upload checkpoint

README.md

@@ -0,0 +1,164 @@
+---
+language:
+- en
+library_name: transformers
+tags:
+- glm
+- MOE
+- pruning
+- compression
+license: mit
+name: cerebras/GLM-4.7-Flash-REAP-23B-A3B
+description: >
+  This model was obtained by uniformly pruning 25% of experts in GLM-4.7-Flash using the REAP method.
+readme: >
+  https://huggingface.co/cerebras/GLM-4.7-Flash-REAP-23B-A3B/main/README.md
+license_link: https://huggingface.co/zai-org/GLM-4.7-Flash/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- zai-org/GLM-4.7-Flash
+---
+
+<p align="center">
+  <em>𓌳 <strong>REAP</strong>𓌳  the Experts: Why Pruning Prevails for One-Shot MoE Compression</em><br>
+  <img src="https://i.imgur.com/rmzG3gg.png" alt="REAP" width="75%">
+</p>
+
+# GLM-4.7-Flash-REAP-23B-A3B
+
+## ✨ Highlights
+
+Introducing **GLM-4.7-Flash-REAP-23B-A3B**, a **memory-efficient compressed variant** of GLM-4.7-Flash that maintains near-identical performance while being **25% lighter**.
+
+This model was created using **REAP (Router-weighted Expert Activation Pruning)**, a novel expert pruning method that selectively removes redundant experts while preserving the router's independent control over remaining experts. Key features include:
+
+- **Near-Lossless Performance**: Maintains almost identical accuracy on code generation, agentic coding, and function calling tasks compared to the full 355B model
+- **25% Memory Reduction**: Compressed from 355B to 218B parameters, significantly lowering deployment costs and memory requirements
+- **Preserved Capabilities**: Retains all core functionalities including code generation, agentic workflows, repository-scale understanding, and function calling
+- **Drop-in Compatibility**: Works with vanilla vLLM - no source modifications or custom patches required
+- **Optimized for Real-World Use**: Particularly effective for resource-constrained environments, local deployments, and academic research
+
+---
+## 📋 Model Overview
+
+**GLM-4.7-Flash-REAP-23B-A3B** has the following specifications:
+
+- **Base Model**: GLM-4.7-Flash
+- **Compression Method**: REAP (Router-weighted Expert Activation Pruning)
+- **Compression Ratio**: 25% expert pruning
+- **Type**: Sparse Mixture-of-Experts (SMoE) Causal Language Model
+- **Number of Parameters**: 23B total, 3B activated per token
+- **Number of Layers**: 47
+- **Number of Attention Heads**: 20 for QKV
+- **Number of Experts**: 48 (uniformly pruned from 64)
+- **Number of Activated Experts**: 4 per token
+- **Context Length**: 202,752 tokens
+- **License**: MIT
+
+---
+
+## 📊 Evaluations
+
+<table>
+  <thead>
+    <tr>
+      <th align="left">Benchmark</th>
+      <th align="center">GLM-4.7-Flash</th>
+      <th align="center"><a href="https://huggingface.co/cerebras/GLM-4.7-Flash-REAP-23B-A3B">GLM-4.7-Flash-REAP-23B-A3B</a></th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><strong>Compression</strong></td>
+      <td align="center">—</td>
+      <td align="center">25%</td>
+    </tr>
+    <tr>
+      <td colspan="5" align="center"><strong>Coding</strong></td>
+    </tr>
+    <tr>
+      <td><strong>HumanEval</strong></td>
+      <td align="center">94.5</td>
+      <td align="center">95.1</td>
+    </tr>
+    <tr>
+      <td><strong>HumanEval+</strong></td>
+      <td align="center">89.0</td>
+      <td align="center">89.0</td>
+    </tr>
+</table>
+
+🟩 *This checkpoint maintains almost identical performance while being 25% lighter.*
+
+For more details on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).
+
+---
+
+## 🚀 Deployment
+
+You can deploy the model directly using the **latest vLLM** (that supports GLM4.7-Flash), no source modifications or custom patches required.
+
+```bash
+vllm serve cerebras/GLM-4.7-Flash-REAP-23B-A3B \
+    --tensor-parallel-size 4 \
+    --reasoning-parser glm45 \
+    --tool-call-parser glm47 \
+    --enable-auto-tool-choice
+```
+
+If you encounter insufficient memory when running this model, you might need to set a lower value for `--max-num-seqs` flag (e.g. set to 64).
+
+
+## 🧩 Model Creation
+
+This checkpoint was created by applying the **REAP (Router-weighted Expert Activation Pruning)** method uniformly across all Mixture-of-Experts (MoE) blocks of **GLM-4.7**, with a **25% pruning rate**.
+
+### How REAP Works
+
+REAP selects experts to prune based on a novel **saliency criterion** that considers both:
+- **Router gate values**: How frequently and strongly the router activates each expert
+- **Expert activation norms**: The magnitude of each expert's output contributions
+
+This dual consideration ensures that experts contributing minimally to the layer's output are pruned, while preserving those that play critical roles in the model's computations.
+
+### Key Advantages
+
+- **One-Shot Compression**: No fine-tuning required after pruning - the model is immediately ready for deployment
+- **Preserved Router Control**: Unlike expert merging methods, REAP maintains the router's independent, input-dependent control over remaining experts, avoiding "functional subspace collapse"
+- **Generative Task Superiority**: REAP significantly outperforms expert merging approaches on generative benchmarks (code generation, creative writing, mathematical reasoning) while maintaining competitive performance on discriminative tasks
+
+### Calibration
+
+The model was calibrated using a diverse mixture of domain-specific datasets including:
+- Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1))
+- Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k))
+- Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))
+
+📚 For more details, refer to the following resources:
+
+- [🧾 arXiv Preprint](https://arxiv.org/abs/2510.13999)
+- [🧾 REAP Blog](https://www.cerebras.ai/blog/reap)
+- [💻 REAP Codebase (GitHub)](https://github.com/CerebrasResearch/reap)
+
+---
+
+## ⚖️ License
+
+This model is derived from
+**[`zai-org/GLM-4.7-Flash`](https://huggingface.co/zai-org/GLM-4.7-Flash)**
+and distributed under the **MIT license**.
+
+---
+
+## 🧾 Citation
+
+If you use this checkpoint, please cite the REAP paper:
+
+```bibtex
+@article{lasby-reap,
+  title={REAP the Experts: Why Pruning Prevails for One-Shot MoE compression},
+  author={Lasby, Mike and Lazarevich, Ivan and Sinnadurai, Nish and Lie, Sean and Ioannou, Yani and Thangarasa, Vithursan},
+  journal={arXiv preprint arXiv:2510.13999},
+  year={2025}
+}
+```

