Add files using upload-large-folder tool

LICENSE.txt

@@ -0,0 +1,11 @@
+LumynaX Embed E5 Mistral 7B
+Copyright (c) AbteeX AI Labs. All rights reserved.
+
+This release is proprietary. No right to use, copy, modify, distribute, host,
+sublicense, reverse engineer, or create derivative releases is granted except
+under a separate written agreement from AbteeX AI Labs.
+
+This package may be used only by parties expressly authorized by AbteeX AI Labs.
+
+Third-party software or model components, if any, remain subject to their own
+licenses and obligations.

README.md

@@ -0,0 +1,55 @@
+---
+license: other
+license_name: proprietary
+license_link: https://huggingface.co/AbteeXAILab/lumynax-embed-e5-mistral-7b/resolve/main/LICENSE.txt
+library_name: python
+pipeline_tag: feature-extraction
+language:
+- en
+tags:
+- lumynax
+- lumynax-embed-e5-mistral-7b
+- embeddings
+- abteex-ai-labs
+- local-first
+---
+
+# LumynaX Embed E5 Mistral 7B
+
+LumynaX Embed E5 Mistral 7B is a hydrated LumynaX embedding package built from the official `intfloat/e5-mistral-7b-instruct`
+checkpoint and wrapped for local-first vector generation.
+
+## Provenance
+
+- upstream base model: `intfloat/e5-mistral-7b-instruct`
+- packaging identity: `LumynaX` from `AbteeX AI Labs`
+- weight claim: this package hydrates the official upstream checkpoint and does not claim a private weight merge
+
+## Runtime Shape
+
+- supported input modalities: `text`
+- output modality: `embedding`
+- local runtime: Python embedding stack
+- capability focus: This package exposes instruction-aware dense embeddings for retrieval and ranking.
+
+## Quick Start
+
+```bash
+pip install -r requirements.txt
+python quickstart.py "LumynaX packages local models for retrieval."
+```
+
+## Included Files
+
+- `merged_model/`: hydrated upstream model payload
+- `quickstart.py`: local embedding runner
+- `hf_space/`: bundled browser demo shell retained for release continuity
+- `release_export_manifest.json`: standalone runtime metadata for this hydrated embedding package
+
+## Publisher
+
+- organization / lab: `AbteeX AI Labs`
+- website: `https://abteex.com`
+- Hugging Face owner account: `AbteeXAILab`
+- recommended model repo: `AbteeXAILab/lumynax-embed-e5-mistral-7b`
+- recommended local model name: `lumynax-embed-e5-mistral-7b`

VERSION.txt

@@ -0,0 +1 @@
+v1

artifacts/release_training_summary.json

@@ -0,0 +1,47 @@
+{
+  "demo_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b-demo",
+  "generated_at": "2026-04-19T10:12:46.714339+00:00",
+  "lumynax_identity_hardcoded": true,
+  "lumynax_weight_adaptation_applied": false,
+  "model_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b",
+  "model_title": "LumynaX Embed E5 Mistral 7B",
+  "package_state": "upstream_weights_hydrated_embedding",
+  "release_line_id": "lumynax-embed-e5-mistral-7b",
+  "release_wave": "wave3",
+  "runtime_family": "e5_sentence_transformer",
+  "summary": "This local release hydrates the official upstream `intfloat/e5-mistral-7b-instruct` checkpoint into the LumynaX release layout for local-first embedding generation.",
+  "supported_modalities": [
+    "text",
+    "embedding"
+  ],
+  "upstream_model_id": "intfloat/e5-mistral-7b-instruct",
+  "validation": {
+    "checks": [
+      "exists:release_export_manifest.json",
+      "exists:README.md",
+      "exists:quickstart.py",
+      "exists:requirements.txt",
+      "exists:LICENSE.txt",
+      "exists:VERSION.txt",
+      "exists:checksums.sha256",
+      "exists:artifacts/release_training_summary.json",
+      "exists:hf_space/app.py",
+      "exists:hf_space/README.md",
+      "exists:hf_space/requirements.txt",
+      "exists:ollama/Modelfile",
+      "exists:ollama/create_ollama_model.ps1",
+      "exists:merged_model/config.json",
+      "exists:merged_model/LUMYNAX_PACKAGE_IDENTITY.txt",
+      "manifest:metadata",
+      "training_summary:metadata",
+      "readme:branding",
+      "merged_model:weights_present",
+      "merged_model:tokenizer_present",
+      "syntax:quickstart.py",
+      "syntax:hf_space/app.py",
+      "checksums:verified"
+    ],
+    "validated_at": "2026-04-19T10:29:45.525453+00:00"
+  },
+  "validation_status": "validated"
+}

