Replace duplicated F32 weights with the local FP8_DYNAMIC checkpoint

README.md

@@ -1,48 +1,33 @@
 ---
 license: mit
+base_model: biomni/Biomni-R0-32B-Preview
 language:
 - en
 tags:
 - agent
 - biology
 - code
-base_model:
-- Qwen/Qwen3-32B
+- fp8
 ---
 
-# Biomni-R0-32B-Preview
-This repo contains the weights of **Biomni-R0-32B-Preview**, a research preview of the series of biomedical AI agents trained by the [Biomni](https://biomni.stanford.edu/) team.
+# Biomni-R0-32B-Preview FP8 Dynamic
 
-Biomni-R0-Preview is a 32B model trained with end-to-end reinforcement learning using the Biomni-E1 environment scaffolding. It has achieved state-of-the-art performance across ten evaluated biomedical benchmarks spanning diverse tasks including crispr delivery, rare disease diagnosis, gwas variant prioritization, etc.
+Local FP8_DYNAMIC compression of [biomni/Biomni-R0-32B-Preview](https://huggingface.co/biomni/Biomni-R0-32B-Preview) revision `71432eb3d5e583bee757e0f9437a17e711e8e3d1`. This is not an official Biomni release. The original F32 weights stay on that repo.
 
-Read more about how the model is trained and evaluted in our [technical report](https://biomni.stanford.edu/blog/biomni-r0-technical-report).
+- Scheme: compressed-tensors FP8, per-channel weights, dynamic per-token activations
+- `lm_head` left dense
+- No calibration dataset
+- Weights about 35GB
 
-<p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/651d0bf7e4025a389cd24c7a/WMcdZj35W1Bbr-m9Cffw1.png" width="800"/>
-</p>
+vLLM reads the scheme from `config.json`. Do not pass `--quantization`.
 
-
-<p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/651d0bf7e4025a389cd24c7a/JeZIg7DJIxc8YLfyOVV0t.png" width="800"/>
-</p>
-
-# Usage: Serve with SGLang
 ```bash
-python -m sglang.launch_server --model-path biomni/Biomni-R0-32B-Preview --port 30000 --host 0.0.0.0 --mem-fraction-static 0.8 --tp 2 --trust-remote-code --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":1.0,"original_max_position_embeddings":32768}, "max_position_embeddings": 131072}'
+vllm serve vonkaiser/Biomni-R0-32B-Preview-FP8-Dynamic \
+  --gpu-memory-utilization 0.90 \
+  --kv-cache-dtype fp8 \
+  --max-model-len 32768
 ```
-This would require two GPUs with 80G VRAM. Alternatively, you may serve with 4 GPUs with 40G VRAM via `--tp 4`.
 
-Note, if your task would take significantly longer than the original 32768 context length, you may set `rope_scaling` factor to a number `>1.0` and `<=4.0` for smoother context window extension. However, `rope_scaling` might degrade performance on tasks with shorter trajectories. Please tune the rope scaling factor according to your usage.
+The chat template asks for a JSON object inside `<tool_call>` tags. Use a tool parser that reads that format (`qwen` or `hermes`). `qwen3_coder` expects a different XML shape and will leave the call in `content`.
 
-To run inference with the Biomni-E1 environment, please follow the instructions in our [official repo](https://github.com/snap-stanford/biomni).
-
-# Citation
-```
-@misc{biomnir0,
-  title     = {Biomni-R0: Using RL to Hill-Climb Biomedical Reasoning Agents to Expert-Level},
-  author    = {Ryan Li and Kexin Huang and Shiyi Cao and Yuanhao Qu and Jure Leskovec},
-  year      = {2025},
-  month     = {September},
-  note      = {Technical Report}
-}
-```
+Base architecture is Qwen/Qwen3-32B. License MIT, same as the source model.

config.json

@@ -17,6 +17,56 @@
   "num_attention_heads": 64,
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "float-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.19.0"
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
@@ -27,4 +77,4 @@
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}
+}