chat_template.jinja

@@ -0,0 +1,86 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,104 @@
+{
+  "architectures": [
+    "Glm4MoeLiteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "mlp_layer_types": [
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm4_moe_lite",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 48,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 20,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 47,
+  "num_key_value_heads": 20,
+  "num_nextn_predict_layers": 0,
+  "pad_token_id": 154820,
+  "partial_rotary_factor": 1.0,
+  "pretraining_tp": 1,
+  "q_lora_rank": 768,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "partial_rotary_factor": 1.0,
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.8,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.0.0rc3",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b230d13ddfce3d53835b9b3b97c7219321be8e9f3465d84de787e4a6b6459720
+size 5363354288

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642adcd78a9d886f6300135a629cf74245996e5fc58ff10add693f0e43b5dd90
+size 5364819824

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d32b9b4173bb8179e25a66ce0c70ff3f10684d9120ffa7ba0ffb38011437431
+size 5365136840

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c82d622e113410c959e165e698e87a9d0fd3730a9e99be5acc610ee747dff73
+size 5364820504

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d160458b9dab6c72f379948724d582981a78ce5d964db308f95046c3cacd7b64
+size 5365136840

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1259f8393bdd3cec42f1eb6ab8b91fa5b1693a69dd0a401a27de47e5c16ef4
+size 5364820504

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd83eec1cccf4bf3d3f4af0e61d0035d9c395fbf18849baf7f7d01366ee29b95
+size 5365136840

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff1b3e5fd3dcd5a6c2f01342b0e2ae609a022b73d4d8fce8555e26bc253e0f0
+size 5364820488

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8233be0ef2f6327e34b9ce892dc141c9a9aa86f784fb616d1587557fa88cc4e
+size 3075099000

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
+size 20217442

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": true,
+  "model_max_length": 128000,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}