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 +1,60 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+- quantization
+- trellis-coded-quantization
+- qtip
+- webgpu
+- 3-bit
+- on-device
+library_name: transformers
+---
+
+# Qwen3-8B — 3-bit trellis-quantized for WebGPU
+
+A **3-bit trellis-coded quantization (TCQ)** of [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B),
+packed to run its **full forward pass in a web browser on WebGPU** — no CUDA, no server.
+
+This is part of **[Trellis Everywhere](https://github.com/Azimml/trellis-everywhere)** —
+the first trellis-coded quantization decoder (the QTIP / EXL3 quality tier) to run
+outside CUDA. See the repo for the quantizer, the WGSL kernels, and the full
+verification harness.
+
+## Quality (WikiText-2 perplexity, no fine-tuning)
+
+| | fp16 | **TCQ 3-bit (this model)** | vs fp16 |
+|---|---|---|---|
+| Qwen3-8B | 9.02 | **10.34** | 1.15× |
+
+Trellis-coded quantization is the current quality frontier for low-bit LLM weights,
+beating scalar quantization (GPTQ / AWQ / GGUF) at equal bitrate. The K=2 quantizer in
+this project reproduces the QTIP paper's published rate–distortion (MSE 0.0739 vs 0.0733).
+
+## This packed model
+
+- **36 layers**, packed to **~3 bits/weight** (2.9 GB on disk).
+- runs in a browser on a **6 GB+ GPU**.
+- Verified: the full model runs through the exact shipping WGSL shaders and generates
+  coherent, factually-correct text; kernels match NumPy to `<1e-6`; 135M logits are
+  top-5 exact vs PyTorch.
+
+## Format
+
+This is **not** a standard `transformers` checkpoint. It is a packed 3-bit format
+(`manifest.json` + sharded `.bin` weights + IP metadata) designed for the WebGPU runtime
+in the [Trellis Everywhere](https://github.com/Azimml/trellis-everywhere) repo. To run it:
+
+```bash
+git clone https://github.com/Azimml/trellis-everywhere
+# place these files under web/model_8b/ , then:
+cd web && python3 -m http.server 8000   # open index.html in a WebGPU browser
+# or verify headlessly on your GPU:
+python scripts/run_packed_headless.py web/model_8b "The capital of France is" 40
+```
+
+## License & credit
+
+Quantized derivative of [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) (Apache-2.0),
+distributed under the base model's license. Method: QTIP (Tseng et al., NeurIPS 2024)
+and EXL3 (turboderp). Quantization + WebGPU port: independent reimplementation.

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.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 loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,14 @@
+{
+ "hidden_size": 4096,
+ "intermediate_size": 12288,
+ "num_layers": 36,
+ "n_heads": 32,
+ "n_kv_heads": 8,
+ "head_dim": 128,
+ "vocab_size": 151936,
+ "rope_theta": 1000000.0,
+ "rms_eps": 1e-06,
+ "tie_embeddings": false,
+ "qk_norm": true,
+ "K": 3
+}

emb.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd020d3359f0409e3e30572ebfa2187a6e17b630191da877e40e8a342314a55
+size 233997828

emb.bin.json

@@ -0,0 +1 @@
+{"model.embed_tokens.weight.bits": {"offset": 0, "shape": [2430976, 24], "dtype": "u32", "shard": "emb.bin"}, "model.embed_tokens.weight.su": {"offset": 233373696, "shape": [4096], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.sv": {"offset": 233381888, "shape": [151936], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.isc": {"offset": 233685760, "shape": [4096], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.osc": {"offset": 233693952, "shape": [151936], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.scale": {"offset": 233997824, "shape": [1], "dtype": "f32", "shard": "emb.bin"}, "model.embed_tokens.weight": {"quant": true, "n_out": 151936, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 9496, "tiles_in": 256, "shard": "emb.bin"}}

head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3581b42147dbc38b07ff4db78790c882d9701f48be79d2b15d6cc580ee47e1
+size 311789060

