Downloads · 30 days
34
2% of all-time downloads
RichardErkhov/johnsnowlabs_-_JSL-Med-Sft-Llama-3-8B-gguf
johnsnowlabs_-_JSL-Med-Sft-Llama-3-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
34
2% of all-time downloads
All-time downloads
1.5K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
JSL-Med-Sft-Llama-3-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| JSL-Med-Sft-Llama-3-8B.Q2_K.gguf | Q2_K | 2.96GB |
| JSL-Med-Sft-Llama-3-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| JSL-Med-Sft-Llama-3-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| JSL-Med-Sft-Llama-3-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| JSL-Med-Sft-Llama-3-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| JSL-Med-Sft-Llama-3-8B.Q3_K.gguf | Q3_K | 3.74GB |
| JSL-Med-Sft-Llama-3-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| JSL-Med-Sft-Llama-3-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| JSL-Med-Sft-Llama-3-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| JSL-Med-Sft-Llama-3-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| JSL-Med-Sft-Llama-3-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| JSL-Med-Sft-Llama-3-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| JSL-Med-Sft-Llama-3-8B.Q4_K.gguf | Q4_K | 4.58GB |
| JSL-Med-Sft-Llama-3-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| JSL-Med-Sft-Llama-3-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| JSL-Med-Sft-Llama-3-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| JSL-Med-Sft-Llama-3-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| JSL-Med-Sft-Llama-3-8B.Q5_K.gguf | Q5_K | 5.34GB |
| JSL-Med-Sft-Llama-3-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| JSL-Med-Sft-Llama-3-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| JSL-Med-Sft-Llama-3-8B.Q6_K.gguf | Q6_K | 6.14GB |
| JSL-Med-Sft-Llama-3-8B.Q8_0.gguf | Q8_0 | 7.95GB |
tags:
This model is developed by John Snow Labs.
This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at [email protected].
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "johnsnowlabs/JSL-Med-Sft-Llama-3-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|---|
| stem | N/A | none | 0 | acc_norm | 0.5803 | ± | 0.0067 |
| none | 0 | acc | 0.6141 | ± | 0.0057 | ||
| - medmcqa | Yaml | none | 0 | acc | 0.5752 | ± | 0.0076 |
| none | 0 | acc_norm | 0.5752 | ± | 0.0076 | ||
| - medqa_4options | Yaml | none | 0 | acc | 0.5970 | ± | 0.0138 |
| none | 0 | acc_norm | 0.5970 | ± | 0.0138 | ||
| - anatomy (mmlu) | 0 | none | 0 | acc | 0.6963 | ± | 0.0397 |
| - clinical_knowledge (mmlu) | 0 | none | 0 | acc | 0.7472 | ± | 0.0267 |
| - college_biology (mmlu) | 0 | none | 0 | acc | 0.7847 | ± | 0.0344 |
| - college_medicine (mmlu) | 0 | none | 0 | acc | 0.6185 | ± | 0.0370 |
| - medical_genetics (mmlu) | 0 | none | 0 | acc | 0.8300 | ± | 0.0378 |
| - professional_medicine (mmlu) | 0 | none | 0 | acc | 0.7022 | ± | 0.0278 |
| - pubmedqa | 1 | none | 0 | acc | 0.7480 | ± | 0.0194 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|---|
| stem | N/A | none | 0 | acc_norm | 0.5803 | ± | 0.0067 |
| none | 0 | acc | 0.6141 | ± | 0.0057 |