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.51.1"
+  "transformers_version": "5.17.0"
 }

model-00001-of-00027.safetensors → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0fdb2eb92ca45f8f56ee26b78e9497a9cc44c64f85bfbe2de9dde4fc8d35b9
-size 4537714712
+oid sha256:b0ca2c41b339e333543b14b74447acb9e2a662e3ab5c0ef8fbd39ee9b38f7586
+size 19926596848

model-00002-of-00027.safetensors → model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e423bb607ece73151c45ba4c53fb8c8ab5ff67a268f590652936e8217a66a8cb
-size 4802607584
+oid sha256:fde030a562aa0dfb50cc943691e0236560fa3829af24a859c0925152363a20f4
+size 17523517568

model-00003-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfaefe833b2e31d58abcb5102be8a3341a10922cde1b9293fcd9eb18948e9d77
-size 4949365440

model-00004-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3cdf3b896771f843bc235639ccb81b8abe288686c66acb3e38105fa8e4d96ba3
-size 4802607584

model-00005-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d27b839e8279f79ccef160d5e0bbad797503c84fbb572ea7b1f6d388047db05e
-size 4949365464

model-00006-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4bf1258b86ceafd8e4917368eb57ad3fa3e38913642b04c6fa7161768a38db5b
-size 4802607616

model-00007-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:866f427d5983a9913d8c03877db8a296353dc913fd3687feba8a069d02298008
-size 4949365464

model-00008-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a154e2962b152b19b0fc3e59bd497449b7498abd8f7c1a4302b41628784b4dd8
-size 4802607616

model-00009-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf040aa0e54e324e248ab3d6f201999775013bd9c05f0346c6c6d9c80bdcc571
-size 4949365464

model-00010-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85047b88fa702d8b8c4c71f8d31ad9d8a401593f1613faeeb72b3562d779d68b
-size 4802607616

model-00011-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21a385961750fe76836b3395c9b2dd2d3d65e440f3fe10dc182490acb6f5f618
-size 4949365464

model-00012-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe57a68504589dcec269b5d430809ada9a67e9fb1632061196df3a0e469c149a
-size 4802607616

model-00013-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eaa7aa485d12ffa44c24066cef385e202f51441b05deb3a31428cfd2096a8475
-size 4949365464

model-00014-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:09e0fc2c00d3524ebf15f3a94b38ae4431a123d077b5f3c18275940e2522025a
-size 4802607616

model-00015-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:273f54a8ccc670bc858d1282381ee115424acbdb071ed3b73cf6076b883852e3
-size 4949365464

model-00016-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a6ac934f24dfe776ccc8f72b829e955128b49083f528e103706a4a8e387c98b
-size 4802607616

model-00017-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:12bfb813502c2cfaf5f963261bb3739a935f24926263dc85cefa6be3fa22f44b
-size 4949365464

model-00018-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f08d7b69d559d0eaa61259218d5f386c2d311d36cca5941e159abef4ffc272dc
-size 4802607616

model-00019-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bc8d13880a0e19369a23f02c07d05963dc0e4c2772cf8129911f48e68065a979
-size 4949365464

model-00020-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a899b98563556b3eff6203c1c8e7283edb01ab83614aa6b6efe173d5c0295c5a
-size 4802607616

model-00021-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3db2b4af17b29a8212e64eba84ed2bc44fb6d3eca93bed149b32e6b7a1dca12a
-size 4949365464

model-00022-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:24c83a27baec7bd1612a93e801711fb7f2ca2e40def9c4537d0c25bba5d12e38
-size 4802607616

model-00023-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a289d21ec2a1285be7f856de74adaa05ece75b818df47bb0cea451e79dfcfe26
-size 4949365464

model-00024-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae4d227bed27f03b1437cacdc740927ca4826a2902e45ae8ac1e5243bde53fb1
-size 4802607616

model-00025-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7d613bea16f760d4e6ab722ef87918ce56fef9556040b9fdd429bfa3533794cd
-size 4949365464

model-00026-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0ba38ab22634bbd8b5fd594f1f2f085c536f18ef66d20d8791fd96ad0cc2dc47
-size 4802607616

model-00027-of-00027.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f688df35a5987ecc3588ed42e452869e689fcfec2cee43d1a27913cf6dddd11e
-size 4684575512

recipe.yaml

@@ -0,0 +1,8 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: FP8_DYNAMIC
+      bypass_divisibility_checks: false
+      requires_calibration_data: false

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -1,237 +1,12 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
+  "backend": "tokenizers",
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": false,
+  "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,