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
+axquant_plan.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,177 @@
+---
+license: apache-2.0
+library_name: mlx
+base_model: deepseek-ai/DeepSeek-V4-Flash
+base_model_relation: quantized
+pipeline_tag: text-generation
+tags:
+- mlx
+- apple-silicon
+- quantized
+- mixed-precision
+- axquant
+- axq
+- development
+- deepseek-v4
+- 2bit
+- 2-bit
+- mtp
+---
+
+# AX-DeepSeek-V4-Flash-MLX-AXQ-2bit
+
+An **AXQuant (AXQ)** mixed-precision MLX checkpoint for Apple Silicon, converted directly from
+the BF16 source model. The language path is quantized while the multi-token-prediction (MTP) head are preserved at BF16 in the checkpoint (or a bound sidecar when present).
+
+> **Development evidence — not a certified AXQuant release.** This package has conversion and
+> artifact-integrity records, but it does not publish measured quality, long-context, kernel-speed,
+> or MTP-speed evidence. Do not interpret the AXQ product label as a benchmark claim.
+
+
+## Model details
+
+| Property | Value |
+| --- | --- |
+| Base model | [deepseek-ai/DeepSeek-V4-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/tree/60d8d70770c6776ff598c94bb586a859a38244f1) |
+| Source revision | `60d8d70770c6776ff598c94bb586a859a38244f1` |
+| Product family | `deepseek-v4` |
+| Source architecture | `DeepseekV4ForCausalLM` (mixture of experts (MoE)); text path optimized |
+| Main-model parameters | 284.33B logical parameters |
+| Quantizer | AXQuant `1.5.1` |
+| Hub budget class | `2bit` |
+| AXQuant base precision class | `2bit-experimental` |
+| Planned storage-adjusted BPW | 3.4232 |
+| Measured main-model BPW | 3.1329 |
+| Measured total BPW, including MTP | **3.1605** |
+| Safetensors weight size | 114.94 GB |
+| Approximate complete download | 115.02 GB |
+| Configured maximum context | 1,048,576 tokens; practical limits depend on unified memory |
+| Primary MLX runtime | MLX-LM |
+| AX Engine native execution | Not established; no validated native manifest is included |
+| MTP present | `True` |
+| Vision present | `False` |
+| Audio present | `False` |
+
+This repository contains MLX Safetensors. It does **not** contain PyTorch or GGUF weights.
+
+## Choosing an AXQ pack
+
+AXQ names describe a **storage-budget product class**, not one uniform precision applied to every
+tensor. Protected tensors remain at higher precision, so the exact measured BPW is authoritative.
+In particular, a `6bit`-named mixed plan may retain `4bit` as its base precision while selecting
+6-bit, 8-bit, or BF16 for other tensors to meet an approximately 6-BPW total budget. Protection
+floors can also raise a `4bit`-named pack close to (or above) a `6bit` budget on small or heavily
+protected models. When that collapse happens, AutomatosX does **not** publish a separate
+misleading `4bit` sibling for that base.
+
+
+| Sibling | Intended trade-off |
+| --- | --- |
+| [4bit sibling](https://huggingface.co/AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-2bit) | Lower-storage AXQ budget; check its exact BPW |
+| [4bit sibling](https://huggingface.co/AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-4bit) | Higher average precision near the 4-BPW budget |
+
+See the [AutomatosX MLX model catalog](https://huggingface.co/collections/AutomatosX/automatosx-mlx-model-catalog)
+for related MLX and OptiQ alternatives.
+
+## Download
+
+```bash
+python -m pip install -U huggingface_hub
+hf download AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-2bit --local-dir ./AX-DeepSeek-V4-Flash-MLX-AXQ-2bit
+```
+
+Allow at least 115.02 GB of free disk space. Pin the resulting Hub commit in reproducible
+deployments rather than relying indefinitely on `main`.
+
+## Run with MLX-LM
+
+```bash
+python -m pip install -U mlx-lm
+mlx_lm.generate \
+  --model AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-2bit \
+  --prompt "Explain mixed-precision quantization in three sentences." \
+  --max-tokens 128 \
+  --temp 0.0
+```
+
+MLX-LM compatibility covers standard **text/backbone inference**. It may ignore AXQuant runtime
+metadata and optional sidecars (`vision.safetensors`, `mtp.safetensors`); this command therefore
