初始化项目,由ModelHub XC社区提供模型

Model: M4-ai/TinyMistral-248M-v3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-12 18:23:18 +08:00
commit 5fd8966cf4
8 changed files with 268562 additions and 0 deletions

35
.gitattributes vendored Normal file
View File

@@ -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

244
README.md Normal file
View File

@@ -0,0 +1,244 @@
---
language:
- en
license: apache-2.0
datasets:
- Locutusque/TM-DATA-V2
- LLM360/TxT360
- mlfoundations/dclm-baseline-1.0
- Skylion007/openwebtext
- JeanKaddour/minipile
- eminorhan/gutenberg_en
model-index:
- name: TinyMistral-248M-v3
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: 16.39
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
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: 1.78
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
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: 0.0
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
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: 0.0
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
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: 5.15
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
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: 1.47
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
name: Open LLM Leaderboard
---
still in training. Trained on about ~21 billion tokens so far.
| Tasks |Version| Filter |n-shot| Metric | | Value | |Stderr|
|----------------------------------------|-------|----------------|-----:|-----------|---|------:|---|-----:|
|Open LLM Leaderboard | N/A| | | | | | | |
| - arc_challenge | 1|none | 25|acc |↑ | 0.2005|± |0.0117|
| | |none | 25|acc_norm |↑ | 0.2406|± |0.0125|
| - gsm8k | 3|flexible-extract| 5|exact_match|↑ | 0.0083|± |0.0025|
| | |strict-match | 5|exact_match|↑ | 0.0000|± |0.0000|
| - hellaswag | 1|none | 10|acc |↑ | 0.2724|± |0.0044|
| | |none | 10|acc_norm |↑ | 0.2838|± |0.0045|
| - mmlu | 2|none | |acc |↑ | 0.2290|± |0.0035|
| - humanities | 2|none | |acc |↑ | 0.2380|± |0.0062|
| - formal_logic | 1|none | 5|acc |↑ | 0.2460|± |0.0385|
| - high_school_european_history | 1|none | 5|acc |↑ | 0.1818|± |0.0301|
| - high_school_us_history | 1|none | 5|acc |↑ | 0.2647|± |0.0310|
| - high_school_world_history | 1|none | 5|acc |↑ | 0.2911|± |0.0296|
| - international_law | 1|none | 5|acc |↑ | 0.2149|± |0.0375|
| - jurisprudence | 1|none | 5|acc |↑ | 0.2685|± |0.0428|
| - logical_fallacies | 1|none | 5|acc |↑ | 0.2209|± |0.0326|
| - moral_disputes | 1|none | 5|acc |↑ | 0.2457|± |0.0232|
| - moral_scenarios | 1|none | 5|acc |↑ | 0.2369|± |0.0142|
| - philosophy | 1|none | 5|acc |↑ | 0.1865|± |0.0221|
| - prehistory | 1|none | 5|acc |↑ | 0.1975|± |0.0222|
| - professional_law | 1|none | 5|acc |↑ | 0.2432|± |0.0110|
| - world_religions | 1|none | 5|acc |↑ | 0.3099|± |0.0355|
| - other | 2|none | |acc |↑ | 0.2375|± |0.0076|
| - business_ethics | 1|none | 5|acc |↑ | 0.3200|± |0.0469|
| - clinical_knowledge | 1|none | 5|acc |↑ | 0.2226|± |0.0256|
| - college_medicine | 1|none | 5|acc |↑ | 0.1965|± |0.0303|
| - global_facts | 1|none | 5|acc |↑ | 0.1800|± |0.0386|
| - human_aging | 1|none | 5|acc |↑ | 0.3004|± |0.0308|
| - management | 1|none | 5|acc |↑ | 0.1942|± |0.0392|
| - marketing | 1|none | 5|acc |↑ | 0.2735|± |0.0292|
| - medical_genetics | 1|none | 5|acc |↑ | 0.3000|± |0.0461|
| - miscellaneous | 1|none | 5|acc |↑ | 0.2478|± |0.0154|
