初始化项目，由ModelHub XC社区提供模型
Model: abhinand/gemma-2b-tamil Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal 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
|
||||
167
README.md
Normal file
167
README.md
Normal file
@@ -0,0 +1,167 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
- ta
|
||||
license: other
|
||||
base_model: google/gemma-2b
|
||||
datasets:
|
||||
- wikimedia/wikipedia
|
||||
license_name: gemma-terms-of-use
|
||||
license_link: https://ai.google.dev/gemma/terms
|
||||
model-index:
|
||||
- name: gemma-2b-tamil
|
||||
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: 47.44
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
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: 71.3
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
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: 38.21
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
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: 34.93
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
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: 65.98
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
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: 12.89
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-tamil
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# Gemma 2B Tamil v0.1 Alpha - Base Model [Experimental Release]
|
||||
|
||||
This is a Tamil foundational model continually pretrained from Google Gemma 2B. This is an experiment to see if Gemma can be adapted for Tamil without expanding vocabulary. While the responses may be rusty at times, it shows a lot of promise for a 2B parameter model.
|
||||
|
||||
> **Please Note:** This model, labeled as a FOUNDATIONAL Language Model (LLM), is designed primarily for Causal Language Modeling (LM) purposes. In other words, if you are looking for an instruction following model in Tamil, you may find [abhinand/gemma-2b-it-tamil-v0.1-alpha](https://huggingface.co/abhinand/gemma-2b-it-tamil-v0.1-alpha) more suitable for your needs.
|
||||
|
||||
**Procedure:**
|
||||
|
||||
1. The [Gemma base model](https://huggingface.co/google/gemma-2b) was continually pretrained on all available Tamil Wikipedia data for 3 epochs.
|
||||
2. The updated model was then finetuned on a mix of English and Tamil alpaca datasets for 5 epochs. Finetuned model can be found [here](https://huggingface.co/abhinand/gemma-2b-it-tamil-v0.1-alpha).
|
||||
|
||||
> **Note:** This project is currently under development (FOR TAMIL). The initial pretraining phase may not have been extensive enough, which suggests that the model's performance could improve by extending the pretraining on a larger dataset, such as CulturaX.
|
||||
|
||||
## Model description
|
||||
|
||||
- **Model type:** A 2B parameter GPT-like model continually pretrained on all available Tamil data from [Wikipedia dataset](https://huggingface.co/datasets/wikimedia/wikipedia).
|
||||
- **Language(s):** Bilingual. English and Tamil.
|
||||
- **License:** [Google Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
||||
- **Training Precision:** `bfloat16`
|
||||
- **Training Hardware:** 4x Nvidia RTX 3090 GPUs
|
||||
- **Training Cost:** $20
|
||||
|
||||
## Support my work
|
||||
|
||||
If you appreciate this work and would like to support its continued development, consider [buying me a coffee](https://www.buymeacoffee.com/abhinand.b). Your support is invaluable and greatly appreciated.
|
||||
|
||||
[](https://www.buymeacoffee.com/abhinand.b)
|
||||
|
||||
## Usage Note
|
||||
|
||||
It's important to note that the models have not undergone detoxification. Therefore, while they possess impressive linguistic capabilities, there is a possibility for them to generate content that could be deemed harmful or offensive. We urge users to exercise discretion and supervise the model's outputs closely, especially in public or sensitive applications.
|
||||
|
||||
## Meet the Developers
|
||||
|
||||
Get to know the creators behind this innovative model and follow their contributions to the field:
|
||||
|
||||
- [Abhinand Balachandran](https://www.linkedin.com/in/abhinand-05/)
|
||||
|
||||
We hope this model serves as a valuable tool in your NLP toolkit and look forward to seeing the advancements it will enable in the understanding and generation of the Tamil language.
|
||||
# [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_abhinand__gemma-2b-tamil)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |45.13|
|
||||
|AI2 Reasoning Challenge (25-Shot)|47.44|
|
||||
|HellaSwag (10-Shot) |71.30|
|
||||
|MMLU (5-Shot) |38.21|
|
||||
|TruthfulQA (0-shot) |34.93|
|
||||
|Winogrande (5-shot) |65.98|
|
||||
|GSM8k (5-shot) |12.89|
|
||||
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "google/gemma-2b",
|
||||
"architectures": [
|
||||
"GemmaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 2,
|
||||
"eos_token_id": 1,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 16384,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "gemma",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 18,
|
||||
"num_key_value_heads": 1,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 256000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 2,
|
||||
"eos_token_id": 1,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.39.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4bf96578863d46894b2e3258a7f9edfe43745530242ed628c41bfa18ae631bb
|
||||
size 1948291744
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c41eb9e5a51165e0d561b01fc4e99c8abb55b799d630d976d06a6d01b8c78350
|
||||
size 1981891704
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:babc8691c262de203049e362ec0213b03002a99a2a5452f6ea5c723dd58f6ff1
|
||||
size 1082180304
|
||||
171
model.safetensors.index.json
Normal file
171
model.safetensors.index.json
Normal file
@@ -0,0 +1,171 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5012344832
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<eos>",
|
||||
"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
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
||||
size 4241003
|
||||
51
tokenizer_config.json
Normal file
51
tokenizer_config.json
Normal file
@@ -0,0 +1,51 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<eos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<bos>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<eos>",
|
||||
"legacy": null,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "GemmaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user