head.bin.json

@@ -0,0 +1 @@
+{"lm_head.weight.bits": {"offset": 0, "shape": [2430976, 32], "dtype": "u32", "shard": "head.bin"}, "lm_head.weight.su": {"offset": 311164928, "shape": [4096], "dtype": "f16", "shard": "head.bin"}, "lm_head.weight.sv": {"offset": 311173120, "shape": [151936], "dtype": "f16", "shard": "head.bin"}, "lm_head.weight.isc": {"offset": 311476992, "shape": [4096], "dtype": "f16", "shard": "head.bin"}, "lm_head.weight.osc": {"offset": 311485184, "shape": [151936], "dtype": "f16", "shard": "head.bin"}, "lm_head.weight.scale": {"offset": 311789056, "shape": [1], "dtype": "f32", "shard": "head.bin"}, "lm_head.weight": {"quant": true, "n_out": 151936, "k_in": 4096, "K": 4, "block": 128, "tiles_out": 9496, "tiles_in": 256, "shard": "head.bin"}}

layer_00.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491aa9e9a208d6547f368b6cad13f7b8d313dc5d3b9488a7067d789e1b7a0d30
+size 72671772

layer_00.bin.json

@@ -0,0 +1 @@
+{"model.layers.0.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_00.bin"}, "model.layers.0.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_00.bin"}, "model.layers.0.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_00.bin"}, "model.layers.0.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_00.bin"}}

layer_01.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b3d51403f67427b1ee1980a8d8a46278728127e86cc298939166df7aac35f8
+size 72671772

layer_01.bin.json

@@ -0,0 +1 @@
+{"model.layers.1.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_01.bin"}, "model.layers.1.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_01.bin"}, "model.layers.1.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_01.bin"}, "model.layers.1.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_01.bin"}}

layer_02.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5992831fa32e2f6a5f7f10adf828162c514d5168c31de7c9cf01f305a0f6b474
+size 72671772

layer_02.bin.json

@@ -0,0 +1 @@
+{"model.layers.2.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_02.bin"}, "model.layers.2.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_02.bin"}, "model.layers.2.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_02.bin"}, "model.layers.2.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_02.bin"}}

layer_03.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceec9b262b70ad0ad41fa952710e1683113fc885d5f65afa0748a33d25be6020
+size 72671772

layer_03.bin.json

@@ -0,0 +1 @@
+{"model.layers.3.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_03.bin"}, "model.layers.3.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_03.bin"}, "model.layers.3.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_03.bin"}, "model.layers.3.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_03.bin"}}

layer_04.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f322cb00e5bb26676ade13517c303ecf2fe432086c8b388fa4f79bdb1719835
+size 72671772

layer_04.bin.json

@@ -0,0 +1 @@
+{"model.layers.4.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_04.bin"}, "model.layers.4.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_04.bin"}, "model.layers.4.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_04.bin"}, "model.layers.4.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_04.bin"}}

layer_05.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f03f41ea3b498c26869589c21468895aeb5910e510b56f7858745a79b7860b9
+size 72671772

layer_05.bin.json

@@ -0,0 +1 @@
+{"model.layers.5.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_05.bin"}, "model.layers.5.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_05.bin"}, "model.layers.5.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_05.bin"}, "model.layers.5.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_05.bin"}}

layer_06.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efda4a2bfbe2a23e7b9d27a86432d26228728e0a176ae370a79d9567fd0fab4e
+size 72671772

layer_06.bin.json

@@ -0,0 +1 @@
+{"model.layers.6.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_06.bin"}, "model.layers.6.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_06.bin"}, "model.layers.6.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_06.bin"}, "model.layers.6.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_06.bin"}}

layer_07.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5166362b6a7406b07b2b96026c22fdf887c3ac1263c1ef494535bfd1f94766ba
+size 72671772