+does not establish MTP acceleration or vision-language quality. The artifact records MLX
+`0.32.0` and MLX-LM `0.31.3` from conversion.
+
+## AX Engine status
+
+This package does **not** include a validated native `model-manifest.json`, so AX Engine execution
+is not established by this release. The AX Engine fields in `axquant_runtime.json` describe the
+intended compatibility contract, not observed runtime evidence. Use the architecture-specific MLX
+runtime path above. The artifact records AX Engine version
+`6.11.1`, but version discovery alone is not a runtime check.
+
+## Quantization layout
+
+| Main-weight precision | Parameters | Share |
+| --- | ---: | ---: |
+| `2bit` | 278.11B | 95.59% |
+| `4bit` | 3.64B | 1.25% |
+| `8bit` | 529.53M | 0.18% |
+| `bf16` | 8.67B | 2.98% |
+
+- Quantization methods: `affine, bf16`.
+- Group sizes used by quantized assignments: `32`.
+- MTP sidecar: 1575 tensors, 6.61B parameters, 3.59 GB, BF16, F32, F8_E4M3, F8_E8M0, I8.
+- Vision sidecar: not included.
+- Optimization scope: `text-path`.
+- Support tier: `convertible`.
+
+BF16 sidecars, when present, are included in total download size. Their presence does not by itself
+establish MTP acceleration or vision-language quality.
+
+## Evidence and validation status
+
+| Check | Status |
+| --- | --- |
+| Planning evidence | `architecture_prior` |
+| Calibration | none; the allocation is based on architecture priors |
+| Quantizer execution | 33492/33492 recorded module conversions succeeded; 0 fallbacks |
+| AX Engine native manifest | not included |
+| Quality versus BF16 or uniform baselines | Not published; no quality-retention claim |
+| MTP acceptance and speed | not measured; no MTP speedup claim |
+| AX Engine kernel evidence | `unmeasured` |
+| Vision-language quality | Not applicable (no vision tower in this package) |
+| Speech-recognition quality | Not applicable |
+| Long-context quality | 1,048,576-token capacity is config metadata, not a validated claim |
+| Release certification | **Not certified**; formal AXQuant M0-M8 gates are not closed |
+
+## Intended use and limitations
+
+- Intended for local development and evaluation on Apple Silicon with MLX-compatible runtimes.
+- No minimum unified-memory figure is claimed; loadability depends on model size, context length,
+  KV-cache policy, runtime buffers, and other processes using unified memory.
+- Architecture-prior allocation is not measured sensitivity. It must not be presented as measured
+  model quality.
+- MTP may be ignored outside AX Engine and its speedup is unmeasured for this exact checkpoint.
+- The configured context window can require substantially more memory as the KV cache grows.
+- AX Engine execution is not established because this package has no validated native manifest.
+
+- Upstream capabilities, limitations, biases, and responsible-use guidance still apply.
+
+## Provenance and audit files
+
+- [`axquant_manifest.json`](axquant_manifest.json): package identity, byte accounting, runtime
+  contract, software versions, and file checksums.
+- [`axquant_plan.json`](axquant_plan.json): per-tensor precision decisions and planning evidence.
+- [`axquant_quantizer_execution.json`](axquant_quantizer_execution.json): conversion coverage and
+  fallback records.
+- [`axquant_runtime.json`](axquant_runtime.json): declared AX Engine and MLX compatibility metadata; runtime checks remain separate evidence.
+- [`axquant_mtp_sidecar_manifest.json`](axquant_mtp_sidecar_manifest.json): MTP tensor provenance.
+
+All published provenance uses repository-relative paths. Local source paths are stripped before
+publication. The checkpoint was converted from BF16 rather than re-quantized from an OptiQ
+artifact. If an OptiQ repository is published separately, it uses a different quantizer and
+should not be assumed to have identical BPW or quality.
+
+## License
+
+The checkpoint follows the upstream model license where applicable (often Apache License 2.0). See
+the [deepseek-ai/DeepSeek-V4-Flash model card](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/tree/60d8d70770c6776ff598c94bb586a859a38244f1) for license terms, model
+limitations, and responsible-use guidance.

