HF中国镜像站's logo

AiAF
/
Pretrained-QLoRA-Codename-75567-V1.1

PEFT
Safetensors
GGUF
axolotl
Generated from Trainer
conversational
Model card Files Community
AiAF commited on
Commit
2e8d8a3
·
verified ·
1 Parent(s): 6982d26

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +13 -0
  2. FP16-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-FP16.gguf +3 -0
  3. tokenizer.model → Q2_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q2_K.gguf +2 -2
  4. adapter_model.safetensors → Q3_K_L-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_L.gguf +2 -2
  5. training_args.bin → Q3_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_M.gguf +2 -2
  6. Q3_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_S.gguf +3 -0
  7. Q4_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_0.gguf +3 -0
  8. Q4_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_M.gguf +3 -0
  9. Q4_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_S.gguf +3 -0
  10. Q5_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_0.gguf +3 -0
  11. Q5_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_M.gguf +3 -0
  12. Q5_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_S.gguf +3 -0
  13. Q6_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q6_K.gguf +3 -0
  14. Q8_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q8_0.gguf +3 -0
  15. adapter_config.json +0 -37
  16. config.json +0 -43
  17. special_tokens_map.json +0 -24
  18. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ FP16-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-FP16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Q2_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Q3_K_L-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Q3_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Q3_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Q4_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Q4_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Q4_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Q5_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Q5_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Q5_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Q6_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Q8_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
FP16-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-FP16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b8cadab4277be5ab906c9e5c79f992f3a51a3d7ecc4a860b8d06fb198addb8
3
+ size 14497341856
tokenizer.model → Q2_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q2_K.gguf RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
- size 587404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990b6e956176d20c04a03a0284a837e465c7568cbabed2901f03c16bcfb2351f
3
+ size 2722881952
adapter_model.safetensors → Q3_K_L-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_L.gguf RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80b0b86a0da65dbb7e74d3f70422c882cee4b80131cff4c77526f2114050fca7
3
- size 2684416208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74d19b74fe6aeab4aa5d3270bf7eb02ac8e1c7ca89067303d5d9beecde83541
3
+ size 3825983904
training_args.bin → Q3_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_M.gguf RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:669717c0d642a513afde9c40be0e82002bafe8b5ea4e70454e420936561f78b9
3
- size 6584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b2b8abe31b7b7dd836547f5bd65386b3c40c0991d230d961ca7272171f744f
3
+ size 3522945440
Q3_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b0cfa8c58f942a273a498d9f3a04b9ff0d1968c89c7efbc3e0c4dba35e5630
3
+ size 3168526752
Q4_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19738ce8d621dbc1ab046e7b2dccaedc9daff8a460c1b14ec969a1da59d83541
3
+ size 4113293728
Q4_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fada526c6667eb3e7fe7b7012dd24d65fdb02d208516d2cbd14c900b7c36729
3
+ size 4372816288
Q4_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527996fd02d4ebf990434fdd68cb504102fd505b9300c0670323806cf14cbf30
3
+ size 4144751008
Q5_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18fd4510d7f3b2a664a1c9afb5e95922e26e61983be41844503a6ef8abe16b52
3
+ size 5002486176
Q5_K_M-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177d4e3d98b54df02c61dbeb7d497ffd6ca50dd5d8bb0e90678bd871a3cca0b9
3
+ size 5136179616
Q5_K_S-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4b8df4eec413d7d050e45b4108f8d0a4a10f181d41655431058ba43d6e28d6
3
+ size 5002486176
Q6_K-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb24dcf4e78bfce788f62f6a50c7a641ed330af68d8a8ccdfef7e706a8a463c
3
+ size 5947253152
Q8_0-Pretrained_QLoRA_Codename-75567-V1.1_Ckpt-51-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ed5bbbd8e6ad41150345429f64afb516d443f00eff6b595193f48399b1096e
3
+ size 7702569376
adapter_config.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": null,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 64,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 256,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "o_proj",
27
- "v_proj",
28
- "down_proj",
29
- "gate_proj",
30
- "k_proj",
31
- "up_proj",
32
- "q_proj"
33
- ],
34
- "task_type": "CAUSAL_LM",
35
- "use_dora": false,
36
- "use_rslora": false
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "_attn_implementation_autoset": true,
3
- "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
4
- "architectures": [
5
- "MistralForCausalLM"
6
- ],
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 1,
9
- "eos_token_id": 2,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 14336,
15
- "max_position_embeddings": 32768,
16
- "model_type": "mistral",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 32,
19
- "num_key_value_heads": 8,
20
- "quantization_config": {
21
- "_load_in_4bit": true,
22
- "_load_in_8bit": false,
23
- "bnb_4bit_compute_dtype": "bfloat16",
24
- "bnb_4bit_quant_storage": "bfloat16",
25
- "bnb_4bit_quant_type": "nf4",
26
- "bnb_4bit_use_double_quant": true,
27
- "llm_int8_enable_fp32_cpu_offload": false,
28
- "llm_int8_has_fp16_weight": false,
29
- "llm_int8_skip_modules": null,
30
- "llm_int8_threshold": 6.0,
31
- "load_in_4bit": true,
32
- "load_in_8bit": false,
33
- "quant_method": "bitsandbytes"
34
- },
35
- "rms_norm_eps": 1e-05,
36
- "rope_theta": 1000000.0,
37
- "sliding_window": null,
38
- "tie_word_embeddings": false,
39
- "torch_dtype": "bfloat16",
40
- "transformers_version": "4.49.0",
41
- "use_cache": false,
42
- "vocab_size": 32768
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json DELETED
The diff for this file is too large to render. See raw diff