AbacusResearch/RasGulla1-7b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AbacusResearch/RasGulla1-7b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 15:44:43 +08:00
commit 19028cb424
19 changed files with 91342 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

14
README.md Normal file
View File

@@ -0,0 +1,14 @@
---
language: en
tags:
- finetuned
- vendor-names
- zip-codes
- cities
license: mit
datasets:
- your_dataset_name
---
# Model Description
This is a finetuned model with Lora weights only. This version is trained on Vendor Street name along with Zip, city, and vendor name only.

33
adapter_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": "unsloth",
"target_modules": [
"up_proj",
"down_proj",
"v_proj",
"q_proj",
"k_proj",
"gate_proj",
"o_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}

3
adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b89bad66e9ca8b3c8ea5f9d6aa25d58cc6241b2c84f708bb92e5248e2e47858
size 167832240

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "AbacusResearch/haLLAwa3",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 32000
}

16
mergekit_config.yml Normal file
View File

@@ -0,0 +1,16 @@
slices:
- sources:
- model: abacusai/Slerp-CM-mist-dpo
layer_range: [0, 32]
- model: AbacusResearch/haLLAwa3
layer_range: [0, 32]
merge_method: slerp
base_model: AbacusResearch/haLLAwa3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.4, 0.6, .5]
- filter: mlp
value: [1, 0.5, 0.6, 0.4, 0.5]
- value: 0.5
dtype: bfloat16

3
model-00001-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f41e9fc13ad824e719353971d357770968cd11dda038031f022ba5b12fd6b07f
size 1979773128

3
model-00002-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a75f5bae417d9ca15c5256121564fc032bc23f75fd03dee376ab1106ed5ddaf2
size 1996567640

3
model-00003-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbb56b45616c960617258de4024f99a18de18cc6f9b0ee42db583dec42b9a50a
size 1895895376

3
model-00004-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95438caf49545047cd35f92b13c29958a7b154836e58d3b91bf29fc9a6441f4c
size 1744900168

3
model-00005-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5cace7c3044c715a297bbde0e409ee782baf22993baea633b80f24e4c8025b35
size 1950412280

3
model-00006-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66c72ed42aaa8e943b97a6a4b9e0000cccebb1aeba52666d0c20ea59bb048fb2
size 1979789776

3
model-00007-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d34a8a35e074d30bc4170dcd4a3274fea4fa2192fc15e3c325a2985959bbee60
size 1946252288

3
model-00008-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6323fdaa7bc877c8725f909b3ad8feb7db7e932f78f3242430ec6cfda113aaf8
size 989907328

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"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
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91122
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

42
tokenizer_config.json Normal file
View File

@@ -0,0 +1,42 @@
{
"add_bos_token": true,
"add_eos_token": false,
"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
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}