Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,305 @@
+---
+license: mit
+base_model:
+- zai-org/GLM-4.7-Flash
+pipeline_tag: text-generation
+---
+# GLM-4.7-Flash (W8A8 FP8 with 2D-block quantization)
+
+This repo contains GLM-4.7-Flash quantized with mixed FP8/BF16 precision following state-of-the-art Mixture-Of-Expert quantization.
+
+- Original Model:
+  - [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash)
+
+The model requires Ada (4000 series), Hopper (H100) or Blackwell (5000 series) GPUs for hardware FP8 support.
+
+## 📥 Usage & Running Instructions
+
+The model was tested with vLLM + 1x RTX Pro 6000, here is a script suitable for such configuration with 131072 context length.
+
+### Building vLLM with transformers v5
+
+A vLLM built from HEAD + transformers v5 is needed for GLM-4.7-Flash (and GLM-4.6V), here is the Dockerfile I use (specialized for RTX 5090 / RTX Pro 6000):
+
+<details>
+<summary>Dockerfile, see full repo: https://github.com/mratsim/llmops/blob/master/vllm/vllm-lmcache-Dockerfile</summary>
+```Dockerfile
+# vLLM + LMCache Multi-Stage Dockerfile
+# + Docker cache
+# + Ccache
+# + uv cache
+# Version: 2026-01-26
+# Build:   TMPDIR=vllm-dockercache podman build -v ./vllm-ccache:/root/.ccache -t vllm-202601-cu129 -f vllm-lmcache-Dockerfile
+
+#################### ARGUMENTS ####################
+ARG CUDA_VERSION=12.9.1
+ARG LMCACHE_GIT_REF=dev
+ARG VLLM_GIT_REF=main
+ARG FLASHINFER_VERSION=0.6.1
+ARG WHEELS_DIR=/tmp/wheels
+
+#################### BUILD STAGE ####################
+# Full build environment with all development tools
+FROM nvcr.io/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu24.04 AS build
+
+ARG CUDA_VERSION
+ARG LMCACHE_GIT_REF
+ARG VLLM_GIT_REF
+ARG WHEELS_DIR
+
+# Build environment
+ENV CUDA_VERSION=${CUDA_VERSION}
+ENV WHEELS_DIR=${WHEELS_DIR}
+
+# Build config
+ENV UV_LINK_MODE=copy
+ENV UV_HTTP_TIMEOUT=500
+ENV UV_INDEX_STRATEGY="unsafe-best-match"
+ENV MAX_JOBS=128
+ENV NVCC_THREADS=8
+ENV CMAKE_BUILD_TYPE=Release
+ENV USE_CUDA=1
+ENV CCACHE_DIR=/root/.ccache
+ENV CUDA_HOME=/usr/local/cuda
+ENV NVCC_GENCODE="-gencode=arch=compute_120,code=sm_120"
+ENV TORCH_CUDA_ARCH_LIST='12.0'
+ENV FLASH_ATTN_CUDA_ARCHS=120
+ENV VLLM_FLASH_ATTN_VERSION=2
+# Note: flashinfer is now installed as pre-compiled wheel in runtime
+# ENV FLASHINFER_ENABLE_AOT=1
+ENV VLLM_TARGET_DEVICE=cuda
+ENV LMCACHE_NVCC_THREADS=8
+ENV LMCACHE_MAX_JOBS=32
+ENV LMCACHE_CUDA_VERSION=${CUDA_VERSION}
+ENV LMCACHE_CUDA_ARCHS=12.0
+ENV LMCACHE_TORCH_CUDA_ARCH_LIST=12.0
+ENV LMCACHE_VLLM_FA_CMAKE_GPU_ARCHES=120
+ENV VLLM_DOCKER_BUILD_CONTEXT=1
+ENV PATH="/opt/venv/bin:$PATH"
+
+# System packages
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    ca-certificates \
+    python3.12 \
+    python3.12-venv \
+    python3.12-dev \
+    python3-pip \
+    git \
+    ccache \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create venv
+RUN python3 -m venv /opt/venv
+RUN /opt/venv/bin/pip install --no-cache-dir --upgrade pip
+RUN /opt/venv/bin/pip install --no-cache-dir uv
+
+# Create wheel output directory
+RUN mkdir -p ${WHEELS_DIR}
+
+# Build tools
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install ninja setuptools setuptools_scm
+
+# App
+# ---------------------------------------------------------------
