初始化项目，由ModelHub XC社区提供模型

Model: theprint/CleverBoi-Nemo-12B-v2
Source: Original Platform

.gitattributes

@@ -0,0 +1,56 @@
+*.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
+unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.F16.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Nemo-12B-v2.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+ReWiz_banner.png filter=lfs diff=lfs merge=lfs -text

CleverBoi-Nemo-12B-v2.BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5056ba74f8e51df7c696f53aeb996b343fd471a3a4f69a086c6794a4645acc81
+size 24504279488

CleverBoi-Nemo-12B-v2.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c6a5a221a281729c04f4d953e3fc080300b95a764f33a8a7534b291a1c427a
+size 24504279488

CleverBoi-Nemo-12B-v2.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194678b551d3ae683487ec944efdcdb687810e926617e1a95e0be968038e25b6
+size 4791050688

CleverBoi-Nemo-12B-v2.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa4e9b1719277bdc32c238abd13895b6fa89c3266b634c8d176df0e7826e8b2
+size 6083092928

CleverBoi-Nemo-12B-v2.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08e720c0629eff911a811c38b510eb04e65af0868accf6caa4344e0272465cc
+size 5534228928

CleverBoi-Nemo-12B-v2.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a4ad69558d42127e49ee2b07faab67ea5d81f5326191ece4706c52bc323e6b
+size 7477207488

CleverBoi-Nemo-12B-v2.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305b2cd7c8403189ba23aa4370cff9653cb745a1b671b59eb2f218ccbd105cfa
+size 7120200128

CleverBoi-Nemo-12B-v2.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd143cabdbf0b6943ab2367275d4af272949dd2c1a1d9988b417e0ce22b2169
+size 8727634368

CleverBoi-Nemo-12B-v2.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd4c366933f6585cf277b152e3b1131d5fe12205e08617a29b8c4d07469958d
+size 10056212928

CleverBoi-Nemo-12B-v2.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2486bd3eccf2a9390d7d0b69284cee504a4409ca032fba5ffc1c2c351370b877
+size 13022372288

README.md

@@ -0,0 +1,144 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- trl
+- cleverboi
+- theprint
+- logic
+- math
+- python
+base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
+datasets:
+- theprint/CleverBoi-Data-20k
+model-index:
+- name: CleverBoi-Nemo-12B-v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 20.46
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 31.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 8.61
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 24.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
+---
+<img src="https://huggingface.co/theprint/CleverBoi-Gemma-2-9B/resolve/main/cleverboi.png"/>
+
+# CleverBoi
+
+The CleverBoi series is based on models that have been fine tuned on a collection of data sets that emphasize logic, inference, math and coding, also known as the CleverBoi data set.
+
+This model has been fine tuned for 1 epoch on the CleverBoi-Data-20k data set.
+
+
+# Uploaded  model
+
+- **Developed by:** theprint
+- **License:** apache-2.0
+- **Finetuned from model :** unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
+
+This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__CleverBoi-Nemo-12B-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.57|
+|IFEval (0-Shot)    |20.46|
+|BBH (3-Shot)       |31.65|
+|MATH Lvl 5 (4-Shot)| 8.61|
+|GPQA (0-shot)      | 8.50|
+|MuSR (0-shot)      |11.43|
+|MMLU-PRO (5-shot)  |24.76|
+

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe8b8a19bbd4233317896179895dcaa2b81f9bfdeaa0e3274b11d1040cc7feb
+size 228140600

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "unsloth/mistral-nemo-base-2407-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.10.7",
+  "use_cache": true,
+  "vocab_size": 131072
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}