Add model files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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 +1,168 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- vllm
+---
+
+<p align="center">
+  <img alt="gpt-oss-20b" src="https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-20b.svg">
+</p>
+
+<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 smaller `gpt-oss-20b` model. Check out [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) for the larger 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.
+* **Native MXFP4 quantization:** The models are trained with native MXFP4 precision for the MoE layer, 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.
+
+---
+
+# 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-20b"
+
+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-20b
+```
+
+[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-20b
+```
+
+[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-20b
+ollama pull gpt-oss:20b
+ollama run gpt-oss:20b
+```
+
+[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-20b
+lms get openai/gpt-oss-20b
+```
+
+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-20b
+huggingface-cli download openai/gpt-oss-20b --include "original/*" --local-dir gpt-oss-20b/
+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".
+
+# Tool use
+
+The gpt-oss models are excellent for:
+* Web browsing (using built-in browsing tools)
+* Function calling with defined schemas
+* Agentic operations like browser tasks
+
+# Fine-tuning
+
+Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
+
+This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas the larger [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) can be fine-tuned on a single H100 node.

config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "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,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "rope_type": "yarn"
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.55.0.dev0",
+  "use_cache": true,
+  "vocab_size": 201088,
+  "mlp_bias": false
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0.dev0"
+}

model-00000-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d0f997dcfc4462089d536bffe51b4bcea2f872f5c430be09ef8ed392312427
+size 4792272488

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbe328ab445455d6f58dc73852b85873bd626986310abd91cd4d2ce3245eaea
+size 4798702184

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18106b209e9ab35c3406db4f6f12a927364a058b21e9d1373d682e20674b303
+size 4170342232

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 13761264768}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.embed_tokens.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors"}}

original/config.json

@@ -0,0 +1 @@
+{"num_hidden_layers": 24, "num_experts": 32, "experts_per_token": 4, "vocab_size": 201088, "hidden_size": 2880, "intermediate_size": 2880, "swiglu_limit": 7.0, "head_dim": 64, "num_attention_heads": 64, "num_key_value_heads": 8, "sliding_window": 128, "initial_context_length": 4096, "rope_theta": 150000, "rope_scaling_factor": 32.0, "rope_ntk_alpha": 1, "rope_ntk_beta": 32}