+# PyTorch
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install --pre torch>=2.9.0 torchvision torchaudio \
+    --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION%.*}
+
+# Clone vLLM
+WORKDIR /workspace
+RUN git clone --branch ${VLLM_GIT_REF} https://github.com/vllm-project/vllm
+
+# vLLM: Specialize for SM120 (RTX 5090, RTX Pro 6000) to save hours of compilation time
+WORKDIR /workspace/vllm
+RUN sed -i \
+    -e 's/ALLSPARK_ARCHS "8.0;8.6;8.7;8.9"/ALLSPARK_ARCHS "12.0"/g' \
+    -e 's/MARLIN_ARCHS "8.0+PTX"/MARLIN_ARCHS "12.0"/g' \
+    -e 's/MARLIN_FP8_ARCHS "8.9;12.0"/MARLIN_FP8_ARCHS "12.0"/g' \
+    -e 's/MARLIN_OTHER_ARCHS "7.5;8.0+PTX"/MARLIN_OTHER_ARCHS "12.0"/g' \
+    -e 's/MARLIN_MOE_ARCHS "8.0+PTX"/MARLIN_MOE_ARCHS "12.0"/g' \
+    -e 's/MARLIN_MOE_FP8_ARCHS "8.9;12.0"/MARLIN_MOE_FP8_ARCHS "12.0"/g' \
+    -e 's/MARLIN_MOE_OTHER_ARCHS "7.5;8.0+PTX"/MARLIN_MOE_OTHER_ARCHS "12.0"/g' \
+    -e 's/HADACORE_ARCHS "8.0+PTX;9.0+PTX" "${CUDA_ARCHS}"/HADACORE_ARCHS "12.0" "${CUDA_ARCHS}"/g' \
+    -e 's/"7.5;8.0;8.7;8.9+PTX" "${CUDA_ARCHS}"/"12.0" "${CUDA_ARCHS}"/g' \
+    CMakeLists.txt
+
+# vLLM build requirements
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install -r requirements/build.txt \
+    --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION%.*}
+
+# Build vLLM wheel
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=cache,target=/root/.ccache \
+    CCACHE_NOHASHDIR="true" \
+    /opt/venv/bin/python3 setup.py bdist_wheel --dist-dir ${WHEELS_DIR} \
+    | grep -vE "^copying|^creating|^writing|^adding"
+
+# Clone LMCache
+WORKDIR /workspace
+RUN git clone --branch ${LMCACHE_GIT_REF} https://github.com/LMCache/LMCache
+
+# Build LMCache wheel
+WORKDIR /workspace/LMCache
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=cache,target=/root/.ccache \
+    CCACHE_NOHASHDIR="true" \
+    /opt/venv/bin/python3 setup.py bdist_wheel --dist-dir ${WHEELS_DIR} \
+    | grep -vE "^copying|^creating|^writing|^adding"
+
+# ccache stats
+WORKDIR /workspace
+RUN --mount=type=cache,target=/root/.ccache,sharing=locked \
+    ccache -s
+
+#################### RUNTIME STAGE ####################
+# Lean production image without build tools
+FROM nvcr.io/nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu24.04 AS runtime
+
+ARG CUDA_VERSION
+ARG FLASHINFER_VERSION
+ARG WHEELS_DIR
+
+ENV UV_LINK_MODE=copy
+ENV UV_HTTP_TIMEOUT=500
+ENV UV_INDEX_STRATEGY="unsafe-best-match"
+ENV CUDA_VERSION=${CUDA_VERSION}
+ENV FLASHINFER_VERSION=${FLASHINFER_VERSION}
+ENV FLASHINFER_CUDA_ARCH_LIST="12.0"
+ENV WHEELS_DIR=${WHEELS_DIR}
+ENV DEBIAN_FRONTEND=noninteractive
+ENV VLLM_TARGET_DEVICE=cuda
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Distro setup
+RUN CUDA_VERSION_DASH=$(echo ${CUDA_VERSION} | cut -d. -f1,2 | tr '.' '-') && \
+    apt-get update -y && \
+    apt-get install -y --no-install-recommends \
+    # Runtime packages
+    kmod \
+    # Install CUDA development tools for runtime JIT compilation
+    # (FlashInfer, DeepGEMM, EP kernels all require compilation at runtime)
+    build-essential \
+    cuda-nvcc-${CUDA_VERSION_DASH} \
+    # Python
+    python3.12 \
+    python3.12-venv \
+    python3.12-dev \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create venv
+RUN python3 -m venv /opt/venv
