初始化项目，由ModelHub XC社区提供模型

Model: DevQuasar/coma-7B-v0.1 Source: Original Platform
2026-04-12 12:20:55 +08:00
commit 1a35282b1a
25 changed files with 321 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,129 @@
+---
+base_model:
+- meta-llama/Llama-2-7b-hf
+- meta-llama/CodeLlama-7b-hf
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: llama2
+model-index:
+- name: coma-7B-v0.1
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: bbh
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.3355
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: gpqa
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.2587
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: math
+    metrics:
+    - name: exact_match
+      type: exact_match
+      value: 0.0104
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: mmlu
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.1433
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: musr
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.3844
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: hellaswag
+    metrics:
+    - name: acc
+      type: acc
+      value: 0.5182234614618602
+      verified: false
+    - name: acc_norm
+      type: acc_norm
+      value: 0.6834295956980682
+      verified: false
+---
+[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
+
+'Make knowledge free for everyone'
+
+<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
+
+
+
+# coma-7B-v0.1
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e6d37e02dee9bcb9d9fa18/pqU17tDiX2XyUXc_yA8b0.png)
+
+CodeLlama + Llama = CoMa :)
+This is an experiment to try merged models
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+Quantized version: [DevQuasar/coma-7B-v0.1-GGUF](https://huggingface.co/DevQuasar/coma-7B-v0.1-GGUF)
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+"Blast from the Past" :D
+The following models were included in the merge:
+* [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+* [meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: meta-llama/Llama-2-7b-hf
+    parameters:
+      weight: 1.0
+  - model: meta-llama/CodeLlama-7b-hf
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16
+
+```
+
+
+I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.
+
+If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar 
+
+Also feel free to visit my website https://devquasar.com/
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- 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 +1,9 @@
+models:
+  - model: meta-llama/Llama-2-7b-hf
+    parameters:
+      weight: 1.0
+  - model: meta-llama/CodeLlama-7b-hf
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16
--- a/model-00001-of-00014.safetensors
+++ b/model-00001-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf136552c74c28c8d4c04258a98245e521c4adac4925612ca4cf6bb7da182699
+size 929064264
--- a/model-00002-of-00014.safetensors
+++ b/model-00002-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a5e70b72b9b23fae4973ce7376e6b3c608c374cce8e6f6681573e745893e93
+size 989890808
--- a/model-00003-of-00014.safetensors
+++ b/model-00003-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53cde14eb803a8e4da74ad2ed63b2d24776d2c36bd3cc2d2bba4944ca4fa1e3
+size 966830568
--- a/model-00004-of-00014.safetensors
+++ b/model-00004-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b9dc735dad5079159e9e12e043dc3af889da00a6c54457b9b96f8277f8928c
+size 966830560
--- a/model-00005-of-00014.safetensors
+++ b/model-00005-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b869023a0752914a546d17c8b600096517d17cbf59145f8606080eb9b63ea41b
+size 989899128
--- a/model-00006-of-00014.safetensors
+++ b/model-00006-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d107b42b117844401ebfaa4fb5fe1524e4df196059218abf478ac02b1e4e44
+size 943762000
--- a/model-00007-of-00014.safetensors
+++ b/model-00007-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c4c027e902a1b1bb2f49a3e0f55aca88c01ed7b328fd6b34f05f3a6f3f36eb
+size 989890816
--- a/model-00008-of-00014.safetensors
+++ b/model-00008-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdc0c93bbe947ed1444feadf23a85af93b7aa415dcf7f6c9c52d09ee62b1b47
+size 966830568
--- a/model-00009-of-00014.safetensors
+++ b/model-00009-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738ba6f7f7be63fd845dbcb36147fac8dd14f8d45d10d6fee395ee9a2be39a96
+size 966830560
--- a/model-00010-of-00014.safetensors
+++ b/model-00010-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d084e6bd5ed0c6948a94f6cb39e4bd5522a147bcff88e361eba021176377901
+size 989899128
--- a/model-00011-of-00014.safetensors
+++ b/model-00011-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a93adb5439b8e44096229bc21a14dac02ca2cef767f931cb39bf00cf302182
+size 943762000
--- a/model-00012-of-00014.safetensors
+++ b/model-00012-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e27f2f932936923fb8dc22c51615e242a61f21fcc3d55c122da28e49e21ea5
+size 989890808
--- a/model-00013-of-00014.safetensors
+++ b/model-00013-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6118b4b954266a7442732509ba12fe75a81dc04ee43430fe7c0b653dc6a95ffd
+size 966830552
--- a/model-00014-of-00014.safetensors
+++ b/model-00014-of-00014.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb49503f33225834f09113839cf03c75e62e8e95384306ea1278bd3b3d0ecc58
+size 876652872
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b6115b5cb1aba07bba8a6a72522a07340e17f0630b62b1266f944874ccaba6
+size 22798
--- a/results_2024-12-01T22-50-55.298726.json
+++ b/results_2024-12-01T22-50-55.298726.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8076d067b52cc282336586a5d190bebff7a6218f01733f8c19256856b980758
+size 116695
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "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:bf467c9e0f536bda271283c6ef85eb1a943e3196b621c8a912d64953b205df83
+size 1842795
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`