Phi-4-mini int4 shards (1 stage, ov-runtime, export v5_canonical_inputs)

.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
+int4/stages-1/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: microsoft/Phi-4-mini-instruct
+tags:
+  - cascadia
+  - openvino
+  - int4
+  - pipeline-parallel
+library_name: cascadia
+---
+
+# Phi-4-mini Instruct — Cascadia int4 shards
+
+Pre-exported [Cascadia](https://github.com/labscommunity/cascadia) inference shards for
+`microsoft/Phi-4-mini-instruct`, so operators can deploy without running an export themselves.
+
+These are **OpenVINO IR** artifacts for Cascadia's `ov-runtime` engine. They are not
+loadable by `transformers` — see *Using these* below.
+
+## Contents
+
+| Preset | Path | Stages | Quant | Size |
+|---|---|---|---|---|
+| `1` | `int4/stages-1` | 1 | int4 | 1.9 GB |
+
+```
+int4/stages-1/
+  pipeline_config.json     # model geometry: layers, heads, rope, arch tag
+  stage_0/
+    openvino_model.xml     # IR graph
+    openvino_model.bin     # int4 weights
+    stage_config.json      # layer_start, layer_end, has_embed, has_head
+  tokenizer/               # tokenizer.json + configs
+```
+
+`cascadia.json` at the repo root is the machine-readable index (sizes, checksums,
+export version) that Cascadia's model registry reads.
+
+## Using these
+
+```bash
+hf download communitylabs/cascadia-phi-4-mini-int4 --local-dir ./phi-4-mini
+cascadia worker --model ./phi-4-mini/int4/stages-1 --engine ov-runtime
+```
+
+The worker takes a **local path**, never a HuggingFace id — Cascadia workers never
+download or convert models at serve time.
+
+## Provenance
+
+Exported with Cascadia's `tools/export_shards.py`, `export_version: v5_canonical_inputs`.
+
+| | |
+|---|---|
+| Source | `microsoft/Phi-4-mini-instruct` |
+| Layers | 32 |
+| Hidden size | 3072 |
+| Attention heads | 24 (8 KV) |
+| Vocab | 200064 |
+| RoPE theta | 10000.0 (partial rotary factor 0.75) |
+| Quantization | int4 (NNCF, group size 128) |
+
+Quantization is lossy. For anything quality-sensitive, benchmark against the source
+model rather than assuming parity.
+
+## License
+
+MIT, inherited from [`microsoft/Phi-4-mini-instruct`](https://huggingface.co/microsoft/Phi-4-mini-instruct).
+These shards are a derivative work; the upstream license and its terms apply.

cascadia.json

@@ -0,0 +1,27 @@
+{
+  "schema": "cascadia-shards-v1",
+  "model": {
+    "id": "phi-4-mini",
+    "name": "Phi-4-mini Instruct",
+    "paramsB": 3.8,
+    "source": "microsoft/Phi-4-mini-instruct",
+    "arch": "phi"
+  },
+  "license": {
+    "spdx": "MIT",
+    "url": "https://huggingface.co/microsoft/Phi-4-mini-instruct",
+    "gatedUpstream": false
+  },
+  "engine": "ov-runtime",
+  "splitMode": "per-export",
+  "artifacts": {
+    "1": {
+      "path": "int4/stages-1",
+      "quant": "int4",
+      "stages": 1,
+      "sizeBytes": 1996385342,
+      "sha256Bin": "22d658ed8bb601d56f3d6ee2bb488d664c0a60755a82f44229a263a549c40a22",
+      "exportVersion": "v5_canonical_inputs"
+    }
+  }
+}

int4/stages-1/pipeline_config.json

@@ -0,0 +1,14 @@
+{
+  "model_id": "microsoft/Phi-4-mini-instruct",
+  "num_stages": 1,
+  "num_layers": 32,
+  "hidden_size": 3072,
+  "num_attention_heads": 24,
+  "num_key_value_heads": 8,
+  "vocab_size": 200064,
+  "rope_theta": 10000.0,
+  "partial_rotary_factor": 0.75,
+  "arch_tag": "phi",
+  "quantization": "int4",
+  "export_version": "v5_canonical_inputs"
+}

int4/stages-1/stage_0/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d658ed8bb601d56f3d6ee2bb488d664c0a60755a82f44229a263a549c40a22
+size 1978245642

int4/stages-1/stage_0/stage_config.json

@@ -0,0 +1,23 @@
+{
+  "stage": 0,
+  "layer_start": 0,
+  "layer_end": 32,
+  "has_embed": true,
+  "has_head": true,
+  "quantization": "int4",
+  "hidden_size": 3072,
+  "vocab_size": 200064,
+  "num_layers_total": 32,
+  "num_kv_heads": 8,
+  "head_dim": 128,
+  "stateful": true,
+  "rope_theta": 10000.0,
+  "partial_rotary_factor": 0.75,
+  "arch_tag": "phi",
+  "target": "cpu-gpu",
+  "static_seq": null,
+  "static_context": null,
+  "inputs": "input_ids/hidden_states, attention_mask, position_ids, beam_idx (KV cache is internal state)",
+  "cache_reorder": true,
+  "export_version": "v5_canonical_inputs"
+}

int4/stages-1/tokenizer/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

int4/stages-1/tokenizer/config.json

@@ -0,0 +1,144 @@
+{
+  "_name_or_path": "Phi-4-mini-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
+    "AutoTokenizer": "Xenova/gpt-4o"
+  },
+  "bos_token_id": 199999,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "vocab_size": 200064
+}

int4/stages-1/tokenizer/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": [
+    200020,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.45.0"
+}

int4/stages-1/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

int4/stages-1/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
+size 15524095

int4/stages-1/tokenizer/tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "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
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}