diff for compatibility

README.md

@@ -1,168 +1,29 @@
 ---
+base_model:
+- openai/gpt-oss-120b
 license: apache-2.0
 pipeline_tag: text-generation
 library_name: transformers
 tags:
-- vllm
+- openai
 ---
 
+<!-- header start -->
 <p align="center">
-  <img alt="gpt-oss-120b" src="https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-120b.svg">
+  <img src="https://huggingface.co/datasets/FriendliAI/documentation-images/resolve/main/model-card-assets/friendliai.png" width="100%" alt="FriendliAI Logo">
 </p>
+<!-- header end -->
 
-<p align="center">
-  <a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
-  <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
-  <a href="https://openai.com/index/gpt-oss-model-card"><strong>Model card</strong></a> ·
-  <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
-</p>
-
-<br>
-
-Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
-
-We’re releasing two flavors of these open models:
-- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
-- `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
-
-Both models were trained on our [harmony response format](https://github.com/openai/harmony) and should only be used with the harmony format as it will not work correctly otherwise.
-
-
-> [!NOTE]
-> This model card is dedicated to the larger `gpt-oss-120b` model. Check out [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) for the smaller model.
-
-# Highlights
-
-* **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.  
-* **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.  
-* **Full chain-of-thought:** Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.  
-* **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning.
-* **Agentic capabilities:** Use the models’ native capabilities for function calling, [web browsing](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#browser), [Python code execution](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#python), and Structured Outputs.
-* **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
-
----
-
-# Inference examples
-
-## Transformers
-
-You can use `gpt-oss-120b` and `gpt-oss-20b` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
-
-To get started, install the necessary dependencies to setup your environment:
-
-```
-pip install -U transformers kernels torch 
-```
-
-Once, setup you can proceed to run the model by running the snippet below:
-
-```py
-from transformers import pipeline
-import torch
-
-model_id = "openai/gpt-oss-120b"
-
-pipe = pipeline(
-    "text-generation",
-    model=model_id,
-    torch_dtype="auto",
-    device_map="auto",
-)
-
-messages = [
-    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
-]
-
-outputs = pipe(
-    messages,
-    max_new_tokens=256,
-)
-print(outputs[0]["generated_text"][-1])
-```
-
-Alternatively, you can run the model via [`Transformers Serve`](https://huggingface.co/docs/transformers/main/serving) to spin up a OpenAI-compatible webserver:
-
-```
-transformers serve
-transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-120b
-```
-
-[Learn more about how to use gpt-oss with Transformers.](https://cookbook.openai.com/articles/gpt-oss/run-transformers)
-
-## vLLM
-
-vLLM recommends using [uv](https://docs.astral.sh/uv/) for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
-
-```bash
-uv pip install --pre vllm==0.10.1+gptoss \
-    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
-    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
-    --index-strategy unsafe-best-match
-
-vllm serve openai/gpt-oss-120b
-```
-
-[Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)
-
-## PyTorch / Triton
-
-To learn about how to use this model with PyTorch and Triton, check out our [reference implementations in the gpt-oss repository](https://github.com/openai/gpt-oss?tab=readme-ov-file#reference-pytorch-implementation).
-
-## Ollama
-
-If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after [installing Ollama](https://ollama.com/download).
-
-```bash
-# gpt-oss-120b
-ollama pull gpt-oss:120b
-ollama run gpt-oss:120b
-```
-
-[Learn more about how to use gpt-oss with Ollama.](https://cookbook.openai.com/articles/gpt-oss/run-locally-ollama)
-
-#### LM Studio
-
-If you are using [LM Studio](https://lmstudio.ai/) you can use the following commands to download.
-
-```bash
-# gpt-oss-120b
-lms get openai/gpt-oss-120b
-```
-
-Check out our [awesome list](https://github.com/openai/gpt-oss/blob/main/awesome-gpt-oss.md) for a broader collection of gpt-oss resources and inference partners.
-
----
-
-# Download the model
-
-You can download the model weights from the [Hugging Face Hub](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) directly from Hugging Face CLI:
-
-```shell
-# gpt-oss-120b
-huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
-pip install gpt-oss
-python -m gpt_oss.chat model/
-```
-
-# Reasoning levels
-
-You can adjust the reasoning level that suits your task across three levels:
-
-* **Low:** Fast responses for general dialogue.  
-* **Medium:** Balanced speed and detail.  
-* **High:** Deep and detailed analysis.
 
