Upload folder using huggingface_hub

.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 +1,41 @@
+---
+license: apache-2.0
+tags:
+  - prime-rl
+  - moe
+  - test-model
+library_name: transformers
+---
+
+<div align="center">
+  <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/61e020e4a343274bb132e138/H2mcdPRWtl4iKLd-OYYBc.jpeg" width="200"/>
+</div>
+
+# glm4-moe-tiny
+
+A small (~543M parameter) GLM-4 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl).
+
+Fine-tuned on [PrimeIntellect/Reverse-Text-SFT](https://huggingface.co/datasets/PrimeIntellect/Reverse-Text-SFT) to provide a non-trivial distribution for KL divergence during RL.
+
+## Quick Start
+
+```bash
+uv run rl @ configs/ci/integration/rl_moe/glm4_moe.toml
+```
+
+See the [Testing MoE at Small Scale](https://github.com/PrimeIntellect-ai/prime-rl/blob/main/docs/testing-moe-at-small-scale.md) guide for full instructions.
+
+## Model Details
+
+| Parameter | Value |
+|-----------|-------|
+| Hidden size | 1024 |
+| Layers | 24 |
+| Experts | 8 |
+| Active experts | 4 |
+| Parameters | ~543M |
+
+## Links
+
+- [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) - RL training framework
+- [PrimeIntellect](https://www.primeintellect.ai/) - Building infrastructure for decentralized AI

chat_template.jinja

@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 256,
+  "n_group": 1,
+  "n_routed_experts": 8,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.2.0.dev0",
+  "use_cache": false,
+  "use_grouped_mm": false,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151329,
+  "transformers_version": "5.2.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5f3d6bcba5415c9ab75c710c612f5e03e85e4b6f8c7ae33fa3fdf09cf8a5fc
+size 1085409024

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|user|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}