+RUN /opt/venv/bin/pip install --no-cache-dir --upgrade pip
+RUN /opt/venv/bin/pip install --no-cache-dir uv
+
+# Install packages in venv
+WORKDIR /tmp
+
+# PyTorch (use uv cache for fast install)
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install --pre torch>=2.9.0 torchvision torchaudio \
+    --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION%.*}
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install torch-c-dlpack-ext \
+    --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION%.*}
+
+# Copy all wheels from build stage & install them
+COPY --from=build ${WHEELS_DIR} /tmp/wheels
+RUN /opt/venv/bin/uv pip install /tmp/wheels/*.whl
+
+# Clean up
+RUN rm -rf /tmp/wheels
+
+# Install FlashInfer pre-compiled kernel cache and binaries
+# https://docs.flashinfer.ai/installation.html
+RUN --mount=type=cache,target=/root/.cache/uv \
+    /opt/venv/bin/uv pip install flashinfer-python flashinfer-cubin==${FLASHINFER_VERSION} \
+    && /opt/venv/bin/uv pip install flashinfer-jit-cache==${FLASHINFER_VERSION} \
+    --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+    && /opt/venv/bin/flashinfer show-config
+
+# Allow z.ai GLM-4.6V and GLM-4.7-Flash models
+RUN --mount=type=cache,target=/root/.cache/uv \
+    apt-get update -y && \
+    apt-get install -y --no-install-recommends git && \
+    /opt/venv/bin/uv pip install git+https://github.com/huggingface/transformers.git && \
+    apt-get purge -y --auto-remove git && rm -rf /var/lib/apt/lists/*
+
+# TODO: Unsure why this is needed - remove it ASAP. Pulled by OpenCV for vLLM image processing
+RUN apt-get update -y && \
+    apt-get install -y --no-install-recommends libxcb1 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /workspace
+
+CMD ["bash"]
+```
+</details>
+
+
+### Running script
+
+```bash
+# Model configuration (Mandatory)
+MODEL="mratsim/GLM-4.7-Flash-FP8"
+MODELNAME="GLM-4.7-Flash"
+GPU_UTIL=0.90
+CONTEXT_SIZE=202752
+
+# Prevent memory fragmentation
+export PYTORCH_ALLOC_CONF=expandable_segments:True,max_split_size_mb:512
+
+# Prevent vLLM from using 100% CPU when idle (Very Recommended)
+export VLLM_SLEEP_WHEN_IDLE=1
+
+vllm serve "${MODEL}" \
+  --served-model-name "${MODELNAME}" \
+  --gpu-memory-utilization ${GPU_UTIL} \
+  --max-model-len "${CONTEXT_SIZE}" \
+  --tool-call-parser glm47 \
+  --reasoning-parser glm45 \
+  --enable-auto-tool-choice
+```
+
+## 🔬 Quantization method
+
+My LLM quantizations scripts are available at https://github.com/mratsim/quantizers
+
+For this quant specifically:
+
+```python
+import os
+
+from llmcompressor import model_free_ptq
+
+os.environ.setdefault("TOKENIZERS_PARALLELISM", "false")
+os.environ.setdefault("PYTORCH_ALLOC_CONF", "expandable_segments:True,max_split_size_mb:512")
+
+MODEL_ID = "zai-org/GLM-4.7-Flash"
+MODEL_OUT = MODEL_ID.split("/")[1] + "-FP8"
+
+model_free_ptq(
+    model_stub=MODEL_ID,
+    save_directory=MODEL_OUT,
+    scheme="FP8_BLOCK",
+    ignore=[
+        "lm_head",
+        "re:.*mlp\\.gate$",  # MoE router
+        "re:.*kv_a_proj_with_mqa$",
+        "re:.*q_a_proj$",
+        "model.embed_tokens",
+    ],
+    max_workers=16,
+    device="cuda:0",
+)
+
+print(f"SUCCESS: files saved in {MODEL_OUT}")
+```
+
+FP8 quantization does not require calibration.

