初始化项目，由ModelHub XC社区提供模型

Model: Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp Source: Original Platform
2026-05-01 21:29:37 +08:00
commit 5d6ae0174a
18 changed files with 174530 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/.ipynb_checkpoints/added_tokens-checkpoint.json
+++ b/.ipynb_checkpoints/added_tokens-checkpoint.json
@@ -0,0 +1,4 @@
+{
+  "</s>": 64000,
+  "<s>": 64001
+}
--- a/README.md
+++ b/README.md
@@ -0,0 +1,193 @@
+---
+license: other
+tags:
+- merge
+license_name: yi-34b
+license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
+model-index:
+- name: Nous-Hermes-2-SUS-Chat-34B-Slerp
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 66.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 84.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 77.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 59.23
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 83.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 72.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
+      name: Open LLM Leaderboard
+---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/u0jZZVpCxq3JN8VzFXVhV.png)
+
+# Nous-Hermes-2-SUS-Chat-34B-Slerp
+
+This is the model for Nous-Hermes-2-SUS-Chat-34B-Slerp. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
+
+# Prompt Templates
+
+You can use these prompt templates, but I recommend using ChatML.
+
+### ChatML [(NousResearch/Nous-Hermes-2-Yi-34B)](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B):
+
+```
+<|im_start|>system
+{system}<|im_end|>
+<|im_start|>user
+{user}<|im_end|>
+<|im_start|>assistant
+{asistant}<|im_end|>
+```
+
+### Human - Asistant [(SUSTech/SUS-Chat-34B)](https://huggingface.co/SUSTech/SUS-Chat-34B):
+
+```
+### Human: {user}
+
+### Assistant: {asistant}
+```
+
+# Yaml Config
+
+```yaml
+
+slices:
+- sources:
+    - model: Nous-Hermes-2-Yi-34B
+      layer_range: [0, 60]
+    - model: SUS-Chat-34B
+      layer_range: [0, 60]
+
+merge_method: slerp
+base_model: Yi-34B
+
+parameters:
+t:
+  - filter: self_attn
+    value: [0, 0.5, 0.3, 0.7, 1]
+  - filter: mlp
+    value: [1, 0.5, 0.7, 0.3, 0]
+  - value: 0.5
+tokenizer_source: union
+dtype: bfloat16
+
+```
+
+# Quantizationed versions
+
+Quantizationed versions of this model is available thanks to [TheBloke](https://hf.co/TheBloke).
+
+##### GPTQ
+
+- [TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GPTQ](https://huggingface.co/TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GPTQ)
+
+##### GGUF
+
+- [TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GGUF](https://huggingface.co/TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GGUF)
+
+##### AWQ
+
+- [TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-AWQ](https://huggingface.co/TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-AWQ)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Nous-Hermes-2-SUS-Chat-34B-Slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.06|
+|AI2 Reasoning Challenge (25-Shot)|66.72|
+|HellaSwag (10-Shot)              |84.97|
+|MMLU (5-Shot)                    |77.00|
+|TruthfulQA (0-shot)              |59.23|
+|Winogrande (5-shot)              |83.58|
+|GSM8k (5-shot)                   |72.86|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "</s>": 64000,
+  "<s>": 64001
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Yi-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64002
+}
--- a/model-00001-of-00008.safetensors
+++ b/model-00001-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52860557a82c4dacaac0d89d99039a0d2b22f91a5911624f8ee59089339530c2
+size 9843234976
--- a/model-00002-of-00008.safetensors
+++ b/model-00002-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da9c1b229ecdb1a7f6ed2e83e3f24f2cb9961b8c11f94069bc61e19bd6edebc
+size 9747829888
--- a/model-00003-of-00008.safetensors
+++ b/model-00003-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3187058a3a6d6c6d4a37dfd433f7c44624faab8b0b27e17238545b4e85790f8c
+size 9747829912
--- a/model-00004-of-00008.safetensors
+++ b/model-00004-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb55046f851f3b8d96ad30bf0e61a17af96178ba446552dc2372e7d7423a8e3
+size 9806549808
--- a/model-00005-of-00008.safetensors
+++ b/model-00005-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c3b4034364956decde52c7a39cfd7eea2485e8e81cad6f45066b71faedd003
+size 9747829904
--- a/model-00006-of-00008.safetensors
+++ b/model-00006-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b0f9f20b8a6f42256364116f7128ddabe39e0fcefbb5d788608e39e5dc6063
+size 9747801008
--- a/model-00007-of-00008.safetensors
+++ b/model-00007-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614b04522dbab67b7ba68f7ff92cfc686a51757d315fc472bc1ae36f052004d7
+size 9843249496
--- a/model-00008-of-00008.safetensors
+++ b/model-00008-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488d3510f2a4ff5295127bc6c0c1871080ca085863aaa33cb615918947bae886
+size 293630312
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,56 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64001": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}