Files changed (4) hide show
  1. .gitattributes +0 -1
  2. Modelfile +0 -4
  3. README.md +2 -27
  4. openthaigpt-Q4_K_M.gguf +0 -3
.gitattributes CHANGED
@@ -34,4 +34,3 @@ saved_model/**/* 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
- openthaigpt-Q4_K_M.gguf 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
 
Modelfile DELETED
@@ -1,4 +0,0 @@
1
- FROM ./openthaigpt-Q4_K_M.gguf
2
- TEMPLATE """[INST] <<SYS>>{{ .System }}<</SYS>>
3
-
4
- {{ .Prompt }} [/INST]"""
 
 
 
 
 
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: llama2
3
  language:
4
  - th
5
  - en
@@ -44,17 +44,6 @@ Thai language multiple choice exams, Test on unseen test sets, Zero-shot learnin
44
 
45
  (Updated on: 7 April 2024)
46
 
47
- ## Benchmark on M3Exam evaluated by an external party (Float16.cloud)
48
-
49
- | **Models** | **ENGLISH (M3EXAM)** | **THAI (M3EXAM)** |
50
- |---------------------|------------------|---------------|
51
- | <b style="color:blue">OTG-7b</b> | <b style="color:blue">40.92 %</b> | <b style="color:blue">25.14 %</b> |
52
- | OTG-13b | 53.69 % | 36.49 % |
53
- | OTG-70b | 72.58 %< | 48.29 % |
54
- | GPT-3.5-turbo-0613* | - | 34.1 % |
55
- | GPT-4-0613* | - | 56.0 % |
56
- More information: https://blog.float16.cloud/the-first-70b-thai-llm/
57
-
58
  ## Licenses
59
  **Source Code**: License Apache Software License 2.0.<br>
60
  **Weight**: Research and **Commercial uses**.<br>
@@ -236,20 +225,6 @@ curl --location 'http://localhost:8000/completion' \
236
  }'
237
  ```
238
 
239
- ### Ollama
240
-
241
- There are two ways to run on ollama
242
-
243
- 1. From this repo Modelfile and 4 bit quantized gguf
244
- ```bash
245
- ollama create -f ./Modelfile
246
- ```
247
-
248
- 2. From Ollama CLI
249
- ```bash
250
- ollama run pacozaa/openthaigpt
251
- ```
252
-
253
  ### GPU Memory Requirements
254
  | **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
255
  |------------------|----------------|------------------------|------------------------|---------------------------------------------|
@@ -275,4 +250,4 @@ ollama run pacozaa/openthaigpt
275
  * Kriangkrai Saetan (kraitan.ss21@gmail.com)
276
  * Pitikorn Khlaisamniang (pitikorn32@gmail.com)
277
 
278
- <i>Disclaimer: Provided responses are not guaranteed.</i>
 
1
  ---
2
+ license: apache-2.0
3
  language:
4
  - th
5
  - en
 
44
 
45
  (Updated on: 7 April 2024)
46
 
 
 
 
 
 
 
 
 
 
 
 
47
  ## Licenses
48
  **Source Code**: License Apache Software License 2.0.<br>
49
  **Weight**: Research and **Commercial uses**.<br>
 
225
  }'
226
  ```
227
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
228
  ### GPU Memory Requirements
229
  | **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
230
  |------------------|----------------|------------------------|------------------------|---------------------------------------------|
 
250
  * Kriangkrai Saetan (kraitan.ss21@gmail.com)
251
  * Pitikorn Khlaisamniang (pitikorn32@gmail.com)
252
 
253
+ <i>Disclaimer: Provided responses are not guaranteed.</i>
openthaigpt-Q4_K_M.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9fe7f5dfb4adaac2211b8159297d3689abb9c94259a9e8b75a86348cf6fdda
3
- size 4132760544