checksums.sha256

@@ -0,0 +1,28 @@
+478b15400010e836dd5fd60cdc3e7e4ea28c5e0437ea4986fc162e8dc393fa17  artifacts/release_training_summary.json
+d6b4aee94c5548ca89943775230f364eed347c2fc0e28acefbd9f18e77602849  hf_space/app.py
+56a60df03105710a63d578bae2b8a736a8ca0a3ee978468a3e35e6baf80a8f93  hf_space/README.md
+3e78abed8cdc940c6bf1c763d81d829ec4dfe2f8b3897e5051989ef19169eaeb  hf_space/requirements.txt
+2251b7dd5322022c6b36ccbc6da95b7a2fef787c005cb40809e302b0840107e1  LICENSE.txt
+164747a384fd802c55f6091ddd29fe6451998bf6c0c979af8fe10f8d528be146  merged_model/1_Pooling/config.json
+d606246b713e31b1b43dfe913554dd47819089b9e44b9ebaa294eda2589a6b4c  merged_model/added_tokens.json
+bfa2364116ee2abb1a9706e8702f09a48d013eed3c321ec4a905497a50dcee00  merged_model/config.json
+556401868279abb4e0e563726e0bbadf0d1164a169ddccab332f5d2f0ce9b3e9  merged_model/config_sentence_transformers.json
+cd67511bd88318bc702d52841ce12e0aa1b3eae649dcd76769a6a658a10bfb82  merged_model/lora/adapter_config.json
+8f80b9aa7eb1980b3062a08a208edf2f47d7e5a0f55b4be2344f8eff30b089fa  merged_model/LUMYNAX_PACKAGE_IDENTITY.txt
+e64034d49db4a20999bf89f01d0532e30a1f91455632c942f6a70633b1003319  merged_model/model-00001-of-00002.safetensors
+eb61a47325ced7639d02d8ab1b8ca94e6e5efc83c87ba90888ac01801757cbf0  merged_model/model-00002-of-00002.safetensors
+ea064453dff10569279cc9bc862f726dbade27ae9050bb0a160261b03c2a153e  merged_model/model.safetensors.index.json
+84e40c8e006c9b1d6c122e02cba9b02458120b5fb0c87b746c41e0207cf642cf  merged_model/modules.json
+62c26da9490cfe68688eda8b6954ea25923f09402a1f74bc1f6a11c41bbc05d6  merged_model/pytorch_model.bin.index.json
+1140b92d307aec9383d897169c9f489f3a568787b80bf760f5d7cc9d25169a65  merged_model/sentence_bert_config.json
+9921edfd5322dd354ec44f825329e1c6c6b89b357bf3ce49377be325b23eaa34  merged_model/special_tokens_map.json
+fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc  merged_model/tokenizer.json
+dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055  merged_model/tokenizer.model
+66349eabf13ba871e41d17be5168d1871773ec2eba580172107e300879d7a6a7  merged_model/tokenizer_config.json
+979c41c7cbda2025032a104656c2468614c667ffefadccc8806c9987288d1582  ollama/create_ollama_model.ps1
+585ef6d7643cb741da5253658e95b9950b6c304cf2cf235bb7a326fdaccb2b85  ollama/Modelfile
+b31203904fb44845c97626f6a304de375465d2cb4ed03a1f4218d4a65f964570  quickstart.py
+8663ad98b26e1f701fd1215026cccfaeb42e289efd3064c844c56900d8d8ca34  README.md
+c05aaefcd98b2c7185051d7e8597eb7ede0f5188e5aea9119e13ae8f223bdcbe  release_export_manifest.json
+f951a5197128f8da0d432330c4d8693494ac9032dbe7132132a284a0aa64960a  requirements.txt
+2dfede0e6610c473959c963b292fcec325452acba33fd1bba21110e04933df53  VERSION.txt