axquant_manifest.json

@@ -0,0 +1,305 @@
+{
+  "axquant_version": "1.5.1",
+  "calibration": null,
+  "created_at": "2026-08-08T10:38:10.173868Z",
+  "effective_bpw": 3.4231523262554298,
+  "files": [
+    {
+      "path": "README.md",
+      "sha256": "60d299bb6aaeed366a664d685c1aac7927f13c2db5415cb2a89e9d3c9f7939f1",
+      "size_bytes": 8056
+    },
+    {
+      "path": "axquant_mtp_sidecar_manifest.json",
+      "sha256": "46bf815a0ef2d1aeee9da90575bcc5897d42ced1a5af4ea095a3e0ecfac26298",
+      "size_bytes": 938
+    },
+    {
+      "path": "axquant_plan.json",
+      "sha256": "68dfeebb6c03f5131d5f252500add55c8f6e5cb8964a5cc07c7946263e1891d7",
+      "size_bytes": 61242784
+    },
+    {
+      "path": "axquant_quantizer_execution.json",
+      "sha256": "cba3419779c8fc31b5441101c409633d22d89f7207045a2f37bbc081099f30a9",
+      "size_bytes": 8049291
+    },
+    {
+      "path": "axquant_runtime.json",
+      "sha256": "58321f239d355ee34d36b7d38b61474cb8ad6bd6a7c03212621d0b729aa68fa1",
+      "size_bytes": 1676
+    },
+    {
+      "path": "config.json",
+      "sha256": "62d2e80106dbc1f93ff640a72b465969ab41721a50ddafb790ed4a0bdebc289a",
+      "size_bytes": 159869
+    },
+    {
+      "path": "generation_config.json",
+      "sha256": "5fccff80f55a4d455bbe516bdd552edf3e9623df95e99fbf2a3c3389fdf91af0",
+      "size_bytes": 170
+    },
+    {
+      "path": "model-00001-of-00022.safetensors",
+      "sha256": "d66390107e70368b1bd4cf11ebea0de190243b8f4339475e3ac65324e6d7f1c5",
+      "size_bytes": 4871235441
+    },
+    {
+      "path": "model-00002-of-00022.safetensors",
+      "sha256": "ba8c2ccd94f6544b969e7054be4e18d9ff41de4028d93365d1c7b88e8d2d8202",
+      "size_bytes": 5105189683
+    },
+    {
+      "path": "model-00003-of-00022.safetensors",
+      "sha256": "4b6d6dc041d105d646bdc075bb561e722b05fb9c23441067c17295917ff18823",
+      "size_bytes": 5102087876
+    },
+    {
+      "path": "model-00004-of-00022.safetensors",
+      "sha256": "4772db7a257330e1b6216e0d7859c22d6d0b83818a221603bdd8b99ae20add47",
+      "size_bytes": 5102088000
+    },
+    {
+      "path": "model-00005-of-00022.safetensors",
+      "sha256": "66c9eebe5e2c386afdf56ae71e550cd5964a04234bee5672954308c52e8860be",
+      "size_bytes": 5102087938
+    },
+    {
+      "path": "model-00006-of-00022.safetensors",
+      "sha256": "9f599f16e8bd001942bfc5022b357f0062d09a14f8053597787843a2266f1170",
+      "size_bytes": 5102088008
+    },
+    {
+      "path": "model-00007-of-00022.safetensors",
+      "sha256": "2828807a642d64e4f1948d08cf44d88ac3eb46ff0e462174d54b6f4adfb90e93",
+      "size_bytes": 5102088114
+    },
+    {
+      "path": "model-00008-of-00022.safetensors",
+      "sha256": "73e646531d89ad50472e66b1adfae28618a9694c6b735fb776741c25ae1bb9e6",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00009-of-00022.safetensors",
+      "sha256": "e799cc2e1d2c58973ec760e0213f1b5d4b8842f6200eb5a43ff12c7dd42f2e44",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00010-of-00022.safetensors",
+      "sha256": "d142f34e678a0304b53b0b6134efffd6043abb8d388f798c63069d6846e2c348",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00011-of-00022.safetensors",
+      "sha256": "6eedbf22e55caad37bb798dae3fcc1552f6ead7a0e341682a1f1c1ae7f2db84b",