original/dtypes.json

@@ -0,0 +1 @@
+{"embedding.weight": "BF16", "block.0.attn.norm.scale": "BF16", "block.0.attn.qkv.weight": "BF16", "block.0.attn.qkv.bias": "BF16", "block.0.attn.sinks": "BF16", "block.0.attn.out.weight": "BF16", "block.0.attn.out.bias": "BF16", "block.0.mlp.norm.scale": "BF16", "block.0.mlp.gate.weight": "BF16", "block.0.mlp.gate.bias": "BF16", "block.0.mlp.mlp1_weight.blocks": "FP4", "block.0.mlp.mlp1_weight.scales": "UE8", "block.0.mlp.mlp1_bias": "BF16", "block.0.mlp.mlp2_weight.blocks": "FP4", "block.0.mlp.mlp2_weight.scales": "UE8", "block.0.mlp.mlp2_bias": "BF16", "block.1.attn.norm.scale": "BF16", "block.1.attn.qkv.weight": "BF16", "block.1.attn.qkv.bias": "BF16", "block.1.attn.sinks": "BF16", "block.1.attn.out.weight": "BF16", "block.1.attn.out.bias": "BF16", "block.1.mlp.norm.scale": "BF16", "block.1.mlp.gate.weight": "BF16", "block.1.mlp.gate.bias": "BF16", "block.1.mlp.mlp1_weight.blocks": "FP4", "block.1.mlp.mlp1_weight.scales": "UE8", "block.1.mlp.mlp1_bias": "BF16", "block.1.mlp.mlp2_weight.blocks": "FP4", "block.1.mlp.mlp2_weight.scales": "UE8", "block.1.mlp.mlp2_bias": "BF16", "block.2.attn.norm.scale": "BF16", "block.2.attn.qkv.weight": "BF16", "block.2.attn.qkv.bias": "BF16", "block.2.attn.sinks": "BF16", "block.2.attn.out.weight": "BF16", "block.2.attn.out.bias": "BF16", "block.2.mlp.norm.scale": "BF16", "block.2.mlp.gate.weight": "BF16", "block.2.mlp.gate.bias": "BF16", "block.2.mlp.mlp1_weight.blocks": "FP4", "block.2.mlp.mlp1_weight.scales": "UE8", "block.2.mlp.mlp1_bias": "BF16", "block.2.mlp.mlp2_weight.blocks": "FP4", "block.2.mlp.mlp2_weight.scales": "UE8", "block.2.mlp.mlp2_bias": "BF16", "block.3.attn.norm.scale": "BF16", "block.3.attn.qkv.weight": "BF16", "block.3.attn.qkv.bias": "BF16", "block.3.attn.sinks": "BF16", "block.3.attn.out.weight": "BF16", "block.3.attn.out.bias": "BF16", "block.3.mlp.norm.scale": "BF16", "block.3.mlp.gate.weight": "BF16", "block.3.mlp.gate.bias": "BF16", "block.3.mlp.mlp1_weight.blocks": "FP4", "block.3.mlp.mlp1_weight.scales": "UE8", "block.3.mlp.mlp1_bias": "BF16", "block.3.mlp.mlp2_weight.blocks": "FP4", "block.3.mlp.mlp2_weight.scales": "UE8", "block.3.mlp.mlp2_bias": "BF16", "block.4.attn.norm.scale": "BF16", "block.4.attn.qkv.weight": "BF16", "block.4.attn.qkv.bias": "BF16", "block.4.attn.sinks": "BF16", "block.4.attn.out.weight": "BF16", "block.4.attn.out.bias": "BF16", "block.4.mlp.norm.scale": "BF16", "block.4.mlp.gate.weight": "BF16", "block.4.mlp.gate.bias": "BF16", "block.4.mlp.mlp1_weight.blocks": "FP4", "block.4.mlp.mlp1_weight.scales": "UE8", "block.4.mlp.mlp1_bias": "BF16", "block.4.mlp.mlp2_weight.blocks": "FP4", "block.4.mlp.mlp2_weight.scales": "UE8", "block.4.mlp.mlp2_bias": "BF16", "block.5.attn.norm.scale": "BF16", "block.5.attn.qkv.weight": "BF16", "block.5.attn.qkv.bias": "BF16", "block.5.attn.sinks": "BF16", "block.5.attn.out.weight": "BF16", "block.5.attn.out.bias": "BF16", "block.5.mlp.norm.scale": "BF16", "block.5.mlp.gate.weight": "BF16", "block.5.mlp.gate.bias": "BF16", "block.5.mlp.mlp1_weight.blocks": "FP4", "block.5.mlp.mlp1_weight.scales": "UE8", "block.5.mlp.mlp1_bias": "BF16", "block.5.mlp.mlp2_weight.blocks": "FP4", "block.5.mlp.mlp2_weight.scales": "UE8", "block.5.mlp.mlp2_bias": "BF16", "block.6.attn.norm.scale": "BF16", "block.6.attn.qkv.weight": "BF16", "block.6.attn.qkv.bias": "BF16", "block.6.attn.sinks": "BF16", "block.6.attn.out.weight": "BF16", "block.6.attn.out.bias": "BF16", "block.6.mlp.norm.scale": "BF16", "block.6.mlp.gate.weight": "BF16", "block.6.mlp.gate.bias": "BF16", "block.6.mlp.mlp1_weight.blocks": "FP4", "block.6.mlp.mlp1_weight.scales": "UE8", "block.6.mlp.mlp1_bias": "BF16", "block.6.mlp.mlp2_weight.blocks": "FP4", "block.6.mlp.mlp2_weight.scales": "UE8", "block.6.mlp.mlp2_bias": "BF16", "block.7.attn.norm.scale": "BF16", "block.7.attn.qkv.weight": "BF16", "block.7.attn.qkv.bias": "BF16", "block.7.attn.sinks": "BF16", "block.7.attn.out.weight": "BF16", "block.7.attn.out.bias": "BF16", "block.7.mlp.norm.scale": "BF16", "block.7.mlp.gate.weight": "BF16", "block.7.mlp.gate.bias": "BF16", "block.7.mlp.mlp1_weight.blocks": "FP4", "block.7.mlp.mlp1_weight.scales": "UE8", "block.7.mlp.mlp1_bias": "BF16", "block.7.mlp.mlp2_weight.blocks": "FP4", "block.7.mlp.mlp2_weight.scales": "UE8", "block.7.mlp.mlp2_bias": "BF16", "block.8.attn.norm.scale": "BF16", "block.8.attn.qkv.weight": "BF16", "block.8.attn.qkv.bias": "BF16", "block.8.attn.sinks": "BF16", "block.8.attn.out.weight": "BF16", "block.8.attn.out.bias": "BF16", "block.8.mlp.norm.scale": "BF16", "block.8.mlp.gate.weight": "BF16", "block.8.mlp.gate.bias": "BF16", "block.8.mlp.mlp1_weight.blocks": "FP4", "block.8.mlp.mlp1_weight.scales": "UE8", "block.8.mlp.mlp1_bias": "BF16", "block.8.mlp.mlp2_weight.blocks": "FP4", "block.8.mlp.mlp2_weight.scales": "UE8", "block.8.mlp.mlp2_bias": "BF16", "block.9.attn.norm.scale": "BF16", "block.9.attn.qkv.weight": "BF16", "block.9.attn.qkv.bias": "BF16", "block.9.attn.sinks": "BF16", "block.9.attn.out.weight": "BF16", "block.9.attn.out.bias": "BF16", "block.9.mlp.norm.scale": "BF16", "block.9.mlp.gate.weight": "BF16", "block.9.mlp.gate.bias": "BF16", "block.9.mlp.mlp1_weight.blocks": "FP4", "block.9.mlp.mlp1_weight.scales": "UE8", "block.9.mlp.mlp1_bias": "BF16", "block.9.mlp.mlp2_weight.blocks": "FP4", "block.9.mlp.mlp2_weight.scales": "UE8", "block.9.mlp.mlp2_bias": "BF16", "block.10.attn.norm.scale": "BF16", "block.10.attn.qkv.weight": "BF16", "block.10.attn.qkv.bias": "BF16", "block.10.attn.sinks": "BF16", "block.10.attn.out.weight": "BF16", "block.10.attn.out.bias": "BF16", "block.10.mlp.norm.scale": "BF16", "block.10.mlp.gate.weight": "BF16", "block.10.mlp.gate.bias": "BF16", "block.10.mlp.mlp1_weight.blocks": "FP4", "block.10.mlp.mlp1_weight.scales": "UE8", "block.10.mlp.mlp1_bias": "BF16", "block.10.mlp.mlp2_weight.blocks": "FP4", "block.10.mlp.mlp2_weight.scales": "UE8", "block.10.mlp.mlp2_bias": "BF16", "block.11.attn.norm.scale": "BF16", "block.11.attn.qkv.weight": "BF16", "block.11.attn.qkv.bias": "BF16", "block.11.attn.sinks": "BF16", "block.11.attn.out.weight": "BF16", "block.11.attn.out.bias": "BF16", "block.11.mlp.norm.scale": "BF16", "block.11.mlp.gate.weight": "BF16", "block.11.mlp.gate.bias": "BF16", "block.11.mlp.mlp1_weight.blocks": "FP4", "block.11.mlp.mlp1_weight.scales": "UE8", "block.11.mlp.mlp1_bias": "BF16", "block.11.mlp.mlp2_weight.blocks": "FP4", "block.11.mlp.mlp2_weight.scales": "UE8", "block.11.mlp.mlp2_bias": "BF16", "block.12.attn.norm.scale": "BF16", "block.12.attn.qkv.weight": "BF16", "block.12.attn.qkv.bias": "BF16", "block.12.attn.sinks": "BF16", "block.12.attn.out.weight": "BF16", "block.12.attn.out.bias": "BF16", "block.12.mlp.norm.scale": "BF16", "block.12.mlp.gate.weight": "BF16", "block.12.mlp.gate.bias": "BF16", "block.12.mlp.mlp1_weight.blocks": "FP4", "block.12.mlp.mlp1_weight.scales": "UE8", "block.12.mlp.mlp1_bias": "BF16", "block.12.mlp.mlp2_weight.blocks": "FP4", "block.12.mlp.mlp2_weight.scales": "UE8", "block.12.mlp.mlp2_bias": "BF16", "block.13.attn.norm.scale": "BF16", "block.13.attn.qkv.weight": "BF16", "block.13.attn.qkv.bias": "BF16", "block.13.attn.sinks": "BF16", "block.13.attn.out.weight": "BF16", "block.13.attn.out.bias": "BF16", "block.13.mlp.norm.scale": "BF16", "block.13.mlp.gate.weight": "BF16", "block.13.mlp.gate.bias": "BF16", "block.13.mlp.mlp1_weight.blocks": "FP4", "block.13.mlp.mlp1_weight.scales": "UE8", "block.13.mlp.mlp1_bias": "BF16", "block.13.mlp.mlp2_weight.blocks": "FP4", "block.13.mlp.mlp2_weight.scales": "UE8", "block.13.mlp.mlp2_bias": "BF16", "block.14.attn.norm.scale": "BF16", "block.14.attn.qkv.weight": "BF16", "block.14.attn.qkv.bias": "BF16", "block.14.attn.sinks": "BF16", "block.14.attn.out.weight": "BF16", "block.14.attn.out.bias": "BF16", "block.14.mlp.norm.scale": "BF16", "block.14.mlp.gate.weight": "BF16", "block.14.mlp.gate.bias": "BF16", "block.14.mlp.mlp1_weight.blocks": "FP4", "block.14.mlp.mlp1_weight.scales": "UE8", "block.14.mlp.mlp1_bias": "BF16", "block.14.mlp.mlp2_weight.blocks": "FP4", "block.14.mlp.mlp2_weight.scales": "UE8", "block.14.mlp.mlp2_bias": "BF16", "block.15.attn.norm.scale": "BF16", "block.15.attn.qkv.weight": "BF16", "block.15.attn.qkv.bias": "BF16", "block.15.attn.sinks": "BF16", "block.15.attn.out.weight": "BF16", "block.15.attn.out.bias": "BF16", "block.15.mlp.norm.scale": "BF16", "block.15.mlp.gate.weight": "BF16", "block.15.mlp.gate.bias": "BF16", "block.15.mlp.mlp1_weight.blocks": "FP4", "block.15.mlp.mlp1_weight.scales": "UE8", "block.15.mlp.mlp1_bias": "BF16", "block.15.mlp.mlp2_weight.blocks": "FP4", "block.15.mlp.mlp2_weight.scales": "UE8", "block.15.mlp.mlp2_bias": "BF16", "block.16.attn.norm.scale": "BF16", "block.16.attn.qkv.weight": "BF16", "block.16.attn.qkv.bias": "BF16", "block.16.attn.sinks": "BF16", "block.16.attn.out.weight": "BF16", "block.16.attn.out.bias": "BF16", "block.16.mlp.norm.scale": "BF16", "block.16.mlp.gate.weight": "BF16", "block.16.mlp.gate.bias": "BF16", "block.16.mlp.mlp1_weight.blocks": "FP4", "block.16.mlp.mlp1_weight.scales": "UE8", "block.16.mlp.mlp1_bias": "BF16", "block.16.mlp.mlp2_weight.blocks": "FP4", "block.16.mlp.mlp2_weight.scales": "UE8", "block.16.mlp.mlp2_bias": "BF16", "block.17.attn.norm.scale": "BF16", "block.17.attn.qkv.weight": "BF16", "block.17.attn.qkv.bias": "BF16", "block.17.attn.sinks": "BF16", "block.17.attn.out.weight": "BF16", "block.17.attn.out.bias": "BF16", "block.17.mlp.norm.scale": "BF16", "block.17.mlp.gate.weight": "BF16", "block.17.mlp.gate.bias": "BF16", "block.17.mlp.mlp1_weight.blocks": "FP4", "block.17.mlp.mlp1_weight.scales": "UE8", "block.17.mlp.mlp1_bias": "BF16", "block.17.mlp.mlp2_weight.blocks": "FP4", "block.17.mlp.mlp2_weight.scales": "UE8", "block.17.mlp.mlp2_bias": "BF16", "block.18.attn.norm.scale": "BF16", "block.18.attn.qkv.weight": "BF16", "block.18.attn.qkv.bias": "BF16", "block.18.attn.sinks": "BF16", "block.18.attn.out.weight": "BF16", "block.18.attn.out.bias": "BF16", "block.18.mlp.norm.scale": "BF16", "block.18.mlp.