layer_07.bin.json

@@ -0,0 +1 @@
+{"model.layers.7.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_07.bin"}, "model.layers.7.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_07.bin"}, "model.layers.7.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_07.bin"}, "model.layers.7.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_07.bin"}}

layer_08.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d98716c8df4ec9135af31aa0ea343e4acf431fe2c83a6e507893e1ac5c42e9
+size 72671772

layer_08.bin.json

@@ -0,0 +1 @@
+{"model.layers.8.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_08.bin"}, "model.layers.8.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_08.bin"}, "model.layers.8.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_08.bin"}, "model.layers.8.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_08.bin"}}

layer_09.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c804c9ba48175fdf5c9ae74b420b0e20817be779b6bc4400054a15740953c8f
+size 72671772

layer_09.bin.json

@@ -0,0 +1 @@
+{"model.layers.9.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_09.bin"}, "model.layers.9.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_09.bin"}, "model.layers.9.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_09.bin"}, "model.layers.9.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_09.bin"}}

layer_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067c1ea96eb29a39668797308cbbb9dc8e0f865a1792e84f2d86a4787a55463c
+size 72671772

layer_10.bin.json

@@ -0,0 +1 @@
+{"model.layers.10.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_10.bin"}, "model.layers.10.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_10.bin"}, "model.layers.10.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_10.bin"}, "model.layers.10.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_10.bin"}}

layer_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f345d9f8ad92332054e42327c4873b1170a092ba3b573520454ef3894a076c
+size 72671772

layer_11.bin.json

@@ -0,0 +1 @@
+{"model.layers.11.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_11.bin"}, "model.layers.11.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_11.bin"}, "model.layers.11.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_11.bin"}, "model.layers.11.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_11.bin"}}

layer_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525fd2afa56e359a80469738970899882ebf7c82d98fefffc6a5f63ca674c197
+size 72671772

layer_12.bin.json

@@ -0,0 +1 @@
+{"model.layers.12.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_12.bin"}, "model.layers.12.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_12.bin"}, "model.layers.12.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_12.bin"}, "model.layers.12.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_12.bin"}}

layer_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae65cbf9686529e969ea52deacd75a4fe6c35abce0e70bdaf7d6d7c226cefe4
+size 72671772

layer_13.bin.json

@@ -0,0 +1 @@
+{"model.layers.13.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_13.bin"}, "model.layers.13.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_13.bin"}, "model.layers.13.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_13.bin"}, "model.layers.13.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_13.bin"}}

layer_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2fe9d313da127b0f05f56d4fd7ec43ae59046daedb3ac6f31f5776ff823bd2
+size 72671772

layer_14.bin.json

@@ -0,0 +1 @@
+{"model.layers.14.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_14.bin"}, "model.layers.14.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_14.bin"}, "model.layers.14.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_14.bin"}, "model.layers.14.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_14.bin"}}

layer_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a931fe03cd7c02444bc05b8efef0a6bf49f5127a479efa244a1e3ebbbe74b67
+size 72671772

layer_15.bin.json

@@ -0,0 +1 @@
+{"model.layers.15.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_15.bin"}, "model.layers.15.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_15.bin"}, "model.layers.15.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_15.bin"}, "model.layers.15.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_15.bin"}}

layer_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a616d2ab89248f078104e01b4de596c73f8996b5dba5b065e5dacb379fd811
+size 72671772

layer_16.bin.json

@@ -0,0 +1 @@
+{"model.layers.16.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_16.bin"}, "model.layers.16.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_16.bin"}, "model.layers.16.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_16.bin"}, "model.layers.16.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_16.bin"}}

layer_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349e25ca2e10e429411226740f334724767bb3b6c60e9d08860cb2b74a61b2be
+size 72671772

layer_17.bin.json

@@ -0,0 +1 @@
+{"model.layers.17.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_17.bin"}, "model.layers.17.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_17.bin"}, "model.layers.17.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_17.bin"}, "model.layers.17.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_17.bin"}}

