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 +1,92 @@
+---
+license: other
+license_name: glm-4
+license_link: https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE
+base_model: THUDM/GLM-4-9B-0414
+tags:
+  - glm
+  - moe
+  - nvfp4
+  - quantized
+  - vllm
+library_name: transformers
+---
+
+# GLM-4.7-Flash-MTP-NVFP4
+
+NVFP4 (Native FP4) quantized version of [THUDM/GLM-4-9B-0414](https://huggingface.co/THUDM/GLM-4-9B-0414) with MTP (Multi-Token Prediction) layers preserved in BF16.
+
+## Model Details
+
+- **Base Model**: THUDM/GLM-4-9B-0414 (GLM-4.7-Flash)
+- **Architecture**: Glm4MoeLiteForCausalLM (MoE with 64 experts, top-4 routing)
+- **Quantization**: NVFP4 with FP8 scales, block size 16
+- **Size**: 20.9 GB (3.0x compression from 62.4 GB BF16)
+- **MTP Layers**: Preserved in BF16 for speculative decoding compatibility
+
+## Quantization Details
+
+| Component | Precision | Notes |
+|-----------|-----------|-------|
+| MLP/FFN layers | NVFP4 | 4-bit weights, 4-bit activations |
+| Attention (self_attn) | BF16 | MLA architecture preserved |
+| MTP layers (eh_proj, shared_head) | BF16 | Speculative decoding compatible |
+| Embeddings | BF16 | Not quantized |
+| Gates | BF16 | Router gates preserved |
+
+### Calibration Settings
+- **Samples**: 512 (from wikitext)
+- **Sequence Length**: 4096
+- **Strategy**: tensor_group with group_size=16
+
+## Benchmark Results
+
+### MMLU-Pro Accuracy
+
+| Model | Accuracy |
+|-------|----------|
+| BF16 (baseline) | 24.83% |
+| NVFP4-v2 (this model) | 23.91% |
+
+### MTP Acceptance Rate
+- **BF16**: 60% acceptance, 1.60 mean accepted length
+- **NVFP4-v2**: 63% acceptance, 1.63 mean accepted length
+
+MTP quality is preserved after quantization.
+
+### Performance Note
+
+MTP speculative decoding currently shows overhead rather than speedup due to missing torch.compile support for the MTP drafter model. For best throughput, run without MTP enabled.
+
+## Usage with vLLM
+
+```bash
+# Standard inference (recommended for performance)
+VLLM_ATTENTION_BACKEND=TRITON_MLA python -m vllm.entrypoints.openai.api_server \
+  --model GadflyII/GLM-4.7-Flash-MTP-NVFP4 \
+  --trust-remote-code \
+  --max-model-len 4096 \
+  --gpu-memory-utilization 0.95
+
+# With MTP speculative decoding (experimental)
+VLLM_ATTENTION_BACKEND=TRITON_MLA python -m vllm.entrypoints.openai.api_server \
+  --model GadflyII/GLM-4.7-Flash-MTP-NVFP4 \
+  --trust-remote-code \
+  --max-model-len 4096 \
+  --gpu-memory-utilization 0.90 \
+  --speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'
+```
+
+## Requirements
+
+- vLLM with NVFP4 support (v0.8.0+)
+- NVIDIA GPU with FP4 support (Blackwell/Ada Lovelace with appropriate kernels)
+- transformers >= 5.0.0
+
+## License
+
+This model inherits the [GLM-4 License](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) from the base model.
+
+## Acknowledgments
+
+Quantized using [llm-compressor](https://github.com/vllm-project/llm-compressor) with compressed-tensors format.

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 +1,80 @@
+{
+  "architectures": [
+    "Glm4MoeLiteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "pad_token_id": 154820,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 202752,
+  "model_type": "glm4_moe_lite",
+  "moe_intermediate_size": 1536,
+  "topk_method": "noaux_tc",
+  "norm_topk_prob": true,
+  "num_attention_heads": 20,
+  "n_group": 1,
+  "topk_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 1,
+  "routed_scaling_factor": 1.8,
+  "num_experts_per_tok": 4,
+  "first_k_dense_replace": 1,
+  "num_hidden_layers": 47,
+  "num_key_value_heads": 20,
+  "num_nextn_predict_layers": 1,
+  "partial_rotary_factor": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "dtype": "bfloat16",
+  "transformers_version": "5.0.0rc0",
+  "q_lora_rank": 768,
+  "kv_lora_rank": 512,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "v_head_dim": 256,
+  "vocab_size": 154880,
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "num_bits": 4,
+          "type": "float",
+          "strategy": "tensor_group",
+          "group_size": 16,
+          "symmetric": true,
+          "dynamic": true
+        },
+        "weights": {
+          "num_bits": 4,
+          "type": "float",
+          "strategy": "tensor_group",
+          "group_size": 16,
+          "symmetric": true
+        },
+        "targets": [
+          "Linear"
+        ]
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "ignore": [
+      "lm_head",
+      "re:.*embed.*",
+      "re:.*gate$",
+      "re:.*self_attn.*",
+      "re:.*\\.eh_proj",
+      "re:.*shared_head\\.head"
+    ],
+    "dynamic": true
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "transformers_version": "5.0.0.dev0"
+}

model-00000-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b660b55607cde8a869c2f841b1bb042d48b611c67ca6e812f188da5bf448a0
+size 5369604384

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9cdccf1c4e022f4107f0e156cfcb3de6e0e7a8e0b8eacc3262014f75e448168
+size 5369189784

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec9fd341824239a59e585a0a58dc9dc5e6e69ab221ae2e56b367df3f1e9ae66
+size 5356474456

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca19c24ab463c1bfb56ece4d78e440d1313e3a4b58b3a99126f223f1b1eaa6f
+size 4817978368

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,321 @@
+{
+  "added_tokens_decoder": {
+    "154820": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154821": {
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154822": {
+      "content": "[gMASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154823": {
+      "content": "[sMASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154824": {
+      "content": "<sop>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154825": {
+      "content": "<eop>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154826": {
+      "content": "<|system|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154827": {
+      "content": "<|user|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154828": {
+      "content": "<|assistant|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154829": {
+      "content": "<|observation|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154830": {
+      "content": "<|begin_of_image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154831": {
+      "content": "<|end_of_image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154832": {
+      "content": "<|begin_of_video|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154833": {
+      "content": "<|end_of_video|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154834": {
+      "content": "<|begin_of_audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154835": {
+      "content": "<|end_of_audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154836": {
+      "content": "<|begin_of_transcription|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154837": {
+      "content": "<|end_of_transcription|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "154838": {
+      "content": "<|code_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154839": {
+      "content": "<|code_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154840": {
+      "content": "<|code_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154841": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154842": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154843": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154844": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154845": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154846": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154847": {
+      "content": "<arg_key>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154848": {
+      "content": "</arg_key>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154849": {
+      "content": "<arg_value>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154850": {
+      "content": "</arg_value>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154851": {
+      "content": "/nothink",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154852": {
+      "content": "<|begin_of_box|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154853": {
+      "content": "<|end_of_box|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154854": {
+      "content": "<|image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "154855": {
+      "content": "<|video|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}