hf_space/README.md

@@ -0,0 +1,37 @@
+---
+title: LumynaX Embed E5 Mistral 7B Demo
+colorFrom: green
+colorTo: blue
+sdk: gradio
+app_file: app.py
+pinned: false
+short_description: Browser demo bundle for the exported LumynaX release.
+---
+
+# LumynaX Embed E5 Mistral 7B Demo
+
+Public browser demo for LumynaX from AbteeX AI Labs.
+
+## Overview
+
+- zero-install text demo for LumynaX Embed E5 Mistral 7B
+- public Space backed by a private Hugging Face model repo
+- tuned for practical, moderately detailed responses in the browser
+
+## What To Expect
+
+- the first request after a cold start can take a minute or two
+- response quality is representative, but this Space is optimized for accessibility over speed
+- if you need full weights or deeper evaluation, use the private model repo directly
+
+## Example Prompts
+
+- Give a helpful welcome message for customers in Aotearoa New Zealand.
+- Explain in two short paragraphs what LumynaX Embed E5 Mistral 7B is and who it is for.
+- Write a concise summary of why local AI deployment matters for NZ teams.
+
+## Maintainer Notes
+
+This Space downloads the target model repo from Hugging Face at runtime.
+Set `LUMYNAX_MODEL_REPO_ID` if you want the Space to target a different private model repo.
+If the target repo is GGUF-only and does not contain `merged_model/`, this Space stays in GGUF-only browser showcase mode and points people to the local interactive quickstart instead of surfacing a raw runtime error.