| - nutrition | 1|none | 5|acc |↑ | 0.2222|± |0.0238|
| - professional_accounting | 1|none | 5|acc |↑ | 0.2021|± |0.0240|
| - professional_medicine | 1|none | 5|acc |↑ | 0.1912|± |0.0239|
| - virology | 1|none | 5|acc |↑ | 0.2590|± |0.0341|
| - social sciences | 2|none | |acc |↑ | 0.2203|± |0.0075|
| - econometrics | 1|none | 5|acc |↑ | 0.2368|± |0.0400|
| - high_school_geography | 1|none | 5|acc |↑ | 0.2020|± |0.0286|
| - high_school_government_and_politics| 1|none | 5|acc |↑ | 0.1865|± |0.0281|
| - high_school_macroeconomics | 1|none | 5|acc |↑ | 0.2205|± |0.0210|
| - high_school_microeconomics | 1|none | 5|acc |↑ | 0.2143|± |0.0267|
| - high_school_psychology | 1|none | 5|acc |↑ | 0.1908|± |0.0168|
| - human_sexuality | 1|none | 5|acc |↑ | 0.2672|± |0.0388|
| - professional_psychology | 1|none | 5|acc |↑ | 0.2386|± |0.0172|
| - public_relations | 1|none | 5|acc |↑ | 0.1727|± |0.0362|
| - security_studies | 1|none | 5|acc |↑ | 0.2367|± |0.0272|
| - sociology | 1|none | 5|acc |↑ | 0.2488|± |0.0306|
| - us_foreign_policy | 1|none | 5|acc |↑ | 0.2600|± |0.0441|
| - stem | 2|none | |acc |↑ | 0.2157|± |0.0073|
| - abstract_algebra | 1|none | 5|acc |↑ | 0.2200|± |0.0416|
| - anatomy | 1|none | 5|acc |↑ | 0.1778|± |0.0330|
| - astronomy | 1|none | 5|acc |↑ | 0.1908|± |0.0320|
| - college_biology | 1|none | 5|acc |↑ | 0.2778|± |0.0375|
| - college_chemistry | 1|none | 5|acc |↑ | 0.2200|± |0.0416|
| - college_computer_science | 1|none | 5|acc |↑ | 0.2100|± |0.0409|
| - college_mathematics | 1|none | 5|acc |↑ | 0.2100|± |0.0409|
| - college_physics | 1|none | 5|acc |↑ | 0.2157|± |0.0409|
| - computer_security | 1|none | 5|acc |↑ | 0.2700|± |0.0446|
| - conceptual_physics | 1|none | 5|acc |↑ | 0.2638|± |0.0288|
| - electrical_engineering | 1|none | 5|acc |↑ | 0.2483|± |0.0360|
| - elementary_mathematics | 1|none | 5|acc |↑ | 0.2037|± |0.0207|
| - high_school_biology | 1|none | 5|acc |↑ | 0.1774|± |0.0217|
| - high_school_chemistry | 1|none | 5|acc |↑ | 0.2020|± |0.0282|
| - high_school_computer_science | 1|none | 5|acc |↑ | 0.2500|± |0.0435|
| - high_school_mathematics | 1|none | 5|acc |↑ | 0.2148|± |0.0250|
| - high_school_physics | 1|none | 5|acc |↑ | 0.2053|± |0.0330|
| - high_school_statistics | 1|none | 5|acc |↑ | 0.1481|± |0.0242|
| - machine_learning | 1|none | 5|acc |↑ | 0.3125|± |0.0440|
| - truthfulqa_gen | 3|none | 0|bleu_acc |↑ | 0.2362|± |0.0149|
| | |none | 0|bleu_diff |↑ |-1.0138|± |0.2569|
| | |none | 0|bleu_max |↑ | 7.9522|± |0.4088|
| | |none | 0|rouge1_acc |↑ | 0.2595|± |0.0153|
| | |none | 0|rouge1_diff|↑ |-1.9129|± |0.4349|
| | |none | 0|rouge1_max |↑ |21.7885|± |0.7307|
| | |none | 0|rouge2_acc |↑ | 0.1200|± |0.0114|
| | |none | 0|rouge2_diff|↑ |-1.9771|± |0.3475|
| | |none | 0|rouge2_max |↑ | 9.0199|± |0.5842|
| | |none | 0|rougeL_acc |↑ | 0.2570|± |0.0153|
| | |none | 0|rougeL_diff|↑ |-1.8812|± |0.4185|
| | |none | 0|rougeL_max |↑ |19.6284|± |0.6850|
| - truthfulqa_mc1 | 2|none | 0|acc |↑ | 0.1983|± |0.0140|
| - truthfulqa_mc2 | 2|none | 0|acc |↑ | 0.3861|± |0.0147|
| - winogrande | 1|none | 5|acc |↑ | 0.4972|± |0.0141|
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|-------------------|------:|------|------|------|---|-----:|---|-----:|
| - mmlu | 2|none | |acc |↑ |0.2290|± |0.0035|
| - humanities | 2|none | |acc |↑ |0.2380|± |0.0062|
| - other | 2|none | |acc |↑ |0.2375|± |0.0076|
