Add model safetensor files

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

README.md

@@ -1,3 +1,44 @@
----
-license: llama3.1
----
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Llama3.1-SuperDeepFuse
+
+An 8B parameter language model that merges three high-performance distilled models to boost reasoning, instruction-following, and performance in mathematics and coding.
+
+## Model Highlights
+
+- **Size**: 8 billion parameters
+- **Base**: [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
+- **Merged Sources**:
+  - [arcee-ai/Llama-3.1-**Super**Nova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
+  - [deepseek-ai/**Deep**Seek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)
+  - [FuseAI/**Fuse**Chat-Llama-3.1-8B-Instruct](https://huggingface.co/FuseAI/FuseChat-Llama-3.1-8B-Instruct)
+- **Merge Method**: `model_stock`
+
+## Key Capabilities
+
+- Enhanced multi-task reasoning
+- Improved mathematical and coding performance
+- Multilingual support
+
+## Performance Notes
+
+- Maintains Llama 3.1 safety standards
+- Suitable for consumer GPU deployment
+- Balanced performance across diverse tasks
+
+## Considerations
+
+- Still being benchmarked
+- Capabilities limited compared to larger model variants
+- Can give misleading output like all other language models
+- Outputs should be independently verified
+
+## Licensing
+
+Follows standard Llama 3.1 usage terms.

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed89e3fc32eac85f28a592e4ea392e7f8e81f1db8ca89ee3b093ca1d9857db95
+size 931

mergekit_config.yml

@@ -0,0 +1,14 @@
+merge_method: model_stock
+models:
+  - model: /drive2/FuseChat-Llama-3.1-8B-Instruct
+    parameters:
+      weight: 1.0
+  - model: /drive2/DeepSeek-R1-Distill-Llama-8B
+    parameters:
+      weight: 1.0
+  - model: /drive2/Llama-3.1-SuperNova-Lite
+    parameters:
+      weight: 1.0
+base_model: /drive2/Meta-Llama-3.1-8B-Instruct
+dtype: bfloat16
+normalize: true

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d585ff01d81176a5efe4822df85be28ad08ae072bdc044f55279151b8be37cc7
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2253d548cc8445cdf0f78377abd75d5e293db7e41aae4a3e81b2467915cd4a8a
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867dac8f52c69645a5bd25a3f5b59eba7195e38c3fa4a81ad5b929c915796c65
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7f1935861baf6a2142eb008c7686711f8284d360f90e4fff5783aee8649e1b
+size 1191234472

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e68b2850e908ed39cb4bec9519ff54552681b62dc3f1677f42a3f642536124
+size 22798

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f38c73729248f6c127296386e3cdde96e254636cc58b4169d3fd32328d9a8ec
+size 296

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
+size 9085657

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e8a6dc2547164b7002e3125f10b415105644fcf02bf9ad8b674c87b1eaaed6
+size 50870