-The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
+# openai/gpt-oss-120b
 
-# Tool use
+* Model creator: [openai](https://huggingface.co/openai)
+* Original model: [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)
 
-The gpt-oss models are excellent for:
-* Web browsing (using built-in browsing tools)
-* Function calling with defined schemas
-* Agentic operations like browser tasks
+## Differences
 
-# Fine-tuning
+* Model weights converted to bfloat16.
 
-Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
+## License
 
-This larger model `gpt-oss-120b` can be fine-tuned on a single H100 node, whereas the smaller [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) can even be fine-tuned on consumer hardware.
+Refer to the license of the original model card.

config.json

@@ -59,15 +59,6 @@
   "num_local_experts": 128,
   "output_router_logits": false,
   "pad_token_id": 199999,
-  "quantization_config": {
-    "modules_to_not_convert": [
-      "model.layers.*.self_attn",
-      "model.layers.*.mlp.router",
-      "model.embed_tokens",
-      "lm_head"
-    ],
-    "quant_method": "mxfp4"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "beta_fast": 32.0,
@@ -82,7 +73,8 @@
   "sliding_window": 128,
   "swiglu_limit": 7.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.55.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0.dev0",
   "use_cache": true,
   "vocab_size": 201088
 }

generation_config.json

@@ -3,9 +3,8 @@
   "do_sample": true,
   "eos_token_id": [
     200002,
-    199999,
-    200012
+    199999
   ],
   "pad_token_id": 199999,
-  "transformers_version": "4.55.0.dev0"
+  "transformers_version": "4.56.0.dev0"
 }

metal/model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f3d5b8a213f146ec29296dad5c3370844d95ba9d21e8dc49f7e61e6e9ee9042
-size 65238253568

model-00003-of-00014.safetensors → model-00001-of-00073.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47aee9e7b9d5bedb215042c01ccededd9bd9c30b0dddea862dc2506b9d6c74de
-size 4115586752
+oid sha256:51b5b69e7feecbc961896afbe7be9a02fce772d236eb5d14d98bf9f93565e872
+size 1212106064

model-00000-of-00014.safetensors → model-00002-of-00073.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695218884684c611fe08a74751ee443f971e9bd9bc062edba822da3fe45969b7
-size 4625017896
+oid sha256:66f8d893fc4fbd27a07d2454114d5cc84821fa18d7575b625aa184b31ef0a572
+size 4248207640

model-00001-of-00014.safetensors → model-00003-of-00073.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a
-size 4115586736
+oid sha256:26fb7705dba6ce529158ecea8863e20dc2c197790c159f3ec15b865b8474c97a
+size 2177954736

model-00004-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6c2752acda607b1d5ca52df9e75c1b9b2761e6875ff10c9bd6ddac473c0262e
-size 4625017896

model-00002-of-00014.safetensors → model-00004-of-00073.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022478dd04398c5bdb545a5be0a6437ecc2eb53d1dbd29edafcfff4b3ddf0a41
-size 4625017888
+oid sha256:dda6a71a050e68fe98ddfc12c0e3e86234b29d2ee5a6ba9083cabcc9e173563f
+size 4248207640

model-00005-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c8dd401544c31cb93b8459eee7da20ea2a07626a59455d7d92b85257df9b46c
-size 4115586696

model-00005-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a37774982420254a3c7141b981aa37878713d6bc6f78a756295cd9e41c1ab88
+size 2177954736

model-00006-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:28d839f2e027985a8b14e45f2323798862eddb7770ee9800ea6b7c803abee489
-size 4625017856

model-00006-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b81738668bce7b58ec8cef5e8c25b1e2b7afafcd1af7913da2788838263bd0
+size 4248207640

model-00007-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8958c5f183c04f6ea959cfd90562b5128124154b2bbf979b8a22b9405b30ed8
-size 4060267176

model-00007-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c25b0c1f0d5f64594529628151ace3ae838869c744c361cd5421165442e26e
+size 2177954736

model-00008-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf1f2a88868ffc37d520dcf77d26f0e823710b5e682d473ff10f6974fa3b7517
-size 4625017896

model-00008-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b43d83c403e92882c79cdfbeb8b80e30d0d7fe58329ab8d3a8a13db0c1d7c5d
+size 4248207640

model-00009-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f72d34a4004241b45c332b61f8ffa124e9a913bc1ab442b66e717d3e94e741ce
-size 4170906304

model-00009-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fc61132427d0002e559feca0a040ddcc2be59557bc9b713c5011702c25e5b6
+size 2177954736

