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
+}