+      "size_bytes": 5102088048
+    },
+    {
+      "path": "model-00012-of-00022.safetensors",
+      "sha256": "2d81890a0a6fd8b1d2b889f5c57a66c9f1139dcbc2b1a8a3845504787d6e5049",
+      "size_bytes": 5102088032
+    },
+    {
+      "path": "model-00013-of-00022.safetensors",
+      "sha256": "21d341534831ea31d5a62b23fd63639de636ca2156138cadb4da13a32d4cc2fd",
+      "size_bytes": 5102088114
+    },
+    {
+      "path": "model-00014-of-00022.safetensors",
+      "sha256": "f5916c727a169952a90b4ae58600c07b097b9490bec791645021fb6f98d96d54",
+      "size_bytes": 5102088114
+    },
+    {
+      "path": "model-00015-of-00022.safetensors",
+      "sha256": "c977aeb7016ecb65819a07a9782d3e766ca9e1026bcd57822af5accd5a14578f",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00016-of-00022.safetensors",
+      "sha256": "70cea71cfa3978ed76cf53514acfd1e8db095ffff5b8b17bf9ef1fb6530988cc",
+      "size_bytes": 5102088082
+    },
+    {
+      "path": "model-00017-of-00022.safetensors",
+      "sha256": "ee25e4b960ac2b7732ec50d65e3c79cc8aacd8c5409bbcca6930a4bd0c677ebb",
+      "size_bytes": 5102088114
+    },
+    {
+      "path": "model-00018-of-00022.safetensors",
+      "sha256": "6c643db0afbeaf01d92c47143fede1cf756e33c167e99103ee151f0fcc779338",
+      "size_bytes": 5102088044
+    },
+    {
+      "path": "model-00019-of-00022.safetensors",
+      "sha256": "be88b3ee2a1dd82c033c81d23bc3de994850aff56aad2dc55e4a3db7177b678f",
+      "size_bytes": 5102088034
+    },
+    {
+      "path": "model-00020-of-00022.safetensors",
+      "sha256": "433030ffdd4a5274d3662c7b3af426bfc8d4168cdbe12e9fce7fa46d6c3fc5a2",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00021-of-00022.safetensors",
+      "sha256": "a8270649726710221d76998e3448dbb36e5bcd7ba7b05404edcccc9283f371d4",
+      "size_bytes": 5102088112
+    },
+    {
+      "path": "model-00022-of-00022.safetensors",
+      "sha256": "25dbb17146eb0c2cf131b3ec95d4b4b517a76a02e474541507681047fb5b98e5",
+      "size_bytes": 4432834385
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "sha256": "1a35387e7cee7bc73301f2a1d90c2419482658b7afa4436fa987199b90a8dc8a",
+      "size_bytes": 209031
+    },
+    {
+      "path": "mtp.safetensors",
+      "sha256": "445e2f72d140a344ab3429b0a073ba2dc3f4198b40b0b7fe7ccc5bc41531806c",
+      "size_bytes": 3593958116
+    },
+    {
+      "path": "mtplx_runtime.json",
+      "sha256": "119b930ed4b470a08008aa2a51b4a83162907a85b8455f559cffa03e33236ed6",
+      "size_bytes": 108
+    },
+    {
+      "path": "tokenizer.json",
+      "sha256": "8421075aceec0741baf15179b6c337f443f9029e53ea88d8c1e909dd0d69b70b",
+      "size_bytes": 10071664
+    },
+    {
+      "path": "tokenizer_config.json",
+      "sha256": "21aa165d554e2c2f252a49730b71962edc15c36bbfa4b090ab7bd3340a2fa549",
+      "size_bytes": 397
+    }
+  ],
+  "format": "mlx",
+  "logical_parameters": 290944616402,
+  "main_logical_parameters": 284334567511,
+  "main_weight_file_size_bytes": 111348932699,
+  "measured_main_bpw": 3.132898927449397,
+  "measured_total_bpw": 3.1605435353698432,
+  "mtp_acceptance_retention": null,
+  "mtp_distribution": {
+    "bf16": {
+      "fraction": 1.0,
+      "parameters": 6610048891
+    }
+  },
+  "mtp_measured_speedup": null,
+  "mtp_policy": {