gate.weight": "BF16", "block.18.mlp.gate.bias": "BF16", "block.18.mlp.mlp1_weight.blocks": "FP4", "block.18.mlp.mlp1_weight.scales": "UE8", "block.18.mlp.mlp1_bias": "BF16", "block.18.mlp.mlp2_weight.blocks": "FP4", "block.18.mlp.mlp2_weight.scales": "UE8", "block.18.mlp.mlp2_bias": "BF16", "block.19.attn.norm.scale": "BF16", "block.19.attn.qkv.weight": "BF16", "block.19.attn.qkv.bias": "BF16", "block.19.attn.sinks": "BF16", "block.19.attn.out.weight": "BF16", "block.19.attn.out.bias": "BF16", "block.19.mlp.norm.scale": "BF16", "block.19.mlp.gate.weight": "BF16", "block.19.mlp.gate.bias": "BF16", "block.19.mlp.mlp1_weight.blocks": "FP4", "block.19.mlp.mlp1_weight.scales": "UE8", "block.19.mlp.mlp1_bias": "BF16", "block.19.mlp.mlp2_weight.blocks": "FP4", "block.19.mlp.mlp2_weight.scales": "UE8", "block.19.mlp.mlp2_bias": "BF16", "block.20.attn.norm.scale": "BF16", "block.20.attn.qkv.weight": "BF16", "block.20.attn.qkv.bias": "BF16", "block.20.attn.sinks": "BF16", "block.20.attn.out.weight": "BF16", "block.20.attn.out.bias": "BF16", "block.20.mlp.norm.scale": "BF16", "block.20.mlp.gate.weight": "BF16", "block.20.mlp.gate.bias": "BF16", "block.20.mlp.mlp1_weight.blocks": "FP4", "block.20.mlp.mlp1_weight.scales": "UE8", "block.20.mlp.mlp1_bias": "BF16", "block.20.mlp.mlp2_weight.blocks": "FP4", "block.20.mlp.mlp2_weight.scales": "UE8", "block.20.mlp.mlp2_bias": "BF16", "block.21.attn.norm.scale": "BF16", "block.21.attn.qkv.weight": "BF16", "block.21.attn.qkv.bias": "BF16", "block.21.attn.sinks": "BF16", "block.21.attn.out.weight": "BF16", "block.21.attn.out.bias": "BF16", "block.21.mlp.norm.scale": "BF16", "block.21.mlp.gate.weight": "BF16", "block.21.mlp.gate.bias": "BF16", "block.21.mlp.mlp1_weight.blocks": "FP4", "block.21.mlp.mlp1_weight.scales": "UE8", "block.21.mlp.mlp1_bias": "BF16", "block.21.mlp.mlp2_weight.blocks": "FP4", "block.21.mlp.mlp2_weight.scales": "UE8", "block.21.mlp.mlp2_bias": "BF16", "block.22.attn.norm.scale": "BF16", "block.22.attn.qkv.weight": "BF16", "block.22.attn.qkv.bias": "BF16", "block.22.attn.sinks": "BF16", "block.22.attn.out.weight": "BF16", "block.22.attn.out.bias": "BF16", "block.22.mlp.norm.scale": "BF16", "block.22.mlp.gate.weight": "BF16", "block.22.mlp.gate.bias": "BF16", "block.22.mlp.mlp1_weight.blocks": "FP4", "block.22.mlp.mlp1_weight.scales": "UE8", "block.22.mlp.mlp1_bias": "BF16", "block.22.mlp.mlp2_weight.blocks": "FP4", "block.22.mlp.mlp2_weight.scales": "UE8", "block.22.mlp.mlp2_bias": "BF16", "block.23.attn.norm.scale": "BF16", "block.23.attn.qkv.weight": "BF16", "block.23.attn.qkv.bias": "BF16", "block.23.attn.sinks": "BF16", "block.23.attn.out.weight": "BF16", "block.23.attn.out.bias": "BF16", "block.23.mlp.norm.scale": "BF16", "block.23.mlp.gate.weight": "BF16", "block.23.mlp.gate.bias": "BF16", "block.23.mlp.mlp1_weight.blocks": "FP4", "block.23.mlp.mlp1_weight.scales": "UE8", "block.23.mlp.mlp1_bias": "BF16", "block.23.mlp.mlp2_weight.blocks": "FP4", "block.23.mlp.mlp2_weight.scales": "UE8", "block.23.mlp.mlp2_bias": "BF16", "norm.scale": "BF16", "unembedding.weight": "BF16"}

original/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3340a61d1a0391e8c5b5d3463d18d4c48129a84bbc04a554c762c99020aa06ed
+size 13761300984

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|return|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}