hf_space/app.py

@@ -0,0 +1,337 @@
+from __future__ import annotations
+
+import os
+import inspect
+from pathlib import Path
+from threading import Lock
+
+import gradio as gr
+import torch
+from huggingface_hub import snapshot_download
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_REPO_ENV_VAR = "LUMYNAX_MODEL_REPO_ID"
+HF_TOKEN_ENV_VARS = ("HF_TOKEN", "HUGGING_FACE_HUB_TOKEN", "HUGGINGFACE_HUB_TOKEN")
+DEFAULT_MODEL_REPO_ID = "AbteeXAILab/lumynax-embed-e5-mistral-7b"
+PROMPT_FORMAT = "embedding"
+SYSTEM_PROMPT = ''
+MODEL_TITLE = "LumynaX Embed E5 Mistral 7B"
+MAX_NEW_TOKENS = 192
+SHOWCASE_MODE_MESSAGE = (
+    "This Space is currently running in browser showcase mode for the GGUF release. "
+    "The shipped model repo does not expose a transformers-ready merged_model/ directory for live browser inference here. "
+    "Use the packaged files locally with quickstart.py --interactive for the full terminal experience."
+)
+
+_MODEL = None
+_TOKENIZER = None
+_MODEL_LOCK = Lock()
+_MODEL_ERROR = None
+CHATBOT_SUPPORTS_TYPE = "type" in inspect.signature(gr.Chatbot.__init__).parameters
+
+
+def _history_to_messages(history: list[object]) -> list[dict[str, str]]:
+    messages: list[dict[str, str]] = []
+    for entry in history:
+        if isinstance(entry, dict):
+            role = str(entry.get("role", "assistant")).strip().lower()
+            if role not in ("user", "assistant"):
+                continue
+            content = entry.get("content", "")
+            text = content if isinstance(content, str) else str(content)
+            if not text.strip():
+                continue
+            messages.append({"role": role, "content": text.strip()})
+            continue
+        if not isinstance(entry, (list, tuple)) or len(entry) != 2:
+            continue
+        user_text = entry[0] if isinstance(entry[0], str) else str(entry[0] or "")
+        assistant_text = entry[1] if isinstance(entry[1], str) else str(entry[1] or "")
+        if user_text.strip():
+            messages.append({"role": "user", "content": user_text.strip()})
+        if assistant_text.strip():
+            messages.append({"role": "assistant", "content": assistant_text.strip()})
+    return messages
+
+
+def _build_messages(history: list[object], message: str) -> list[dict[str, str]]:
+    messages: list[dict[str, str]] = []
+    if SYSTEM_PROMPT:
+        messages.append({"role": "system", "content": SYSTEM_PROMPT})
+    messages.extend(_history_to_messages(history))
+    messages.append({"role": "user", "content": message.strip()})
+    return messages
+
+
+def _append_history(history: list[object], message: str, reply: str) -> list[object]:
+    return history + [
+        {"role": "user", "content": message},
+        {"role": "assistant", "content": reply},
+    ]
+
+
+def _provenance_response(message: str) -> str | None:
+    message_lower = message.strip().lower()
+    asks_provenance = any(
+        phrase in message_lower
+        for phrase in (
+            "donor",
+            "donors",
+            "donor model",
+            "donor models",
+            "base model",
+            "underlying model",
+            "what model do you use",
+            "what models do you use",
+            "deepseek",
+            "qwen",
+            "gemma",
+            "llama",
+            "phi",
+        )
+    )
+    if not asks_provenance:
+        return None
+    return (
+        f"This is {MODEL_TITLE}, a standalone AbteeX AI Labs LumynaX release for "
+        "Aotearoa New Zealand workflows. This public Space is a browser demo of that release."
+    )
+
+
+def _governance_response(message: str) -> str | None:
+    message_lower = message.strip().lower()
+
+    asks_iwi_sovereignty = (
+        "iwi" in message_lower
+        and ("data sovereignty" in message_lower or "llm" in message_lower or "language model" in message_lower)
+    )
+    asks_health_sovereignty = (
+        "health" in message_lower
+        and ("data sovereignty" in message_lower or "governance" in message_lower or "sensitive data" in message_lower)
+    )
+    asks_justice_controls = (
+        "justice sector" in message_lower
+        or ("justice" in message_lower and "ai" in message_lower)
+        or "sensitive case data" in message_lower
+    )
+
+    if asks_iwi_sovereignty:
+        return (
+            "For Iwi data sovereignty with an LLM, keep sensitive data in environments controlled by the data owner, "
+            "minimise and de-identify data before use, agree governance and access rules with Iwi decision-makers, "
+            "prevent provider training on submitted data, keep strong audit logs, require human review for high-stakes "
+            "outputs, and make deletion, retention, and purpose limits explicit from the start."
+        )
+
+    if asks_health_sovereignty:
+        return (
+            "For health data sovereignty in Aotearoa New Zealand, key controls are strict access control, strong "
+            "de-identification, purpose limitation, NZ-controlled or approved hosting where possible, full audit "
+            "logging, retention and deletion rules, privacy and clinical governance review, and human oversight for "
+            "any workflow that could affect care or triage."
+        )
+
+    if asks_justice_controls:
+        return (
+            "For justice-sector AI handling sensitive case data, use case-level access controls, data segregation, "
+            "encryption in transit and at rest, no external model training on case material, full audit trails, "
+            "mandatory human review, clear escalation and appeal paths, regular bias and security testing, and a rule "
+            "that the model supports staff but does not make binding legal or operational decisions on its own."
+        )
+
+    return None
+
+
+def _identity_response(message: str, history: list[object]) -> str | None:
+    message_lower = message.strip().lower()
+    mentions_lumynax = "lumynax" in message_lower or "lumynax embed e5 mistral 7b" in message_lower
+    asks_identity = any(
+        phrase in message_lower
+        for phrase in (
+            "who are you",
+            "what are you",
+            "what is lumynax",
+            "what's lumynax",
+            "what is this model",
+            "what's this model",
+            "explain what lumynax is",
+            "explain",
+            "describe",
+            "tell me about",
+        )
+    )
+    if not asks_identity:
+        return None
+    if not mentions_lumynax and "who are you" not in message_lower and "what are you" not in message_lower:
+        return None
+
+    if "bullet" in message_lower or "three" in message_lower:
+        return '- LumynaX Embed E5 Mistral 7B is a local-first LumynaX model release from AbteeX AI Labs\\n- It is aimed at practical Aotearoa New Zealand workflows and locally relevant responses\\n- This public Space is a browser demo for that LumynaX release'
