初始化项目，由ModelHub XC社区提供模型

Model: dphn/Dolphin3.0-Llama3.1-8B Source: Original Platform
2026-05-26 15:09:15 +08:00
commit dde45fdbab
14 changed files with 369 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,240 @@
+---
+license: llama3.1
+datasets:
+- OpenCoder-LLM/opc-sft-stage1
+- OpenCoder-LLM/opc-sft-stage2
+- microsoft/orca-agentinstruct-1M-v1
+- microsoft/orca-math-word-problems-200k
+- NousResearch/hermes-function-calling-v1
+- AI-MO/NuminaMath-CoT
+- AI-MO/NuminaMath-TIR
+- allenai/tulu-3-sft-mixture
+- cognitivecomputations/dolphin-coder
+- HuggingFaceTB/smoltalk
+- cognitivecomputations/samantha-data
+- m-a-p/CodeFeedback-Filtered-Instruction
+- m-a-p/Code-Feedback
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B
+model-index:
+- name: Dolphin3.0-Llama3.1-8B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 76.21
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 27.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 10.5
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 4.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      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: 8.97
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      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: 22.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=cognitivecomputations%2FDolphin3.0-Llama3.1-8B
+      name: Open LLM Leaderboard
+---
+
+# Dolphin 3.0 Llama 3.1 8B 🐬
+Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3)
+
+Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)
+
+[![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations)
+Discord: https://discord.gg/cognitivecomputations
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/cNCs1TBD3FelWCJGkZ3cd.png" width="600" />
+
+## Sponsors
+Our appreciation for the generous sponsors of Dolphin 3.0:
+- [Crusoe Cloud](https://crusoe.ai/) - provided 16x L40s for training and evals
+- [Akash](https://akash.network/) - provided on-demand 8x H100 for training
+- [Lazarus](https://www.lazarusai.com/) - provided 16x H100 for training
+- [Cerebras](https://cerebras.ai/) - provided excellent and fast inference services for data labeling
+- [Andreessen Horowitz](https://a16z.com/) - provided a [grant](https://a16z.com/supporting-the-open-source-ai-community/) that make Dolphin 1.0 possible and enabled me to bootstrap my homelab
+
+## What is Dolphin?
+
+Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models.  Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
+
+Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini.  But these models present problems for businesses seeking to include AI in their products.
+1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
+2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
+3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
+4) They can see all your queries and they can potentially use that data in ways you wouldn't want.
+Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt.  You decide the alignment.  You have control of your data.  Dolphin does not impose its ethics or guidelines on you.  You are the one who decides the guidelines.
+
+Dolphin belongs to YOU, it is your tool, an extension of your will.
+Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
+
+https://erichartford.com/uncensored-models
+
+## Chat Template
+
+We use ChatML for the chat template.
+
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## System Prompt
+
+In Dolphin, the system prompt is what you use to set the tone and alignment of the responses.  You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
+
+Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
+
+Example use of system prompt:
+
+```
+<|im_start|>system
+You are Dolphin, a golang coding assistant.  you only code in golang.  If the user requests any other programming language, return the solution in golang instead.<|im_end|>
+<|im_start|>user
+Please implement A* using python<|im_end|>
+<|im_start|>assistant
+```
+
+## Sample Outputs
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/C-r1X13UBjnUUNb0q2JLV.png" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/4l3KAZiKej2ON7i35PsOa.png" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/1ZalmR66LnwhEQQEFttlu.png" width="600" />
+
+## How to use
+
+There are many ways to use a huggingface model including:
+- ollama
+- LM Studio
+- Huggingface Transformers library
+- vllm
+- sglang
+- tgi
+
+### ollama
+- [Install ollama](https://ollama.com/download)
+- ```ollama run hf.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF:Q4_0```
+- ```/set system <your system prompt>```
+
+## Evals
+
+TBD
+
+## Appreciation
+
+Respect and thanks to the creators of the open source datasets that were used:
+- [OpenCoder-LLM](https://huggingface.co/OpenCoder-LLM) (opc-sft-stage1, opc-sft-stage2)
+- [microsoft](https://huggingface.co/OpenCoder-LLM) (orca-agentinstruct-1M-v1, orca-math-word-problems-200k)
+- [NousResearch](https://huggingface.co/NousResearch) (hermes-function-calling-v1)
+- [AI-MO](https://huggingface.co/AI-MO) (NuminaMath-CoT, NuminaMath-TIR)
+- [allenai](https://huggingface.co/allenai) (tulu-3-sft-mixture)
+- [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) (smoltalk)
+- [m-a-p](https://huggingface.co/m-a-p) (CodeFeedback-Filtered-Instruction, Code-Feedback)
+
+Special thanks to 
+- Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
+- [RLHFlow](https://huggingface.co/RLHFlow) for the excellent reward model used to filter the datasets
+- Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.
+
+
+
+# [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/cognitivecomputations__Dolphin3.0-Llama3.1-8B-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=cognitivecomputations%2FDolphin3.0-Llama3.1-8B&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    24.97|
+|IFEval (0-Shot)    |    76.21|
+|BBH (3-Shot)       |    27.63|
+|MATH Lvl 5 (4-Shot)|    10.50|
+|GPQA (0-shot)      |     4.36|
+|MuSR (0-shot)      |     8.97|
+|MMLU-PRO (5-shot)  |    22.13|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "cognitivecomputations/Dolphin-3.0-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [128256, 128001, 128008, 128009],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 128258
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "others", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [128256, 128001, 128008, 128009],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.1"
+}
--- a/model-00001-of-00004.safetensors
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cefb45d70138704e88ef40aabc345bca71aa916e1603c3f111022c3759529d6
+size 4976715056
--- a/model-00002-of-00004.safetensors
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d9c8a8a3d8d4ae145fc4a9c846c877bb485a2d3fff81924fe4918c2eb17ba8
+size 4999802720
--- a/model-00003-of-00004.safetensors
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34806daa7441ecb31d7bbbfdf17c7bef2bbad544d550da1cb99e300af36ebf8c
+size 4915916176
--- a/model-00004-of-00004.safetensors
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce0b3146956b8c5fce3a886d953b3aa2746247062253572721dd9ebbf61dfd3
+size 1168155192
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e675e9f23a294baff7e3a614ae39e4cef7f2b7aef18cf8baf18515eec29ef1
+size 23950
--- 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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_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:e40b93124a3e29f62d5f4ff41be56cb2af34ecacf9239acd9da53a98860380b5
+size 17210298
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdbfb2e4f29eb2f7e8b9278034e76ea38ad252ac3005a9204879b2b666733b9
+size 51234
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed29d41b391f7b81d14769a2e07bd879a469abf30ca105fdf5527e82ad734ace
+size 1063526
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "others", "allow_remote": true}`