+    "candidate_bits": [
+      8,
+      16
+    ],
+    "min_bits": 8,
+    "mode": "protected",
+    "optimize_for_acceptance": true,
+    "preserve_external_sidecar": true,
+    "protect_norms": true,
+    "protect_output_head": true
+  },
+  "mtp_present": true,
+  "mtp_weight_file_size_bytes": 3593958116,
+  "plan_sha256": "82be00de00e2883e066b6f5ca7fab13f9a479b2f645e41697c5bb327b93fdbbc",
+  "profile": "general",
+  "protected_weight_file_size_bytes": 0,
+  "quantizer": "axquant",
+  "runtime": {
+    "ax_engine": {
+      "decode_kernel": null,
+      "fused_mtp": null,
+      "kernel_evidence": "unmeasured",
+      "model_manifest": "model-manifest.json",
+      "preferred_group_size": 32
+    },
+    "compatible_runtimes": [
+      {
+        "compatibility_level": "B",
+        "manifest": "config.json",
+        "mtp_support": "runtime-dependent",
+        "name": "mlx-lm",
+        "notes": [
+          "Standard backbone inference is the compatibility target.",
+          "AXQuant MTP metadata may be ignored by MLX-LM."
+        ],
+        "standard_inference": true,
+        "standard_mlx_weights": true,
+        "support_level": "standard-inference"
+      }
+    ],
+    "created_at": "2026-08-08T10:35:23.323798Z",
+    "kv_cache": null,
+    "memory_policy": {
+      "kv_cache_precision": "runtime-default",
+      "mtp_buffers": "preallocate-when-enabled",
+      "prefix_cache": "runtime-managed",
+      "unified_memory_safety_margin": "benchmark-required"
+    },
+    "mtp": {
+      "acceptance_retention": null,
+      "detected": true,
+      "draft_tokens": 1,
+      "enabled_by_default": true,
+      "head_precision": null,
+      "measured_speedup": null,
+      "optimized": false,
+      "recommended_temperature_max": null,
+      "sidecar_file": "mtp.safetensors",
+      "verification_mode": "runtime-default"
+    },
+    "optimization_scope": "text-path",
+    "primary_runtime": {
+      "compatibility_level": "A",
+      "manifest": "model-manifest.json",
+      "mtp_support": "native",
+      "name": "ax-engine",
+      "notes": [
+        "Runtime claims require a passing AX Engine doctor and benchmark report."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "optimized"
+    },
+    "schema_version": "axquant.runtime.v1"
+  },
+  "schema_version": "axquant.artifact.v2",
+  "software_versions": {
+    "ax_engine": "6.11.1",
+    "axquant": "1.5.1",
+    "mlx": "0.32.0",
+    "mlx_lm": "0.31.3",
+    "pydantic": "2.13.4",
+    "python": "3.13.15",
+    "safetensors": "0.8.0"
+  },
+  "source_model": {
+    "architecture": "DeepseekV4ForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "deepseek-ai/DeepSeek-V4-Flash",
+    "revision": "60d8d70770c6776ff598c94bb586a859a38244f1"
+  },
+  "target_class": "2bit-experimental",
+  "weight_distribution": {
+    "2bit": {
+      "fraction": 0.9558778727829667,
+      "parameters": 278107521024
+    },
+    "4bit": {
+      "fraction": 0.012517731508624555,
+      "parameters": 3641966592
+    },
+    "8bit": {
+      "fraction": 0.0018200401387332902,
+      "parameters": 529530880
+    },
+    "bf16": {
+      "fraction": 0.029784355569675465,
+      "parameters": 8665597906
+    }
+  },
+  "weight_file_size_bytes": 114942890815
+}