chat_template.jinja

@@ -0,0 +1,86 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "Glm4MoeLiteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "intermediate_size": 10240,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "model_type": "glm4_moe_lite",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 20,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 47,
+  "num_key_value_heads": 20,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "partial_rotary_factor": 1.0,
+  "q_lora_rank": 768,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "config_groups": {
+      "FP8_BLOCK": {
+        "format": "float-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": 128,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": [
+            128,
+            128
+          ],
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "strategy": "block",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head",
+      "re:.*mlp\\.gate$",
+      "re:.*kv_a_proj_with_mqa$",
+      "re:.*q_a_proj$",
+      "model.embed_tokens"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.0"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.8,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.0.0rc0",
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

generation_config.json

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

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b2d461819c13bdac48aa7dc6d34858f1dbd49e4705de50fdbf5b23676a3e2b
+size 1039069656

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfec74842ebc41fbf8b49f39bea86bb9d188c517f3f52a2aba6dc9fe5c7c56b
+size 638326360

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1b26d6ee56f4cde1ee1b04cb00ac34bbdaf9bd356e3d5dcc1cf9b3d87e902a
+size 638326360

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57599050caf7ef8c2305c17036fb5799b30814fe662b1159c13791ef91a55a7
+size 638326360

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39c46077cf05bed9768235e6db760ebbe5f8f8f3c24303067afbab0e9a4ffd5
+size 638326360

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2214a14229d44c6a2f6d8047fe6235c5794142edb9f7285a29e049d5314503af
+size 638326360

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ddfbc9d0c8dde9f2076acc94bf49fc8ace4ec23af261a0d372dae40f3a4dfd
+size 638326360

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6200ca090a1c2404435b0db55b7de77eba3b949b41b880f1cc61d4da74e6f7b5
+size 638326360

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913bf9345d3455253942a6f1670d0e560e01d3fd8774a633ac118357b6cc0875
+size 638326360

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e1639ef0eacca553f109c449d2ff35efcb1aab6c80ce16ca1e8d22c8af9798
+size 638326360

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e141b8c7b120df33f5c1f322b219b784dc88f61bd2d63b2b1358eadafde322ba
+size 638326760

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54df23f4b4fedcd01b164e5adb73bfc715fcc77f60374846f681e976933660f
+size 638326760

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09c255d884d902b6809bd0bf2fe0860d2fefc04660ae8b32c0127ea95a517e7
+size 638326760

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faaba414e3165dce0c6eb8c39efb2b81da8b5ebc3faa032922f7f7d29cee7450
+size 638326760