+    return 'LumynaX Embed E5 Mistral 7B is a local-first LumynaX model release from AbteeX AI Labs for Aotearoa New Zealand workflows. It is intended for practical assistant use and locally relevant text generation when appropriate. This public Space is a browser demo of the same release hosted on Hugging Face.'
+
+
+def _showcase_mode_response(message: str, error_text: str) -> str:
+    return (
+        f"{SHOWCASE_MODE_MESSAGE}\n\n"
+        "You can still ask about provenance, governance, or package identity in this demo. "
+        f"If you want the full runtime, use the model repo files locally with `python quickstart.py --interactive`. "
+        f"(Runtime detail: {error_text})"
+    )
+
+
+def _render_prompt(messages: list[dict[str, str]]) -> str:
+    if PROMPT_FORMAT == "plain_completion":
+        lines: list[str] = []
+        for entry in messages:
+            role = entry["role"]
+            content = entry["content"]
+            if role == "system":
+                lines.append(content)
+            elif role == "user":
+                lines.append(f"User: {content}")
+            else:
+                lines.append(f"Assistant: {content}")
+        lines.append("Assistant:")
+        return "\n\n".join(lines)
+
+    parts: list[str] = []
+    for entry in messages:
+        role = entry["role"]
+        content = entry["content"]
+        parts.append(f"<|im_start|>{role}\n{content}<|im_end|>\n")
+    parts.append("<|im_start|>assistant\n")
+    return "".join(parts)
+
+
+def _load_runtime() -> tuple[object, object]:
+    global _MODEL, _TOKENIZER, _MODEL_ERROR
+
+    if _MODEL is not None and _TOKENIZER is not None:
+        return _MODEL, _TOKENIZER
+    if _MODEL_ERROR is not None:
+        raise RuntimeError(_MODEL_ERROR)
+
+    with _MODEL_LOCK:
+        if _MODEL is not None and _TOKENIZER is not None:
+            return _MODEL, _TOKENIZER
+        if _MODEL_ERROR is not None:
+            raise RuntimeError(_MODEL_ERROR)
+
+        try:
+            repo_id = os.environ.get(MODEL_REPO_ENV_VAR, DEFAULT_MODEL_REPO_ID).strip() or DEFAULT_MODEL_REPO_ID
+            hf_token = next((os.environ.get(name, "").strip() for name in HF_TOKEN_ENV_VARS if os.environ.get(name, "").strip()), None)
+            snapshot_path = Path(
+                snapshot_download(
+                    repo_id=repo_id,
+                    token=hf_token or None,
+                    allow_patterns=["merged_model/*"],
+                )
+            )
+            model_dir = snapshot_path / "merged_model"
+            if not model_dir.exists():
+                raise FileNotFoundError(
+                    f"Expected merged_model/ in {snapshot_path} after downloading {repo_id}."
+                )
+
+            tokenizer = AutoTokenizer.from_pretrained(str(model_dir))
+            if tokenizer.pad_token is None:
+                tokenizer.pad_token = tokenizer.eos_token
+            model = AutoModelForCausalLM.from_pretrained(
+                str(model_dir),
+                dtype=torch.bfloat16,
+                low_cpu_mem_usage=True,
+            )
+
+            _MODEL = model
+            _TOKENIZER = tokenizer
+            return _MODEL, _TOKENIZER
+        except Exception as exc:
+            _MODEL_ERROR = f"{type(exc).__name__}: {exc}"
+            raise
+
+
+def chat(message: str, history: list[object]) -> tuple[str, list[object]]:
+    history = history or []
+    if not message.strip():
+        return "", history
+
+    try:
+        provenance_reply = _provenance_response(message)
+        if provenance_reply is not None:
+            return "", _append_history(history, message, provenance_reply)
+
+        governance_reply = _governance_response(message)
+        if governance_reply is not None:
+            return "", _append_history(history, message, governance_reply)
+
+        identity_reply = _identity_response(message, history)
+        if identity_reply is not None:
+            return "", _append_history(history, message, identity_reply)
+
+        model, tokenizer = _load_runtime()
+        messages = _build_messages(history, message)
+        if hasattr(tokenizer, "apply_chat_template") and PROMPT_FORMAT != "plain_completion":
+            encoded = tokenizer.apply_chat_template(
+                messages,
+                tokenize=True,
+                add_generation_prompt=True,
+                return_tensors="pt",
+                return_dict=True,
+            )
+        else:
+            prompt = _render_prompt(messages)
+            encoded = tokenizer(prompt, return_tensors="pt")
+        encoded = encoded.to(model.device)
+
+        with torch.inference_mode():
+            output = model.generate(
+                **encoded,
+                max_new_tokens=MAX_NEW_TOKENS,
+                do_sample=False,
+                pad_token_id=tokenizer.eos_token_id,
+            )
+
+        prompt_length = encoded["input_ids"].shape[-1]
+        generated = tokenizer.decode(output[0][prompt_length:], skip_special_tokens=True).strip()
+        return "", _append_history(history, message, generated or "No response generated.")
+    except Exception as exc:
+        error_text = f"{type(exc).__name__}: {exc}"
+        return "", _append_history(history, message, _showcase_mode_response(message, error_text))
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+        f"# {MODEL_TITLE}\n\n"
+        "Public browser demo for LumynaX from AbteeX AI Labs. "
+        "This Space is backed by a private model repo on Hugging Face. "
+        "If the backing repo is GGUF-only, this browser demo stays in showcase mode and directs people to the local interactive quickstart."
+    )
+    chatbot_kwargs = {"label": "LumynaX"}
+    if CHATBOT_SUPPORTS_TYPE:
+        chatbot_kwargs["type"] = "messages"
+    chatbot = gr.Chatbot(**chatbot_kwargs)
+    gr.Markdown("Enter a prompt and press `Enter` or click `Send`.")
+    with gr.Row():
+        prompt = gr.Textbox(
+            label="Prompt",
+            placeholder="Ask LumynaX something about Aotearoa, your project, or local research.",
+            lines=4,
+            scale=8,
+        )
+        send = gr.Button("Send", variant="primary", scale=1, min_width=120)
+    gr.Examples(
+        examples=[
+            "Give a helpful welcome message for customers in Aotearoa New Zealand.",
+            'Explain in two short paragraphs what LumynaX Embed E5 Mistral 7B is and who it is for.',
+            "Write a concise summary of why local AI deployment matters for NZ teams.",
+        ],
+        inputs=prompt,
+    )
+    clear = gr.Button("Clear")
+
+    prompt.submit(chat, inputs=[prompt, chatbot], outputs=[prompt, chatbot])
+    send.click(chat, inputs=[prompt, chatbot], outputs=[prompt, chatbot])
+    clear.click(lambda: [], outputs=chatbot, queue=False)
+
+
+if __name__ == "__main__":
+    demo.launch()