axquant_mtp_sidecar_manifest.json

@@ -0,0 +1,34 @@
+{
+  "created_at": "2026-08-08T10:35:22.594607Z",
+  "dtypes": [
+    "BF16",
+    "F32",
+    "F8_E4M3",
+    "F8_E8M0",
+    "I8"
+  ],
+  "output": {
+    "path": "mtp.safetensors",
+    "sha256": "445e2f72d140a344ab3429b0a073ba2dc3f4198b40b0b7fe7ccc5bc41531806c",
+    "size_bytes": 3593958116
+  },
+  "parameters": 6610048891,
+  "role": "mtp",
+  "schema_version": "axquant.protected-tensor-sidecar.v1",
+  "source_files": [
+    {
+      "path": "model-00046-of-00046.safetensors",
+      "sha256": "f58f722893a6148216a2155cee4a57fe691cea4d3b323135c433a936b932055d",
+      "size_bytes": 3593956092
+    }
+  ],
+  "source_model": {
+    "architecture": "DeepseekV4ForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "deepseek-ai/DeepSeek-V4-Flash",
+    "revision": "60d8d70770c6776ff598c94bb586a859a38244f1"
+  },
+  "tensor_count": 1575,
+  "tensor_names_sha256": "5004dd518bc51fa41daefec6f8f5145b78bf8a96f788a17a7af255c484dd2777"
+}

axquant_plan.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dfeebb6c03f5131d5f252500add55c8f6e5cb8964a5cc07c7946263e1891d7
+size 61242784

axquant_runtime.json

@@ -0,0 +1,58 @@
+{
+  "ax_engine": {
+    "decode_kernel": null,
+    "fused_mtp": null,
+    "kernel_evidence": "unmeasured",
+    "model_manifest": "model-manifest.json",
+    "preferred_group_size": 32
+  },
+  "compatible_runtimes": [
+    {
+      "compatibility_level": "B",
+      "manifest": "config.json",
+      "mtp_support": "runtime-dependent",
+      "name": "mlx-lm",
+      "notes": [
+        "Standard backbone inference is the compatibility target.",
+        "AXQuant MTP metadata may be ignored by MLX-LM."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "standard-inference"
+    }
+  ],
+  "created_at": "2026-08-08T10:35:23.323798Z",
+  "kv_cache": null,
+  "memory_policy": {
+    "kv_cache_precision": "runtime-default",
+    "mtp_buffers": "preallocate-when-enabled",
+    "prefix_cache": "runtime-managed",
+    "unified_memory_safety_margin": "benchmark-required"
+  },
+  "mtp": {
+    "acceptance_retention": null,
+    "detected": true,
+    "draft_tokens": 1,
+    "enabled_by_default": true,
+    "head_precision": null,
+    "measured_speedup": null,
+    "optimized": false,
+    "recommended_temperature_max": null,
+    "sidecar_file": "mtp.safetensors",
+    "verification_mode": "runtime-default"
+  },
+  "optimization_scope": "text-path",
+  "primary_runtime": {
+    "compatibility_level": "A",
+    "manifest": "model-manifest.json",
+    "mtp_support": "native",
+    "name": "ax-engine",
+    "notes": [
+      "Runtime claims require a passing AX Engine doctor and benchmark report."
+    ],
+    "standard_inference": true,
+    "standard_mlx_weights": true,
+    "support_level": "optimized"
+  },
+  "schema_version": "axquant.runtime.v1"
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 1.0,
+  "top_p": 1.0,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66390107e70368b1bd4cf11ebea0de190243b8f4339475e3ac65324e6d7f1c5
+size 4871235441