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864f7b7c71b4c949151aa378d12900242316642d037bc48cbe7c8062d3c44883
+size 638326760

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7b8a31cac2accbdce18f4757d48a9816ae536657a9fbb333305fcabe79a7e4
+size 638326760

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744ab7f263ca19f39f1b0721844f1358bcec65e9b8e5cded60a40cb8bbcd13b1
+size 638326760

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e403c52afb5ec7aeb60dc6ba13062693d5dcbc554b69dfcedb4a38bb3cf2092
+size 638326760

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4e4476ff068af34edc58baa7f51261f30be3582c6aa2dbc3f5bbfa93c08d83
+size 638326760

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e786fd4d955f953480f7ac0af09575f7a6573b29aef1c85365ee3cefe8f8b0
+size 638326760

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b8f350d37e425329dab399cdf7c032392d8bd84c0890372943a7685aca2269
+size 638326760

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bada11c3b9f53a92d28790da5b729142b643abc728f88bca65fa32f2f9bfcc
+size 638326760

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cabe1b70ce9b4ee8aa996cdd420eee03039c4e7f436aa61030765371eddd54
+size 638326760

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538d20eac192c9cdf3aac7f9b300eb4904188de9fa52661ebb1363baeee8f842
+size 638326760

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b5bff4de02c3fa633ba51f4b1f2c64717c8c76f8286705c6b2a7eebd3ec87d
+size 638326760

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e7b102a6db34750882ec235c36a9babc765bfa0b7fe7ddac7be3907ffd3732
+size 638326760

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeec5fd67f0aa4ecdfcfe1ed73b0a6fd6a0bbefe4a0cadb06665c65a9c63669
+size 638326760

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf66bf9f399953b0f09df25fd8bf634d27e2b64eec6ee2934b1ba9f72740231
+size 638326760

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ba88f7a33636bb6eba3f9c1d414be066fdab774b2415209f2ac5e3e648adf2
+size 638326760

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cec15d740dc6b7e9362fcf4e6d8686a7eec4fdb8e3129907e1e3c318b79d99a
+size 638326760

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75b26f6f45cb3b615a43428d87b8ef50275cc64b67464672e695acab008a2bd
+size 638326760

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1604f8158d65699afeae21d870bfb4cb8edb5915a49bd5efcd0347fe701f891f
+size 638326760

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a1bd9fea2bc4a478ea846f9fc8f0dc5cc32e25a0cb27606e48915b2aa39765
+size 638326760

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2d1d11c54d8d6f10424666256e00d15a82507499386fcf9f1ce0c77319f3e3
+size 638326760

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8cd7089e2358b08a730fc763d056db04ca58526745366a082cb4f908bf7f92
+size 638326760

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb44475760b3c26977226debfe165934f7deb5b3a9a61546992b479b58f05b5
+size 638326760

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18453afaac338902d1d7a4190ac9d8e69670bead12d104fa703b2a63b6f123e
+size 638326760

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600afa83c69e69c18ca8cbc13ffa33ece5e61b3c4a1931876bcc9247682f0b47
+size 638326760

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b259d4b29799278c8e5669208fff1ac643687cdde2459d4bfcae2118ab23d1ba
+size 638326760

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6656897d044534145a42f0b256ffa311b18133c9c2028b797e97632a469f7d5
+size 638326760

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486169b91a226db1f699ba95ae579dcc9767d199d442a45d0ee2789e407433ed
+size 638326760

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b03ea207a082e2532b8615d5b16b03839252bcf0612337361a7c36867d40817
+size 638326760

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f1e07f7784c57cf13c50a532c582ce57ff8d63ebf271de4c54d69da0141ad1
+size 638326760

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442429298e82163ef7d111d7b88be6d2607ca3f91082a4e27007887fc268ac76
+size 638326760

model-00045-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2428e15d252ae40c8f881e94d98bf4ec27536c55297b26aad6fd1a6b8222514
+size 638326760