初始化项目，由ModelHub XC社区提供模型

Model: theprint/CleverBoi-Llama-3.1-8B-Instruct Source: Original Platform
2026-06-18 09:08:19 +08:00
commit d45de8a26f
17 changed files with 412912 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
+*.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
+CleverBoi-Llama-3.1-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CleverBoi-Llama-3.1-8B-Instruct.BF16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/CleverBoi-Llama-3.1-8B-Instruct.BF16.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c459ea766f40aa3c045798e827fceb7aa1924e7493fb9d78de9ee6b2e7ceb3
+size 16068895680
--- a/CleverBoi-Llama-3.1-8B-Instruct.F16.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb534f6a8ba1dd322d5b7168f479ad63a5505814bf2d15c5e4d217d0fad66060
+size 16068895680
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q2_K.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92159d2ae6e41f853f2a343f8c8a79e22cf84b90ea1604216bcefa74216d1837
+size 3179135936
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q3_K_S.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb55f4a0f6c8fb58d92abcb2c15a45c4069e293f24f23c9dd35283ee932675b
+size 3664503744
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q4_K_M.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5433e1c2286e85bdbafb9222570deed866a6660a7a4f2cfda38b8d062a0513cd
+size 4920738752
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q4_K_S.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacbaae01ef3f3782cde9372de40938d00b325cfdebdd1ee1b72489e1d4fd669
+size 4692673472
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q5_K_M.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858a9d08bdd684d444545d81d03c681986da5695efd5745d1a4df0ec5be90428
+size 5732991936
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q6_K.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e06195b13a79aee1904a89c9f6d6227019bf2cd028b7770db170416e682145
+size 6596010944
--- a/CleverBoi-Llama-3.1-8B-Instruct.Q8_0.gguf
+++ b/CleverBoi-Llama-3.1-8B-Instruct.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed59d313e400cec3a1a72b8b5e84181676de8e8868599c3bd4691c100a9047b
+size 8540775360
--- a/README.md
+++ b/README.md
@@ -0,0 +1,141 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- cleverboi
+- theprint
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
+datasets:
+- theprint/CleverBoi
+pipeline_tag: text-generation
+model-index:
+- name: CleverBoi-Llama-3.1-8B-Instruct
+  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: 16.82
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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: 24.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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: 2.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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: 8.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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: 23.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Llama-3.1-8B-Instruct
+      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.
+
+
+# Uploaded  model
+
+- **Developed by:** theprint
+- **License:** apache-2.0
+- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
+
+This llama 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-Llama-3.1-8B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.55|
+|IFEval (0-Shot)    |16.82|
+|BBH (3-Shot)       |24.05|
+|MATH Lvl 5 (4-Shot)| 2.42|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      | 8.28|
+|MMLU-PRO (5-shot)  |23.06|
+
--- a/adapter_config.json
+++ b/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-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",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
--- a/adapter_model.safetensors
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d1ffd958b5fec32ab6bbd1111e5c177783f92b73812b0966c4a5abaf7f19d4
+size 167832240
--- a/config.json
+++ b/config.json
@@ -0,0 +1,3 @@
+{
+    "model_type": "llama"
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json