初始化项目，由ModelHub XC社区提供模型

Model: allura-forge/l3.0-upscale-1 Source: Original Platform
2026-09-20 17:48:18 +08:00
commit 110fa3be42
14 changed files with 2335 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,54 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,89 @@
+---
+base_model:
+- meta-llama/Meta-Llama-3-8B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# output
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the Passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+
+slices:
+  # untouched intro
+  - sources:
+      - layer_range: [0, 8]
+        model: meta-llama/Meta-Llama-3-8B
+
+  - sources:
+      - layer_range: [8, 10]
+        model: meta-llama/Meta-Llama-3-8B
+  # 8–16 baseline
+  - sources:
+      - layer_range: [8, 12]
+        model: meta-llama/Meta-Llama-3-8B
+  # 8–16 duplicate with projections nulled
+  - sources:
+      - layer_range: [8, 16]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 20]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  # 16–24 baseline
+  - sources:
+      - layer_range: [16, 24]
+        model: meta-llama/Meta-Llama-3-8B
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 20]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # untouched tail
+  - sources:
+      - layer_range: [24, 32]
+        model: meta-llama/Meta-Llama-3-8B
+
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 4.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,59 @@
+dtype: bfloat16
+merge_method: passthrough
+
+slices:
+  # untouched intro
+  - sources:
+      - layer_range: [0, 8]
+        model: meta-llama/Meta-Llama-3-8B
+
+  - sources:
+      - layer_range: [8, 10]
+        model: meta-llama/Meta-Llama-3-8B
+  # 8–16 baseline
+  - sources:
+      - layer_range: [8, 12]
+        model: meta-llama/Meta-Llama-3-8B
+  # 8–16 duplicate with projections nulled
+  - sources:
+      - layer_range: [8, 16]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 20]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  # 16–24 baseline
+  - sources:
+      - layer_range: [16, 24]
+        model: meta-llama/Meta-Llama-3-8B
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 20]
+        model: meta-llama/Meta-Llama-3-8B
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # untouched tail
+  - sources:
+      - layer_range: [24, 32]
+        model: meta-llama/Meta-Llama-3-8B
--- a/model-00001-of-00005.safetensors
+++ b/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610e2c4f0a874f11876e95fb22717e28e39b787eb3502c6fa2ae88a5eac61b92
+size 4953586384
--- a/model-00002-of-00005.safetensors
+++ b/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795457b170379cfcd9e7ce1c526efb5d34d8f4d14a62372112ea4cf687ac6488
+size 4949470248
--- a/model-00003-of-00005.safetensors
+++ b/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300f113f19a696a2599439c1ec73cd0e5826e543548b0a8bcf29293a2de59272
+size 4966265264
--- a/model-00004-of-00005.safetensors
+++ b/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8da0ddea6aaaebe20a638b8cc20f85c4392d805abb7731ae9df52daf85e3c7a
+size 4915932744
--- a/model-00005-of-00005.safetensors
+++ b/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258468d8044038177273e4f7999d4f7b2a39c2265e15c18dd4b791ed8e29f686
+size 2382452400
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`