初始化项目，由ModelHub XC社区提供模型

Model: Felladrin/Smol-Llama-101M-Chat-v1 Source: Original Platform
2026-08-11 04:31:17 +08:00
commit 65b90529b8
9 changed files with 93828 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 +1,239 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation
+base_model: BEE-spoke-data/smol_llama-101M-GQA
+datasets:
+- Open-Orca/SlimOrca-Dedup
+- VMware/open-instruct
+- LDJnr/Capybara
+- cognitivecomputations/ultrachat-uncensored
+- starfishmedical/webGPT_x_dolly
+- THUDM/webglm-qa
+widget:
+  - messages:
+      - role: system
+        content: You are a helpful assistant who gives creative responses.
+      - role: user
+        content: Write the background story of a game about wizards and llamas in a sci-fi world.
+  - messages:
+      - role: system
+        content: A friendly chat between a user and an assistant.
+      - role: user
+        content: Got a question for you!
+      - role: assistant
+        content: "Sure! What's it?"
+      - role: user
+        content: I need to build a simple website. Where should I start learning about web development?
+  - messages:
+      - role: system
+        content: "You are a helpful assistant who provides concise answers to the user's questions."
+      - role: user
+        content: How to become more healthy?
+  - messages:
+      - role: system
+        content: You are a helpful assistant, who always answers with empathy.
+      - role: user
+        content: List the pros and cons of social media.
+  - messages:
+      - role: system
+        content: You are a helpful assistant, who always answers with empathy.
+      - role: user
+        content: Hello!
+      - role: assistant
+        content: Hi! How can I help you today?
+      - role: user
+        content: 'Take a look at the info below.
+
+          - The tape inside the VHS cassettes is very delicate and can be easily ruined,
+          making them unplayable and unrepairable. The reason the tape deteriorates is that
+          the magnetic charge needed for them to work is not permanent, and the magnetic
+          particles end up losing their charge in a process known as remanence decay. These
+          particles could also become demagnetised via being stored too close to a magnetic
+          source.
+      
+          - One of the most significant issues with VHS tapes is that they have moving parts,
+          meaning that there are more occasions when something can go wrong, damaging your
+          footage or preventing it from playing back. The tape itself is a prominent cause
+          of this, and tape slippage can occur. Tapes slippage can be caused when the tape
+          loses its tension, or it has become warped. These problems can occur in storage
+          due to high temperatures or frequent changes in humidity.
+      
+          - VHS tapes deteriorate over time from infrequent or overuse. Neglect means mold
+          and dirt, while overuse can lead to scratches and technical difficulties. This
+          is why old VHS tapes inevitably experience malfunctions after a long period of
+          time. Usually anywhere between 10 to 25+ years.
+      
+          - Some VHS tapes like newer mini DVs and Digital 8 tapes can suffer from digital
+          corruption, meaning that the footage becomes lost and cannot be recovered. These
+          tapes were the steppingstone from VHS to the digital age when capturing footage
+          straight to digital became the norm. Unfortunately,they are susceptible to digital
+          corruption, which causes video pixilation and/or loss of audio.'
+      - role: assistant
+        content: Alright!
+      - role: user
+        content: 'Now I''m going to write my question, and if the info above is useful, you can use them in your response.
+      
+          Ready?'
+      - role: assistant
+        content: Ready for your question!
+      - role: user
+        content: Why do VHS tapes deteriorate over time?
+inference:
+  parameters:
+    max_new_tokens: 250
+    penalty_alpha: 0.5
+    top_k: 4
+    repetition_penalty: 1.105
+model-index:
+- name: Smol-Llama-101M-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: 22.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-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: 28.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-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: 24.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-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: 45.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-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: 50.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-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: 0.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Smol-Llama-101M-Chat-v1
+      name: Open LLM Leaderboard
+---
+
+# A Llama Chat Model of 101M Parameters
+
+- Base model: [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA)
+- Datasets:
+  - [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
+  - [VMware/open-instruct](https://huggingface.co/datasets/VMware/open-instruct)
+  - [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara)
+  - [cognitivecomputations/ultrachat-uncensored](https://huggingface.co/datasets/cognitivecomputations/ultrachat-uncensored)
+  - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly)
+  - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
+- Availability in other ML formats:
+  - GGUF: [Felladrin/gguf-Smol-Llama-101M-Chat-v1](https://huggingface.co/Felladrin/gguf-Smol-Llama-101M-Chat-v1)
+  - ONNX: [Felladrin/onnx-Smol-Llama-101M-Chat-v1](https://huggingface.co/Felladrin/onnx-Smol-Llama-101M-Chat-v1)
+  - MLC: [Felladrin/mlc-q4f16-Smol-Llama-101M-Chat-v1](https://huggingface.co/Felladrin/mlc-q4f16-Smol-Llama-101M-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: 4
+repetition_penalty: 1.105
+```
+
+## [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__Smol-Llama-101M-Chat-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.73|
+|AI2 Reasoning Challenge (25-Shot)|22.87|
+|HellaSwag (10-Shot)              |28.69|
+|MMLU (5-Shot)                    |24.93|
+|TruthfulQA (0-shot)              |45.76|
+|Winogrande (5-shot)              |50.04|
+|GSM8k (5-shot)                   | 0.08|
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": ["LlamaForCausalLM"],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-5,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdacc417fd69784ef63e8b2cc69e0da795771013f07a695da9f79a3f945d30c
+size 405058720
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,61 @@
+{
+  "weight_map": {
+    "lm_head.weight": "model.safetensors",
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.input_layernorm.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors"
+  }
+}
--- a/special_tokens_map.json
+++ b/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": "</s>",
+    "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
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,41 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "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": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}