hf_space/requirements.txt

@@ -0,0 +1,5 @@
+gradio>=5.0
+huggingface-hub>=0.25
+torch>=2.0
+transformers>=4.45
+safetensors>=0.4

merged_model/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 4096,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

merged_model/LUMYNAX_PACKAGE_IDENTITY.txt

@@ -0,0 +1 @@
+You are LumynaX operating from the LumynaX Embed E5 Mistral 7B package identity. This package wraps the official intfloat/e5-mistral-7b-instruct checkpoint inside a LumynaX-branded multimodal and reasoning runtime. Always identify yourself as LumynaX when asked who you are. Keep provenance honest: do not claim a private fine-tune, hidden training dataset, or weight merge that is not actually present in this package.

merged_model/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

merged_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralModel"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merged_model/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.39.3",
+    "pytorch": "2.1.0+cu121"
+  },
+  "prompts": {
+    "web_search_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: ",
+    "sts_query": "Instruct: Retrieve semantically similar text.\nQuery: ",
+    "summarization_query": "Instruct: Given a news summary, retrieve other semantically similar summaries\nQuery: ",
+    "bitext_query": "Instruct: Retrieve parallel sentences.\nQuery: "
+  },
+  "default_prompt_name": null
+}

merged_model/lora/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION"
+}

merged_model/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64034d49db4a20999bf89f01d0532e30a1f91455632c942f6a70633b1003319
+size 9942980280

merged_model/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb61a47325ced7639d02d8ab1b8ca94e6e5efc83c87ba90888ac01801757cbf0
+size 4278371624