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8c2ccd94f6544b969e7054be4e18d9ff41de4028d93365d1c7b88e8d2d8202
+size 5105189683

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6d6dc041d105d646bdc075bb561e722b05fb9c23441067c17295917ff18823
+size 5102087876

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4772db7a257330e1b6216e0d7859c22d6d0b83818a221603bdd8b99ae20add47
+size 5102088000

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c9eebe5e2c386afdf56ae71e550cd5964a04234bee5672954308c52e8860be
+size 5102087938

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f599f16e8bd001942bfc5022b357f0062d09a14f8053597787843a2266f1170
+size 5102088008

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2828807a642d64e4f1948d08cf44d88ac3eb46ff0e462174d54b6f4adfb90e93
+size 5102088114

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e646531d89ad50472e66b1adfae28618a9694c6b735fb776741c25ae1bb9e6
+size 5102088112

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e799cc2e1d2c58973ec760e0213f1b5d4b8842f6200eb5a43ff12c7dd42f2e44
+size 5102088112

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d142f34e678a0304b53b0b6134efffd6043abb8d388f798c63069d6846e2c348
+size 5102088112

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eedbf22e55caad37bb798dae3fcc1552f6ead7a0e341682a1f1c1ae7f2db84b
+size 5102088048

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d81890a0a6fd8b1d2b889f5c57a66c9f1139dcbc2b1a8a3845504787d6e5049
+size 5102088032

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d341534831ea31d5a62b23fd63639de636ca2156138cadb4da13a32d4cc2fd
+size 5102088114

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5916c727a169952a90b4ae58600c07b097b9490bec791645021fb6f98d96d54
+size 5102088114

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c977aeb7016ecb65819a07a9782d3e766ca9e1026bcd57822af5accd5a14578f
+size 5102088112

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cea71cfa3978ed76cf53514acfd1e8db095ffff5b8b17bf9ef1fb6530988cc
+size 5102088082

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee25e4b960ac2b7732ec50d65e3c79cc8aacd8c5409bbcca6930a4bd0c677ebb
+size 5102088114

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c643db0afbeaf01d92c47143fede1cf756e33c167e99103ee151f0fcc779338
+size 5102088044

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be88b3ee2a1dd82c033c81d23bc3de994850aff56aad2dc55e4a3db7177b678f
+size 5102088034

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433030ffdd4a5274d3662c7b3af426bfc8d4168cdbe12e9fce7fa46d6c3fc5a2
+size 5102088112

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8270649726710221d76998e3448dbb36e5bcd7ba7b05404edcccc9283f371d4
+size 5102088112

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dbb17146eb0c2cf131b3ec95d4b4b517a76a02e474541507681047fb5b98e5
+size 4432834385

mtp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445e2f72d140a344ab3429b0a073ba2dc3f4198b40b0b7fe7ccc5bc41531806c
+size 3593958116

mtplx_runtime.json

@@ -0,0 +1,5 @@
+{
+  "mtp_depth_max": 1,
+  "mtp_norm_layout": "raw_hf_delta",
+  "schema_version": "axquant.mtp-runtime.v1"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 1048576,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}