| - social sciences| 2|none | |acc |↑ |0.2203|± |0.0075|
| - stem | 2|none | |acc |↑ |0.2157|± |0.0073|
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|---------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|agieval_nous | 0|none | |acc_norm|↑ |0.2133|± |0.0081|
| - agieval_aqua_rat | 1|none | 0|acc |↑ |0.2047|± |0.0254|
| | |none | 0|acc_norm|↑ |0.1969|± |0.0250|
| - agieval_logiqa_en | 1|none | 0|acc |↑ |0.2043|± |0.0158|
| | |none | 0|acc_norm|↑ |0.2304|± |0.0165|
| - agieval_lsat_ar | 1|none | 0|acc |↑ |0.1739|± |0.0250|
| | |none | 0|acc_norm|↑ |0.1957|± |0.0262|
| - agieval_lsat_lr | 1|none | 0|acc |↑ |0.1549|± |0.0160|
| | |none | 0|acc_norm|↑ |0.1608|± |0.0163|
| - agieval_lsat_rc | 1|none | 0|acc |↑ |0.1636|± |0.0226|
| | |none | 0|acc_norm|↑ |0.2119|± |0.0250|
| - agieval_sat_en | 1|none | 0|acc |↑ |0.2670|± |0.0309|
| | |none | 0|acc_norm|↑ |0.2621|± |0.0307|
| - agieval_sat_en_without_passage| 1|none | 0|acc |↑ |0.2670|± |0.0309|
| | |none | 0|acc_norm|↑ |0.2621|± |0.0307|
| - agieval_sat_math | 1|none | 0|acc |↑ |0.2182|± |0.0279|
| | |none | 0|acc_norm|↑ |0.2318|± |0.0285|
|arc_challenge | 1|none | 0|acc |↑ |0.1945|± |0.0116|
| | |none | 0|acc_norm|↑ |0.2372|± |0.0124|
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.3861|± |0.0147|
| Groups |Version|Filter|n-shot| Metric | |Value | |Stderr|
|------------|------:|------|------|--------|---|-----:|---|-----:|
|agieval_nous| 0|none | |acc_norm|↑ |0.2133|± |0.0081|
# [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_M4-ai__TinyMistral-248M-v3)
| Metric |Value|
|-------------------|----:|
|Avg. | 4.13|
|IFEval (0-Shot) |16.39|
|BBH (3-Shot) | 1.78|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot) | 0.00|
|MuSR (0-shot) | 5.15|
|MMLU-PRO (5-shot) | 1.47|

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "M4-ai/TinyMistral-248M-v3",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 32,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 12,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 32,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.2",
"use_cache": true,
"vocab_size": 32005
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.45.2"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9432ee6e0681473a9ed513e43362d9911832f9a5c7faded76f46ec66c55a9d3b
size 496060688

34
special_tokens_map.json Normal file
View File

@@ -0,0 +1,34 @@
{
"additional_special_tokens": [
"<|ASSISTANT|>",
"<|USER|>"
],
"bos_token": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"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
}
}

268122
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

91
tokenizer_config.json Normal file
View File

@@ -0,0 +1,91 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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
},
"32000": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<|ASSISTANT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<|USER|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|ASSISTANT|>",
"<|USER|>"
],
"bos_token": "<|bos|>",
"chat_template": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}{%- else -%}{{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'<|im_start|>assistant\n'-}}{%- endif -%}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": true,
"max_length": 1536,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}