Dystrio Sculpt default tier of Mistral 7B Instruct v0.3

README.md

@@ -0,0 +1,141 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+language:
+  - en
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+tags:
+  - dystrio
+  - sculpt
+  - pruned
+  - compressed
+  - efficient
+  - structural-pruning
+  - dense
+  - runtime-agnostic
+  - no-custom-kernels
+  - hf-drop-in
+  - drop-in-replacement
+  - smaller
+  - faster
+  - mistral
+datasets:
+  - wikitext
+model-index:
+  - name: Dystrio Sculpt (Mistral-7B-Instruct-v0.3 Default)
+    results:
+      - task:
+          type: text-generation
+        dataset:
+          name: WikiText-103 (validation)
+          type: wikitext
+        metrics:
+          - name: perplexity
+            type: perplexity
+            value: 11.6283
+          - name: ppl_ratio
+            type: ppl_ratio
+            value: 0.923
+---
+
+# dystrio/Mistral-7B-Instruct-v0.3-sculpt-default
+
+> **11% smaller, quality improved (0.923x PPL), drop-in replacement. No custom kernels. No runtime changes.**
+
+Dystrio Sculpt structurally compresses transformer FFN blocks, producing dense models that load with standard `transformers` — no custom code, no new ops, no deployment friction.
+
+This is the **Default** tier of [Mistral 7B Instruct v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
+
+## Quick Start
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("dystrio/Mistral-7B-Instruct-v0.3-sculpt-default", torch_dtype="bfloat16", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("dystrio/Mistral-7B-Instruct-v0.3-sculpt-default")
+
+inputs = tokenizer("The future of AI inference is", return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Benchmark Results
+
+All tiers compiled from [Mistral 7B Instruct v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on A100 80GB, bf16:
+
+| Model | PPL | PPL Ratio | Weights (GB) | Chat Prefill TPS | RAG TTFT p95 (ms) | Decode TPS |
+|-------|-----|-----------|-------------|------------------|-------------------|------------|
+| **Baseline** | 12.5983 | 1.0 | 13.500496 | 10557.3 | 133.325 | 66.8 |
+| **sculpt-default** | 11.6283 | 0.923 | 12.000496 | 11594.3 | 123.069 | 65.3 |
+| **sculpt-production** | 14.2859 | 1.134 | 11.250496 | 12093.9 | 120.842 | 66.0 |
+| **sculpt-throughput** | 16.3355 | 1.2966 | 10.406746 | 12667.0 | 112.683 | 65.8 |
+| **sculpt-experimental** | 25.1515 | 1.9964 | 9.562996 | 13595.9 | 110.293 | 66.5 |
+
+### Key Metrics (this model)
+
+| Metric | Value |
+|--------|-------|
+| **Weights memory** | 12.000496 GB (11% smaller) |
+| **PPL ratio** | 0.923 |
+| **Chat prefill TPS** | 11594.3 (+10%) |
+| **RAG TTFT p95** | 123.069 ms (-8%) |
+| **Decode TPS** | 65.3 (flat) |
+| **Parameters** | 6.44B |
+
+## All Sculpt Tiers
+
+| Tier | HuggingFace | Size | PPL Ratio | Use Case |
+|------|-------------|------|-----------|----------|
+| default | [dystrio/Mistral-7B-Instruct-v0.3-sculpt-default](https://huggingface.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-default) 👈 **this model** | 12.000496 GB | 0.923 | Zero-regret: quality preserved, smaller footprint |
+| production | [dystrio/Mistral-7B-Instruct-v0.3-sculpt-production](https://huggingface.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-production) | 11.250496 GB | 1.134 | Practical savings with modest quality tradeoff |
+| throughput | [dystrio/Mistral-7B-Instruct-v0.3-sculpt-throughput](https://huggingface.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-throughput) | 10.406746 GB | 1.2966 | Maximum usable compression for speed/edge |
+| experimental | [dystrio/Mistral-7B-Instruct-v0.3-sculpt-experimental](https://huggingface.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-experimental) | 9.562996 GB | 1.9964 | Boundary exploration, maximum structural compression |
+
+## What is Dystrio Sculpt?
+
+Dystrio Sculpt is a structural FFN compiler for transformer LLMs. It:
+
+- Removes redundant neurons from SwiGLU feed-forward blocks
+- Uses conductance-aware scoring and adaptive repair
+- Produces standard HuggingFace safetensors output
+- Requires **no custom kernels** and **no runtime changes**
+- Works as a compile step before deployment
+- Stacks with quantization (AWQ, GPTQ, GGUF) for compound savings
+
+## Compatibility
+
+- ✅ HuggingFace Transformers
+- ✅ vLLM
+- ✅ TGI (Text Generation Inference)
+- ✅ llama.cpp / GGUF conversion
+- ✅ AWQ / GPTQ quantization
+- ✅ Any framework that loads standard safetensors
+
+## Benchmark Environment
+
+- **GPU**: NVIDIA A100-SXM4-80GB
+- **dtype**: bf16
+- **Torch**: 2.10.0+cu128
+- **Transformers**: 5.3.0
+- **Deterministic**: True
+- Single-GPU, standard HuggingFace Transformers, no custom kernels.
+
+## Metric Definitions
+
+- **PPL ratio**: WikiText-103 perplexity relative to baseline. <1.0 = quality improved.
+- **Prefill TPS**: Tokens per second during prompt encoding (higher = faster).
+- **TTFT p95**: Time to first token at 95th percentile (lower = faster).
+- **Decode TPS**: Tokens per second during generation (higher = faster).
+- **Weights (GB)**: Model parameter memory (deterministic, runtime-independent).
+
+## Citation
+
+```bibtex
+@misc{dystrio_sculpt_2026,
+  title={Dystrio Sculpt: Structural FFN Compilation for Transformer LLMs},
+  author={Dystrio},
+  year={2026},
+  url={https://huggingface.co/dystrio}
+}
+```

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202f48221cd5e93df34e454bfd684427478e28a1596943a8efc98ac9b105b44d
+size 12885468352

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}