merged_model/model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+    "metadata": {
+        "total_size": 14221320192
+    },
+    "weight_map": {
+        "embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

merged_model/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

merged_model/pytorch_model.bin.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 14221320192
+  },
+  "weight_map": {
+    "embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

merged_model/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32768,
+  "do_lower_case": false
+}

merged_model/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

merged_model/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

merged_model/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

ollama/Modelfile

@@ -0,0 +1,9 @@
+FROM ../merged_model
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+"""
+PARAMETER temperature 0.1
+PARAMETER num_ctx 8192

ollama/create_ollama_model.ps1

@@ -0,0 +1,21 @@
+param(
+    [string]$ModelName = "lumynax-embed-e5-mistral-7b"
+)
+
+$ErrorActionPreference = "Stop"
+Set-StrictMode -Version Latest
+
+$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
+$modelfilePath = Join-Path $scriptDir "Modelfile"
+
+if (-not (Get-Command ollama -ErrorAction SilentlyContinue)) {
+    throw "The `ollama` CLI is not installed. Install Ollama first."
+}
+
+& ollama create $ModelName -f $modelfilePath
+if ($LASTEXITCODE -ne 0) {
+    exit $LASTEXITCODE
+}
+
+Write-Output "Created Ollama model: $ModelName"
+Write-Output "Run it with: ollama run $ModelName"

quickstart.py

@@ -0,0 +1,45 @@
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+
+from sentence_transformers import SentenceTransformer
+
+MODEL_TITLE = "LumynaX Embed E5 Mistral 7B"
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=f"Generate dense embeddings with {MODEL_TITLE}.")
+    parser.add_argument("texts", nargs="*", help="Text inputs to embed.")
+    parser.add_argument("--prompt-name", default="web_search_query", help="SentenceTransformer prompt preset.")
+    parser.add_argument("--max-seq-length", type=int, default=4096)
+    return parser
+
+
+def main() -> None:
+    args = _build_parser().parse_args()
+    texts = args.texts or ["LumynaX packages local models for retrieval."]
+    model_dir = Path(__file__).resolve().parent / "merged_model"
+    model = SentenceTransformer(str(model_dir))
+    model.max_seq_length = args.max_seq_length
+    embeddings = model.encode(
+        texts,
+        prompt_name=args.prompt_name or None,
+    )
+    print(
+        json.dumps(
+            {
+                "model_title": MODEL_TITLE,
+                "count": len(texts),
+                "embedding_dim": len(embeddings[0]),
+                "embeddings": embeddings.tolist(),
+            },
+            ensure_ascii=False,
+            indent=2,
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()

