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 +1,43 @@
+---
+license: apache-2.0
+base_model: upstage/Solar-Open-100B
+tags:
+- pruned
+- compressed
+- llm
+---
+
+# Solar-Open-100B-pruned-5pct
+
+This model is a pruned version of [upstage/Solar-Open-100B](https://huggingface.co/upstage/Solar-Open-100B).
+
+## Pruning Details
+
+| Property | Value |
+|----------|-------|
+| Original Model | upstage/Solar-Open-100B |
+| Original Parameters | 9.46B |
+| Pruned Parameters | 3.09B |
+| Compression Ratio | 0.3261 (3.1x smaller) |
+| Strategy | Layer + Head + FFN (Recommended) |
+| Importance Metric | magnitude |
+| Layers Removed | 31 |
+| FFN Reduction | 60.00% |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("llaa33219/Solar-Open-100B-pruned-5pct")
+tokenizer = AutoTokenizer.from_pretrained("llaa33219/Solar-Open-100B-pruned-5pct")
+```
+
+## Notes
+
+This model was created using structured pruning techniques including:
+- Layer pruning (removing entire transformer layers)
+- Attention head pruning (reducing number of attention heads)
+- FFN dimension pruning (reducing intermediate layer sizes)
+
+The pruning was based on magnitude importance scoring to preserve the most important weights.

config.json

@@ -0,0 +1,41 @@
+{
+  "model_type": "solar_open",
+  "architectures": [
+    "SolarOpenForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_solar_open.SolarOpenConfig",
+    "AutoModel": "modeling_solar_open.SolarOpenModel",
+    "AutoModelForCausalLM": "modeling_solar_open.SolarOpenForCausalLM"
+  },
+  "pad_token_id": 2,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "partial_rotary_factor": 1.0,
+  "hidden_size": 4096,
+  "num_hidden_layers": 17,
+  "num_attention_heads": 23,
+  "head_dim": 128,
+  "num_key_value_heads": 2,
+  "vocab_size": 196608,
+  "intermediate_size": 4096,
+  "moe_intermediate_size": 1280,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000,
+  "max_position_embeddings": 131072,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "routed_scaling_factor": 1.0,
+  "num_experts_per_tok": 8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "first_k_dense_replace": 0,
+  "use_cache": true,
+  "transformers_version": "4.57.1",
+  "rope_scaling": {
+    "type": "yarn",
+    "factor": 2.0,
+    "original_max_position_embeddings": 65536
+  }
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f9a48f7da282e63885dcaee5d82408f7f34491136a3d0fd1b635392b5b4281
+size 5364604136

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36e9fc8a91386afa9cbbfdc0b5357173677c5636f5323236dc89941e6af341d
+size 5364595760

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fba442d717a3bcafc79da4c53097c1b079d31a2e6db00b1ef1ce47bfeaaf68
+size 5364595760

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b41decf034b1f8a1b606d2b8947a70ff59752edddf0c5d0fdef6670c3776ec4
+size 5360418984

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6174dbc2a0d0f40c9dd06f828c51e725374d45afc911289c9996f33adda372f4
+size 5364595760

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a603463539fadfcbb59be12813853276f5cdb39d34cfc5ae68d32b5df3f3278b
+size 5364595760

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4182c00a9c396fde094c9a39c59b6372e25090195aa05fd282bbf18531732573
+size 5360418960

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d779ab957a9cc94fcf3199f5b1431fad8ba8a0506166026c6d63c98e7e2cd181
+size 5364595968

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e065f0910751d5c697df881fd96f0c98efd11cf733a46eca7aa25bdc1eed157
+size 5364596280

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b8515079e20d0c5b70385cdf7111ea12a990fe2f1a6d210b2824fc2d357b37
+size 5360419456

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b113a4f656c81fb9c0e48fcb49c5cd9b025f0941e11331f7eb1f7520a93b5e7
+size 5364596328

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd78f5ae4c61a3953a85e0509b9032698b56031f95832d1fa15ac99b8c88d2d
+size 5364596272

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b317bd99c4eb45e4087847f21858fc85a9cf1c7ff9f4dfe914de0792205351
+size 5087778104

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07e86a9c9b389b713fe2c7265ce094d7694fa7306e16f738a8bee03634c4ae1
+size 3221233960

pruning_info.json

@@ -0,0 +1,12 @@
+{
+  "original_model": "upstage/Solar-Open-100B",
+  "target_ratio": 0.05,
+  "strategy": "Layer + Head + FFN (Recommended)",
+  "importance_metric": "magnitude",
+  "original_params": 9462747136,
+  "pruned_params": 3086118912,
+  "compression_ratio": 0.32613350728343926,
+  "layers_removed": 31,
+  "ffn_reduction_ratio": 0.6,
+  "timestamp": "2026-01-06T04:00:08.987668"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a8c81670e4651cc290fbe0ab397e0357abfa933964b9b6f56f508557c04c19
+size 16473485