model-00010-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f48c867c2cb0a44bfc2f8768cb98e4aec9a350946fceacfebdcad5d32ad4a471
-size 4625017896

model-00010-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc516fd1e058767eb5d566b81f2619fc9319aed76409628d94b9fda5e4994a0
+size 4248207640

model-00011-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a06851b2cfd35f48722f823bc1ab8f7bcb4a878a5b8e975f4d3544f230454eeb
-size 4115586752

model-00011-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153eef134702ea1df876220d0e3873e47b124b7764dabc8c64f25a8247761fec
+size 2177954736

model-00012-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3af33667c307e20ae2a7648ea52653de46dd0171601ec5c696e47a2f5d5bf1e4
-size 4064660808

model-00012-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b2a45ac61f5b5d44e5a2df4b88643f8c7d57545b06c60121d954a9598599c1
+size 4248207640

model-00013-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bcbcb74b043e071d1e05471d500d74dcf661175e00878ed302ccdf1801a75aef
-size 4625017896

model-00013-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ceba841dfdd14f0e2b313e676c48c4d66b5824a2fdfa25aa327fabccb227f2
+size 2177954736

model-00014-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54b1be1609696c307cc5ca117b1fa54feaddebffa04e9c2db117652a01964230
-size 4115586736

model-00014-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4ba78d4b340e08bcdb3fbfb48c26cc57abd581046b6a2a6620b9c63cca14aa
+size 4248207640

model-00015-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c5e76d8bd303eba203bb00f9ab3dcb4cffa22efe3c400c63c4eb146dd1d744
+size 2177954736

model-00016-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925cd470b083f8ce05484d991c989419873eecf562080947d4c64649ab56677d
+size 4248207640

model-00017-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ccd83bcd726ee1d758e4eda1d181fc9725e19dfd7ed6326e60b2403f394010
+size 2177954736

model-00018-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52b5fe061cefc784b2fb5a09ce6f30fe1fa6641103a141a5b8722df2a48aff8
+size 4248207640

model-00019-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491cc447b9ac3010ddd8a5a1a2debfbf089a5fd1bececa2bca9589e23280b512
+size 2177954736

model-00020-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3484899ce81bacff6cf71f3e225152d61b3f688906bdaca527c87c5eb35d7c1f
+size 4248207640

model-00021-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd51c755fc6bf56bbe9eff6fe4045ec3b6e36880b88a385304ce9b8e8e1d348f
+size 2177954688

model-00022-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d18647e59b8982622412fa33d9c8defbac9441670fedeb94bf216382f904e48
+size 4248207640

model-00023-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80156129505db89d74e0f54e3f2f4ce43f9355f92d19483179d66eaaab4db20
+size 2177954752

model-00024-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75eeb2761915a28fd12ae35d2fa13b6b984d9c6829184dc6a81bb778d1811c2
+size 4248207640

model-00025-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d06dffd73f797cb37e5490618d6b65e047525f6aa520220a26a26de6b831d31
+size 2177954752

model-00026-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d69f06e29de3eeb3e8df6353d418cfca5a6abb432f90b95c750252e5d3b7e1
+size 4248207640

model-00027-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5661406e1ac416fc79107b63e0b73d86a7620e88da97910d98ad8e76af6e43a
+size 2177954752

model-00028-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2301da5402b74812725f99d892af657a421d7d3ff1fedf3309c28aa0fa0e4353
+size 4248207640

model-00029-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1abacc9e3da8fa1e9228657af1df9bb963ad5b943021dc2062b35de801f8da
+size 2177954752

model-00030-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8c1f5337c4b372da5d49cfeca7996e85cf3f8af0323359abfc5a38539db4d1
+size 4248207640

model-00031-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706223001eb940b0d020019616a37d5701474474fed8488ae048103b68ef2f6e
+size 2177954752

model-00032-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9dc8df6da9507d6f99547ed7b6ab17793cbcd5a81c0c2f3439ff8f6c1d10c9
+size 4248207640

model-00033-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f451697d42df95e85c5b2126324d663589b3d8f0afdb050f9c1ec445b95c01
+size 2177954752

model-00034-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2278f08494e6ef08a3e4b5794fc650970b01bb6652502c3bf861d9ee39024d52
+size 4248207640

model-00035-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1125afcc82b1f89b8f043e607fb5c5fe2a12eb3180704819c7ab53e34b8f161a
+size 2177954752