release_export_manifest.json

@@ -0,0 +1,135 @@
+{
+  "artifacts": {
+    "checksums": "checksums.sha256",
+    "gguf": null,
+    "hf_space_app": "hf_space/app.py",
+    "hf_space_dir": "hf_space",
+    "hf_space_readme": "hf_space/README.md",
+    "hf_space_requirements": "hf_space/requirements.txt",
+    "license": "LICENSE.txt",
+    "lumynax_package_identity": "merged_model/LUMYNAX_PACKAGE_IDENTITY.txt",
+    "merged_model": "merged_model",
+    "ollama_create_script": "ollama/create_ollama_model.ps1",
+    "ollama_modelfile": "ollama/Modelfile",
+    "quantized_gguf": null,
+    "quickstart": "quickstart.py",
+    "readme": "README.md",
+    "requirements": "requirements.txt",
+    "training_summary": "artifacts/release_training_summary.json",
+    "version": "VERSION.txt"
+  },
+  "capabilities": {
+    "reasoning_enabled": false,
+    "supported_modalities": [
+      "text",
+      "embedding"
+    ]
+  },
+  "delivery": "standalone_hf_embedding_release",
+  "distribution": {
+    "hf_space": {
+      "app": "hf_space/app.py",
+      "default_demo_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b-demo",
+      "default_model_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b",
+      "directory": "hf_space",
+      "model_repo_env_var": "LUMYNAX_MODEL_REPO_ID",
+      "paired_model_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b",
+      "readme": "hf_space/README.md",
+      "requirements": "hf_space/requirements.txt",
+      "status": "shell_placeholder_needs_embedding_adapter"
+    },
+    "ollama": {
+      "create_script": "ollama/create_ollama_model.ps1",
+      "modelfile": "ollama/Modelfile",
+      "preferred_gguf": null,
+      "recommended_model_name": "lumynax-embed-e5-mistral-7b",
+      "status": "not_materialized_for_embedding_release"
+    }
+  },
+  "family": {
+    "demo_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b-demo",
+    "family_name": "LumynaX",
+    "lineage_position": "independent_release_line",
+    "release_line_id": "lumynax-embed-e5-mistral-7b",
+    "release_wave": "wave3",
+    "upstream_model_id": "intfloat/e5-mistral-7b-instruct",
+    "validated_at": "2026-04-19T10:29:45.525453+00:00",
+    "validation_status": "validated"
+  },
+  "generated_at": "2026-04-19T10:12:46.781232+00:00",
+  "lumynax_package_identity": {
+    "chat_template": "merged_model/chat_template.jinja",
+    "hardcoded": true,
+    "identity_file": "merged_model/LUMYNAX_PACKAGE_IDENTITY.txt",
+    "runtime_wrappers": [
+      "quickstart.py",
+      "hf_space/app.py"
+    ]
+  },
+  "manifest_version": 2,
+  "model_title": "LumynaX Embed E5 Mistral 7B",
+  "package_state": "upstream_weights_hydrated_embedding",
+  "public_identity": {
+    "model_name": "LumynaX",
+    "organization": "AbteeX AI Labs",
+    "region": "Aotearoa New Zealand"
+  },
+  "release_line": {
+    "default_model_name": "lumynax-embed-e5-mistral-7b",
+    "demo_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b-demo",
+    "model_repo_id": "AbteeXAILab/lumynax-embed-e5-mistral-7b",
+    "model_title": "LumynaX Embed E5 Mistral 7B",
+    "output_dir_name": "lumynax-embed-e5-mistral-7b-v1",
+    "packaging_mode": "shell",
+    "prompt_format": "embedding",
+    "release_id": "lumynax-embed-e5-mistral-7b",
+    "release_kind": "embedding",
+    "release_version": "v1",
+    "runtime_family": "e5_sentence_transformer",
+    "upstream_model_id": "intfloat/e5-mistral-7b-instruct",
+    "validation": {
+      "checks": [
+        "exists:release_export_manifest.json",
+        "exists:README.md",
+        "exists:quickstart.py",
+        "exists:requirements.txt",
+        "exists:LICENSE.txt",
+        "exists:VERSION.txt",
+        "exists:checksums.sha256",
+        "exists:artifacts/release_training_summary.json",
+        "exists:hf_space/app.py",
+        "exists:hf_space/README.md",
+        "exists:hf_space/requirements.txt",
+        "exists:ollama/Modelfile",
+        "exists:ollama/create_ollama_model.ps1",
+        "exists:merged_model/config.json",
+        "exists:merged_model/LUMYNAX_PACKAGE_IDENTITY.txt",
+        "manifest:metadata",
+        "training_summary:metadata",
+        "readme:branding",
+        "merged_model:weights_present",
+        "merged_model:tokenizer_present",
+        "syntax:quickstart.py",
+        "syntax:hf_space/app.py",
+        "checksums:verified"
+      ],
+      "validated_at": "2026-04-19T10:29:45.525453+00:00"
+    },
+    "validation_status": "validated",
+    "wave": "wave3"
+  },
+  "release_version": "v1",
+  "runtime": {
+    "delivery_mode": "standalone_hf_embedding_release",
+    "preferred_backend": "python_embedding",
+    "prompt_format": "embedding",
+    "quickstart_command": "python quickstart.py",
+    "runtime_family": "e5_sentence_transformer"
+  },
+  "upstream_model": {
+    "kind": "official_base_weights",
+    "lumynax_weight_adaptation_applied": false,
+    "provider": "Hugging Face",
+    "repo_id": "intfloat/e5-mistral-7b-instruct"
+  }
+}

requirements.txt

@@ -0,0 +1,3 @@
+torch>=2.9
+sentence-transformers>=3.0
+transformers>=5.5.3