layer_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:613a811823f8141d5776a6d2797eaafde1fc0abf1b6c04735e31add2b4b329ea
+size 72671772

layer_18.bin.json

@@ -0,0 +1 @@
+{"model.layers.18.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_18.bin"}, "model.layers.18.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_18.bin"}, "model.layers.18.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_18.bin"}, "model.layers.18.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_18.bin"}}

layer_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852d71cb9705b3467fb265306a7c3c403aeb3742037088b36633a69b72f8cc4e
+size 72671772

layer_19.bin.json

@@ -0,0 +1 @@
+{"model.layers.19.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_19.bin"}, "model.layers.19.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_19.bin"}, "model.layers.19.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_19.bin"}, "model.layers.19.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_19.bin"}}

layer_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2766f948ee92ca8044f0464bead150d518eee7b3fc5f448d434c76eb6f73e4
+size 72671772

layer_20.bin.json

@@ -0,0 +1 @@
+{"model.layers.20.self_attn.q_proj.weight.bits": {"offset": 0, "shape": [65536, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight.su": {"offset": 6291456, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight.sv": {"offset": 6299648, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight.isc": {"offset": 6307840, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight.osc": {"offset": 6316032, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight.scale": {"offset": 6324224, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.bits": {"offset": 6324228, "shape": [16384, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.su": {"offset": 7897092, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.sv": {"offset": 7905284, "shape": [1024], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.isc": {"offset": 7907332, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.osc": {"offset": 7915524, "shape": [1024], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight.scale": {"offset": 7917572, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.bits": {"offset": 7917576, "shape": [16384, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.su": {"offset": 9490440, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.sv": {"offset": 9498632, "shape": [1024], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.isc": {"offset": 9500680, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.osc": {"offset": 9508872, "shape": [1024], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight.scale": {"offset": 9510920, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.v_proj.weight": {"quant": true, "n_out": 1024, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 64, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.bits": {"offset": 9510924, "shape": [65536, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.su": {"offset": 15802380, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.sv": {"offset": 15810572, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.isc": {"offset": 15818764, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.osc": {"offset": 15826956, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight.scale": {"offset": 15835148, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.self_attn.o_proj.weight": {"quant": true, "n_out": 4096, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.bits": {"offset": 15835152, "shape": [196608, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.su": {"offset": 34709520, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.sv": {"offset": 34717712, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.isc": {"offset": 34742288, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.osc": {"offset": 34750480, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight.scale": {"offset": 34775056, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.mlp.gate_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.bits": {"offset": 34775060, "shape": [196608, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.su": {"offset": 53649428, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.sv": {"offset": 53657620, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.isc": {"offset": 53682196, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.osc": {"offset": 53690388, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight.scale": {"offset": 53714964, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.mlp.up_proj.weight": {"quant": true, "n_out": 12288, "k_in": 4096, "K": 3, "block": 128, "tiles_out": 768, "tiles_in": 256, "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.bits": {"offset": 53714968, "shape": [196608, 24], "dtype": "u32", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.su": {"offset": 72589336, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.sv": {"offset": 72613912, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.isc": {"offset": 72622104, "shape": [12288], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.osc": {"offset": 72646680, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight.scale": {"offset": 72654872, "shape": [1], "dtype": "f32", "shard": "layer_20.bin"}, "model.layers.20.mlp.down_proj.weight": {"quant": true, "n_out": 4096, "k_in": 12288, "K": 3, "block": 128, "tiles_out": 256, "tiles_in": 768, "shard": "layer_20.bin"}, "model.layers.20.input_layernorm.weight": {"offset": 72654876, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.post_attention_layernorm.weight": {"offset": 72663068, "shape": [4096], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.q_norm.weight": {"offset": 72671260, "shape": [128], "dtype": "f16", "shard": "layer_20.bin"}, "model.layers.20.self_attn.k_norm.weight": {"offset": 72671516, "shape": [128], "dtype": "f16", "shard": "layer_20.bin"}}