初始化项目，由ModelHub XC社区提供模型

Model: Felladrin/Pythia-31M-Chat-v1 Source: Original Platform
2026-11-02 04:26:17 +08:00
commit 3bf3fe1b9d
7 changed files with 100889 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 +1,281 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: EleutherAI/pythia-31m
+datasets:
+- totally-not-an-llm/EverythingLM-data-V3
+- databricks/databricks-dolly-15k
+- THUDM/webglm-qa
+- starfishmedical/webGPT_x_dolly
+- Amod/mental_health_counseling_conversations
+- sablo/oasst2_curated
+- cognitivecomputations/wizard_vicuna_70k_unfiltered
+- mlabonne/chatml_dpo_pairs
+pipeline_tag: text-generation
+widget:
+  - messages:
+      - role: system
+        content: >-
+          You are a career counselor. The user will provide you with an individual
+          looking for guidance in their professional life, and your task is to assist
+          them in determining what careers they are most suited for based on their skills,
+          interests, and experience. You should also conduct research into the various
+          options available, explain the job market trends in different industries, and
+          advice on which qualifications would be beneficial for pursuing particular fields.
+      - role: user
+        content: Heya!
+      - role: assistant
+        content: Hi! How may I help you?
+      - role: user
+        content: >-
+          I am interested in developing a career in software engineering. What
+          would you recommend me to do?
+  - messages:
+      - role: system
+        content: "You are a helpful assistant who answers user's questions with details and curiosity."
+      - role: user
+        content: What are some potential applications for quantum computing?
+  - messages:
+      - role: system
+        content: You are a highly knowledgeable assistant. Help the user as much as you can.
+      - role: user
+        content: What are some steps I can take to become a healthier person?
+inference:
+  parameters:
+    max_new_tokens: 250
+    penalty_alpha: 0.5
+    top_k: 2
+    repetition_penalty: 1.0016
+model-index:
+- name: Pythia-31M-Chat-v1
+  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: 22.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      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: 25.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      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: 23.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      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: 47.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      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: 0.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Pythia-31M-Chat-v1
+      name: Open LLM Leaderboard
+---
+
+# A Pythia Chat Model of 31M Parameters
+
+- Base model: [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m)
+- Availability in other ML formats:
+  - GGUF: [Felladrin/gguf-Pythia-31M-Chat-v1](https://huggingface.co/Felladrin/gguf-Pythia-31M-Chat-v1)
+  - ONNX: [Felladrin/onnx-Pythia-31M-Chat-v1](https://huggingface.co/Felladrin/onnx-Pythia-31M-Chat-v1)
+
+## Recommended prompt format
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{user_message}<|im_end|>
+<|im_start|>assistant
+```
+
+## Recommended inference parameters
+
+```yml
+penalty_alpha: 0.5
+top_k: 2
+repetition_penalty: 1.0016
+```
+
+## Datasets and parameters used for training
+
+| Dataset | License Type |
+|---------|--------------|
+| [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3) | mit |
+| [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) | cc-by-sa-3.0 |
+| [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa) | apache-2.0 |
+| [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly) | cc-by-sa-3.0 |
+| [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations) | openrail |
+| [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated) | apache-2.0 |
+| [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered) | apache-2.0 |
+| [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) | apache-2.0 |
+
+```python
+SFTTrainer(
+    model,
+    train_dataset=train_dataset,
+    dataset_text_field="text",
+    eval_dataset=eval_dataset,
+    max_seq_length=2048,
+    packing=True,
+    args=TrainingArguments(
+        learning_rate=2e-6,
+        per_device_train_batch_size=1,
+        per_device_eval_batch_size=1,
+        gradient_accumulation_steps=16,
+        lr_scheduler_type="cosine",
+        num_train_epochs=1,
+        logging_strategy="steps",
+        save_strategy="steps",
+        evaluation_strategy="steps",
+        logging_steps=10,
+        eval_steps=10,
+        save_steps=10,
+        warmup_steps=50,
+        load_best_model_at_end=True,
+        metric_for_best_model="eval_loss",
+        greater_is_better=False,
+        weight_decay=0.01,
+        save_total_limit=10,
+        neftune_noise_alpha=5,
+    ),
+    callbacks=[
+        EarlyStoppingCallback(
+            early_stopping_patience=3,
+            early_stopping_threshold=0.005
+        ),
+    ],
+)
+```
+
+```python
+DPOTrainer(
+    model,
+    beta=0.1,
+    train_dataset=dataset,
+    tokenizer=tokenizer,
+    eval_dataset=eval_dataset,
+    max_length=1536,
+    max_prompt_length=1024,
+    args=TrainingArguments(
+        learning_rate=2e-6,
+        per_device_train_batch_size=1,
+        per_device_eval_batch_size=1,
+        gradient_accumulation_steps=1,
+        lr_scheduler_type="cosine",
+        num_train_epochs=1,
+        logging_strategy="steps",
+        save_strategy="steps",
+        evaluation_strategy="steps",
+        logging_steps=1,
+        eval_steps=1,
+        save_steps=1,
+        warmup_steps=0,
+        load_best_model_at_end=True,
+        metric_for_best_model="eval_loss",
+        greater_is_better=False,
+        weight_decay=0.0,
+        neftune_noise_alpha=5,
+        remove_unused_columns=False,
+    ),
+    callbacks=[
+        EarlyStoppingCallback(
+            early_stopping_patience=3,
+            early_stopping_threshold=0.005
+        ),
+    ],
+)
+```
+
+## [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_Felladrin__Pythia-31M-Chat-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |19.92|
+|AI2 Reasoning Challenge (25-Shot)|22.70|
+|HellaSwag (10-Shot)              |25.60|
+|MMLU (5-Shot)                    |23.24|
+|TruthfulQA (0-shot)              | 0.00|
+|Winogrande (5-shot)              |47.99|
+|GSM8k (5-shot)                   | 0.00|
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "architectures": ["GPTNeoXForCausalLM"],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-5,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50da98b79aa17cd03b2a86e9571a60bdd186c9bb46af3675284ad9801244e1be
+size 121987544
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}