Hugging Face's logo

ewof
/
koishi-7b-qlora

Text Generation
Transformers
PyTorch
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
ewof commited on
Commit
c774d60
·
1 Parent(s): 0e5ce15

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +13 -0
  2. config.json +1 -24
  3. ggml-model-F16.gguf +3 -0
  4. ggml-model-Q2_K.gguf +3 -0
  5. ggml-model-Q3_K_L.gguf +3 -0
  6. ggml-model-Q3_K_M.gguf +3 -0
  7. ggml-model-Q3_K_S.gguf +3 -0
  8. ggml-model-Q4_0.gguf +3 -0
  9. ggml-model-Q4_K_M.gguf +3 -0
  10. ggml-model-Q4_K_S.gguf +3 -0
  11. ggml-model-Q5_0.gguf +3 -0
  12. ggml-model-Q5_K_M.gguf +3 -0
  13. ggml-model-Q5_K_S.gguf +3 -0
  14. ggml-model-Q6_K.gguf +3 -0
  15. ggml-model-Q8_0.gguf +3 -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
+ ggml-model-F16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ ggml-model-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ ggml-model-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
39
+ ggml-model-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ ggml-model-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
41
+ ggml-model-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
42
+ ggml-model-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ ggml-model-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ ggml-model-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ ggml-model-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ ggml-model-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ ggml-model-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
48
+ ggml-model-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,26 +1,3 @@
1
  {
2
- "_name_or_path": "/home/models/mistralai_Mistral-7B-v0.1",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "bfloat16",
23
- "transformers_version": "4.36.0.dev0",
24
- "use_cache": false,
25
- "vocab_size": 32003
26
  }
 
1
  {
2
+ "model_type": "mistral"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
ggml-model-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47410f61c098fe7f2ee5f58740f4a6e0a5aee46c93d8c95efc7465bfe06e855f
3
+ size 14330142272
ggml-model-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d250a266a9f3c610f7bb03160c2a03e2b41723f5dcd87616be5771fe996fc811
3
+ size 3083111936
ggml-model-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5188aa44a9e5132f1deb5a4269c68ccdd866a2da2de10e65c9b09834ad8ea3e
3
+ size 3822039776
ggml-model-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c147c65e6f76f70ad2d44ae3d2cc151b9dac4d0bd96cbf2aa2688b3decf95e3d
3
+ size 3519001312
ggml-model-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769ac59b590d86fb7e80b4dbf42a8d4cfb8bc78a6e39f85f8d9e1f0cdb014f3b
3
+ size 3164582624
ggml-model-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46809db084eeb7fc304f42d9e2bb32fcbc21c5a0b09af969141522b4dedf3b3f
3
+ size 4108933440
ggml-model-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78d71aa312259046a9a5f79326f84f345f9e67f40f7f3d0f159fbf72c4191c5
3
+ size 4368456000
ggml-model-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198838d06bd81e141efddf63efe8d5fa501720e52ebc001c786cc9fdddee20b8
3
+ size 4140390720
ggml-model-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db08f584603582fcace07b5d181afa49b54b1acca5d7910839913c3a9d3f573
3
+ size 4997734208
ggml-model-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d24d00d273fae0a2a255828d103cdcf7ffc4c7d259eb3b2c5a78c9b9963786
3
+ size 5131427648
ggml-model-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08672bd06e05ecc88af982a3467be7de63b09a04765541fab731acd80120fb42
3
+ size 4997734208
ggml-model-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5c3d296c5b84a7a5d6aa015917f77494ef083a1ebff98fb711ec1a5cf99001
3
+ size 5942085024
ggml-model-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ac6db44b566e4ed2c20735cb386d7faf985a5f0fd8c3ad2525a8ec203b7f27
3
+ size 7695883488